1
00:00:08,400 --> 00:00:19,840
Speaker 1: Pushkin. Around twenty ten, Sarah Rudd was rooting for this

2
00:00:20,079 --> 00:00:23,639
Speaker 1: British soccer team. It was a team called Blackpool. It

3
00:00:23,680 --> 00:00:26,880
Speaker 1: had been her great grandfather's favorite team. She was really

4
00:00:26,920 --> 00:00:30,560
Speaker 1: into it, but she started getting annoyed by this one player.

5
00:00:30,960 --> 00:00:32,400
Speaker 1: His name was Charlie Adam.

6
00:00:32,720 --> 00:00:36,479
Speaker 2: He just loved to take shots from really long distance

7
00:00:36,760 --> 00:00:40,080
Speaker 2: and it drove me crazy. Every possession just kind of

8
00:00:40,200 --> 00:00:43,839
Speaker 2: ended with him taking like these random shots and it's like,

9
00:00:43,920 --> 00:00:44,800
Speaker 2: what a waste?

10
00:00:44,880 --> 00:00:45,440
Speaker 3: What are you doing.

11
00:00:45,960 --> 00:00:48,879
Speaker 1: Sarah was living in Seattle working for Microsoft as a

12
00:00:48,920 --> 00:00:53,760
Speaker 1: software engineer, but she really wanted to get into sports analytics. Basically,

13
00:00:53,880 --> 00:00:56,880
Speaker 1: she wanted to do moneyball, but for soccer. And then

14
00:00:57,000 --> 00:01:00,480
Speaker 1: she discovered that this sports data company called stat DNA

15
00:01:00,760 --> 00:01:04,360
Speaker 1: was hosting a contest, a contest where people could use

16
00:01:04,400 --> 00:01:10,200
Speaker 1: the company's soccer tracking data to generate analytical insights. And

17
00:01:10,240 --> 00:01:13,399
Speaker 1: she thought this could be my chance, This could be

18
00:01:13,440 --> 00:01:16,800
Speaker 1: my chance to break into the industry, and also at

19
00:01:16,800 --> 00:01:20,120
Speaker 1: the same time that that guy, Charlie Adam really should

20
00:01:20,160 --> 00:01:22,720
Speaker 1: not be taking those long shots.

21
00:01:22,959 --> 00:01:27,440
Speaker 2: I'm a big fan of searching for inspiration elsewhere, so

22
00:01:27,720 --> 00:01:29,959
Speaker 2: I started just looking around and seeing like, well, what

23
00:01:30,040 --> 00:01:30,759
Speaker 2: have other people done?

24
00:01:30,800 --> 00:01:34,679
Speaker 3: In this space, and it turns out for soccer not much.

25
00:01:35,080 --> 00:01:38,040
Speaker 2: But there was some really interesting papers in other sports,

26
00:01:38,080 --> 00:01:40,680
Speaker 2: and the one that caught my eye was by a

27
00:01:40,720 --> 00:01:44,920
Speaker 2: gentleman named Keith Goldner. He had done something using NFL

28
00:01:45,000 --> 00:01:48,200
Speaker 2: data where he looked at kind of this, if the

29
00:01:48,240 --> 00:01:51,000
Speaker 2: ball is on the thirty five yard line, it's second

30
00:01:51,080 --> 00:01:53,920
Speaker 2: and ten with you know, X amount of time on.

31
00:01:53,920 --> 00:01:55,639
Speaker 3: The clock, like how likely are you to score?

32
00:01:56,360 --> 00:01:59,320
Speaker 2: And you know, I thought that was really interesting and

33
00:01:59,400 --> 00:02:01,480
Speaker 2: I thought, well, isn't that kind of similar to Charlie

34
00:02:01,480 --> 00:02:04,640
Speaker 2: Adam having the ball forty yards out?

35
00:02:04,880 --> 00:02:08,560
Speaker 1: So Sarah took this methodology it's called a Markov chain

36
00:02:08,720 --> 00:02:12,120
Speaker 1: just fyi, and she applied it to soccer. She built

37
00:02:12,160 --> 00:02:14,480
Speaker 1: a model that let you look at a moment when

38
00:02:14,520 --> 00:02:17,280
Speaker 1: a player had the ball in a given location on

39
00:02:17,400 --> 00:02:20,840
Speaker 1: the field, and the model could evaluate what the player

40
00:02:20,960 --> 00:02:25,480
Speaker 1: did at that moment. Specifically, the model let you ask,

41
00:02:25,960 --> 00:02:29,840
Speaker 1: did the choice the player made passing forward, passing to

42
00:02:29,880 --> 00:02:34,960
Speaker 1: the side, shooting whatever. Did this choice the player made

43
00:02:35,440 --> 00:02:39,760
Speaker 1: increase or decrease the probability of the team scoring a

44
00:02:39,800 --> 00:02:41,480
Speaker 1: goal on that possession?

45
00:02:41,960 --> 00:02:45,600
Speaker 2: And yeah, it really hadn't been done in soccer before,

46
00:02:45,680 --> 00:02:49,799
Speaker 2: which was kind of yeah, why it was kind of

47
00:02:49,840 --> 00:02:50,799
Speaker 2: a revolutionary paper.

48
00:02:50,840 --> 00:02:52,000
Speaker 3: I hate to use that term, but.

49
00:02:52,000 --> 00:02:54,440
Speaker 1: Like I'm saying it listed, I'm saying that listed five

50
00:02:54,440 --> 00:02:56,320
Speaker 1: point thirty eight had like a list of the ten

51
00:02:56,360 --> 00:02:59,040
Speaker 1: big papers and figuring out this kind of thing, and

52
00:02:59,120 --> 00:03:02,000
Speaker 1: yours was the first out on the list, so it

53
00:03:02,040 --> 00:03:04,760
Speaker 1: was chronological to be fair, but still big first is

54
00:03:04,760 --> 00:03:05,280
Speaker 1: a big deal.

55
00:03:05,520 --> 00:03:07,720
Speaker 2: Yeah, and you know it was cool because I was

56
00:03:07,919 --> 00:03:09,480
Speaker 2: kind of like, oh, well, I'm just doing what this

57
00:03:09,520 --> 00:03:12,120
Speaker 2: guy in the other football is doing.

58
00:03:12,680 --> 00:03:13,920
Speaker 3: But yeah, it was pretty impactful.

59
00:03:14,880 --> 00:03:17,280
Speaker 1: And by the way, what did you find out about

60
00:03:17,360 --> 00:03:17,880
Speaker 1: Charlie Adam?

61
00:03:18,240 --> 00:03:22,120
Speaker 2: Yeah? Not good to shoot from my hearts out was

62
00:03:23,120 --> 00:03:26,920
Speaker 2: what I found out, which was really like soul soothing

63
00:03:27,000 --> 00:03:28,600
Speaker 2: for me, or it was like I was right.

64
00:03:34,200 --> 00:03:37,320
Speaker 1: I'm Jacob Goldstein and this is what's your problem. Today

65
00:03:37,320 --> 00:03:40,320
Speaker 1: we have the third and final episode in our series

66
00:03:40,360 --> 00:03:43,440
Speaker 1: of interviews with people who are working at the frontiers

67
00:03:43,480 --> 00:03:47,440
Speaker 1: of technology to help a lead athletes perform better. My

68
00:03:47,520 --> 00:03:50,720
Speaker 1: guest today is Sarah Rudd. She's the co founder and

69
00:03:50,840 --> 00:03:55,160
Speaker 1: CEO at Source Football, a soccer analytics company that works

70
00:03:55,160 --> 00:03:58,720
Speaker 1: with professional soccer teams in the US, the UK, and Europe.

71
00:03:59,160 --> 00:04:02,600
Speaker 1: There are different to frame the core problem that Sarah

72
00:04:02,680 --> 00:04:05,160
Speaker 1: is trying to solve for today's show, I'm going to

73
00:04:05,200 --> 00:04:09,400
Speaker 1: go with a problem that generalizes way beyond sports. The

74
00:04:09,480 --> 00:04:13,320
Speaker 1: problem is this, how do you translate analytical insights into

75
00:04:13,400 --> 00:04:18,839
Speaker 1: meaningful changes in the real world. In our conversation, Sarah

76
00:04:18,839 --> 00:04:21,599
Speaker 1: and I talked about analytics and the challenge of getting

77
00:04:21,640 --> 00:04:24,720
Speaker 1: people to change their behavior, change the way they make

78
00:04:24,800 --> 00:04:28,160
Speaker 1: decisions based on analytics. But before we got to all that,

79
00:04:28,240 --> 00:04:30,679
Speaker 1: we talked a little bit more about that first paper

80
00:04:30,760 --> 00:04:34,039
Speaker 1: that Sarah wrote to prove that Charlie Adams should stop

81
00:04:34,040 --> 00:04:37,360
Speaker 1: shooting from forty yards out. Sarah told me that paper

82
00:04:37,440 --> 00:04:39,880
Speaker 1: also led to some less obvious insights.

83
00:04:41,360 --> 00:04:43,839
Speaker 2: Yeah, I think like one of the first ones was

84
00:04:43,839 --> 00:04:47,120
Speaker 2: that crossing from kind of like wide situations, which was

85
00:04:47,200 --> 00:04:50,480
Speaker 2: real really still very popular. So if you think of

86
00:04:50,520 --> 00:04:52,920
Speaker 2: like a player coming down the wings and then they're

87
00:04:52,960 --> 00:04:54,719
Speaker 2: going to kick the ball high in the air and

88
00:04:54,720 --> 00:04:56,800
Speaker 2: then hopefully a teammate is going to head it into

89
00:04:56,800 --> 00:04:57,360
Speaker 2: the goal.

90
00:04:57,560 --> 00:05:00,000
Speaker 3: That is also like pretty low value.

91
00:05:00,160 --> 00:05:03,719
Speaker 2: Oh interesting, yeah, because you have like a really high

92
00:05:04,160 --> 00:05:06,320
Speaker 2: chance of like turning the ball over from that.

93
00:05:06,920 --> 00:05:10,120
Speaker 1: And was that finding contrary to the sort of conventional

94
00:05:10,160 --> 00:05:11,040
Speaker 1: wisdom of the time.

95
00:05:11,360 --> 00:05:13,560
Speaker 2: Yeah, at that time, it was at that time there

96
00:05:13,640 --> 00:05:18,520
Speaker 2: was still a lot of teams using that tactic, and

97
00:05:18,560 --> 00:05:22,520
Speaker 2: I think, you know, going back, like people were starting

98
00:05:22,520 --> 00:05:25,279
Speaker 2: to just kind of intuitively be like, maybe there's a

99
00:05:25,320 --> 00:05:28,560
Speaker 2: better way. So it's not like it kind of like

100
00:05:28,600 --> 00:05:32,200
Speaker 2: broke soccer or football, but it just kind of I

101
00:05:32,240 --> 00:05:35,039
Speaker 2: think reinforced some of the intuitions that people had where

102
00:05:35,040 --> 00:05:36,600
Speaker 2: it's like, maybe there's a better way to do this.

103
00:05:36,880 --> 00:05:38,880
Speaker 1: And just to be clear, in the time since then,

104
00:05:38,920 --> 00:05:42,320
Speaker 1: in the whatever fifteen years or so since then, have

105
00:05:42,920 --> 00:05:45,520
Speaker 1: analytics shown clearly that that's a bad call and has

106
00:05:45,600 --> 00:05:47,880
Speaker 1: that style of play decreased as a result.

107
00:05:48,480 --> 00:05:50,640
Speaker 2: Yeah, And you know, now it's actually seen as like

108
00:05:50,680 --> 00:05:53,159
Speaker 2: a sign of like ooh, the offense is struggling, like

109
00:05:53,200 --> 00:05:56,680
Speaker 2: we're resorting to this really low probability tactic.

110
00:05:57,240 --> 00:06:00,960
Speaker 1: So okay, so this paper you write, you hired by

111
00:06:00,960 --> 00:06:04,960
Speaker 1: this analytics company, and then the analytics company gets acquired

112
00:06:05,000 --> 00:06:08,640
Speaker 1: by Arsenal, the famous London soccer team, and you wind

113
00:06:08,720 --> 00:06:13,479
Speaker 1: up working at Arsenal for many years. And one of

114
00:06:13,520 --> 00:06:17,479
Speaker 1: the things I've heard you talk about about that that time,

115
00:06:17,880 --> 00:06:20,640
Speaker 1: and that clearly is a big important theme that goes

116
00:06:20,640 --> 00:06:23,640
Speaker 1: beyond soccer is trying to figure out how to get

117
00:06:23,960 --> 00:06:27,920
Speaker 1: the people who make real world decisions to actually listen

118
00:06:28,000 --> 00:06:30,599
Speaker 1: to you, to you and the analytics people.

119
00:06:31,279 --> 00:06:34,839
Speaker 2: Yeah, it's it's really hard because like if you you know,

120
00:06:34,920 --> 00:06:37,719
Speaker 2: remove sports from it, just getting anybody to change their

121
00:06:37,880 --> 00:06:42,839
Speaker 2: opinion based on facts or evidence is really really difficult.

122
00:06:42,880 --> 00:06:46,800
Speaker 2: And now you're talking about people who are in incredibly

123
00:06:46,839 --> 00:06:50,799
Speaker 2: stressful jobs where they can lose their job really based

124
00:06:50,800 --> 00:06:51,240
Speaker 2: on like.

125
00:06:51,320 --> 00:06:54,080
Speaker 3: Some random occurrence that happens over the weekend.

126
00:06:54,240 --> 00:06:57,240
Speaker 2: Right, Like, right, the result doesn't go other way, you're fired,

127
00:06:57,680 --> 00:06:58,400
Speaker 2: Good luck to you.

128
00:06:58,400 --> 00:07:01,240
Speaker 1: Which is not the way analytics works. Right, Like, the

129
00:07:01,240 --> 00:07:03,680
Speaker 1: way analytics works is you need a large end, You

130
00:07:03,760 --> 00:07:05,880
Speaker 1: need to do the thing one hundred times, and then

131
00:07:06,320 --> 00:07:08,600
Speaker 1: sixty times it'll go the way the analytics says it.

132
00:07:08,640 --> 00:07:11,560
Speaker 1: Forty times it won't. That's just the nature of the

133
00:07:11,600 --> 00:07:13,000
Speaker 1: probabilistic world we live in.

134
00:07:13,360 --> 00:07:16,040
Speaker 2: Yeah, and you know, like analytics is also all about

135
00:07:16,120 --> 00:07:19,280
Speaker 2: separating process from outcomes, and yet these decisions are still

136
00:07:19,320 --> 00:07:22,280
Speaker 2: being made on outcomes. So I have a lot of

137
00:07:22,280 --> 00:07:25,120
Speaker 2: empathy for kind of people who are in this situation.

138
00:07:25,280 --> 00:07:27,720
Speaker 1: And a coach will get fired more likely if they

139
00:07:27,840 --> 00:07:30,720
Speaker 1: do the thing that the analytics says that's contrary to

140
00:07:30,760 --> 00:07:33,040
Speaker 1: the sort of conventional wisdom in the sport. Right. It's

141
00:07:33,040 --> 00:07:36,520
Speaker 1: like why in American football coaches for a long time

142
00:07:36,560 --> 00:07:39,200
Speaker 1: didn't go for it enough on fourth down, right when

143
00:07:39,280 --> 00:07:42,280
Speaker 1: the analytic clearly said they should, But everybody would get

144
00:07:42,280 --> 00:07:43,760
Speaker 1: pissed at them if they went for it and didn't

145
00:07:43,760 --> 00:07:47,920
Speaker 1: get it. Now that's change right because of analytics. Interestingly, although,

146
00:07:48,040 --> 00:07:49,880
Speaker 1: was it this last Super Bowl where the coach kept

147
00:07:49,880 --> 00:07:51,360
Speaker 1: going for it on fourth down and not getting it

148
00:07:51,400 --> 00:07:53,640
Speaker 1: and people are like, he did it too much? I

149
00:07:53,680 --> 00:07:55,960
Speaker 1: was like, no, he didn't. Just because it didn't work

150
00:07:56,000 --> 00:07:57,840
Speaker 1: out doesn't mean it was the wrong decision.

151
00:07:58,480 --> 00:08:00,280
Speaker 2: Yeah, And so you know, this just kind of goes

152
00:08:00,320 --> 00:08:02,720
Speaker 2: back to like you need to have kind of top

153
00:08:02,760 --> 00:08:05,560
Speaker 2: top decision makers saying like, yeah, it's okay if you're

154
00:08:05,560 --> 00:08:08,080
Speaker 2: going to do something that looks a little bit unconventional.

155
00:08:08,240 --> 00:08:10,120
Speaker 3: Yeah, we believe in it, we trust it.

156
00:08:11,240 --> 00:08:13,360
Speaker 1: So okay. So we've talked about why it's hard. Did

157
00:08:13,400 --> 00:08:15,920
Speaker 1: you figure anything out about how to get people to

158
00:08:16,000 --> 00:08:16,840
Speaker 1: change their decision?

159
00:08:16,960 --> 00:08:19,640
Speaker 2: I would say the best thing would be building trust

160
00:08:19,800 --> 00:08:22,840
Speaker 2: through a common language, And so for us, the common

161
00:08:22,880 --> 00:08:26,720
Speaker 2: language was video, so we could build a model but

162
00:08:26,880 --> 00:08:29,760
Speaker 2: like until we could show them the model outputs on

163
00:08:30,000 --> 00:08:33,439
Speaker 2: video and walk them through it and say, this is

164
00:08:33,480 --> 00:08:36,319
Speaker 2: what the model sees, this is what the model predicts.

165
00:08:36,679 --> 00:08:39,040
Speaker 2: What do you think, like, walk me through it. And

166
00:08:39,120 --> 00:08:42,360
Speaker 2: so then it became kind of like these collaborative, iterative

167
00:08:42,559 --> 00:08:43,800
Speaker 2: model building processes.

168
00:08:44,120 --> 00:08:46,880
Speaker 1: It's sort of a version of having an idea and

169
00:08:46,880 --> 00:08:49,959
Speaker 1: then convincing your boss that that idea is actually their idea,

170
00:08:50,440 --> 00:08:52,840
Speaker 1: and once they think it's their idea, then they'll do it.

171
00:08:52,840 --> 00:08:55,959
Speaker 3: It sounds like that, like maybe a little bit less cynical,

172
00:08:56,040 --> 00:08:56,760
Speaker 3: but yeah.

173
00:08:56,640 --> 00:09:00,199
Speaker 1: Yeah, yeah. So so eventually you left Arsenal and you

174
00:09:00,280 --> 00:09:04,160
Speaker 1: started source Football, this company that you're running. Now, what

175
00:09:04,160 --> 00:09:05,400
Speaker 1: what led you to make that leap?

176
00:09:05,840 --> 00:09:08,840
Speaker 2: So, you know, part of starting this company was that,

177
00:09:09,160 --> 00:09:11,480
Speaker 2: you know, I wanted to learn and to experience as

178
00:09:11,520 --> 00:09:14,960
Speaker 2: much as possible. But the other part is that we

179
00:09:15,040 --> 00:09:19,040
Speaker 2: felt like there's a huge need for clubs to get

180
00:09:19,040 --> 00:09:22,560
Speaker 2: help in terms of getting started on this analytics journey

181
00:09:22,559 --> 00:09:24,880
Speaker 2: where you know, a lot of them just don't even

182
00:09:25,200 --> 00:09:25,920
Speaker 2: know where to begin.

183
00:09:26,000 --> 00:09:27,680
Speaker 3: They don't know what's good what's bad.

184
00:09:28,559 --> 00:09:31,840
Speaker 2: So our kind of main value add is coming in

185
00:09:32,240 --> 00:09:34,960
Speaker 2: helping them get set up, helping them get started and

186
00:09:35,000 --> 00:09:38,920
Speaker 2: then once that happens, doing all of the hard work,

187
00:09:39,040 --> 00:09:42,959
Speaker 2: hard thinking that's impossible to get done within a football club.

188
00:09:43,920 --> 00:09:46,960
Speaker 2: If anyone has ever been in a training ground, Like

189
00:09:47,080 --> 00:09:50,960
Speaker 2: I'm sure it's the same across all sports, but they're chaotic,

190
00:09:51,080 --> 00:09:54,360
Speaker 2: they're noisy, they're loud, Like they're not good places to

191
00:09:54,440 --> 00:09:59,120
Speaker 2: do deep testosterone. Yeah, a lot of a lot of

192
00:09:59,120 --> 00:10:04,240
Speaker 2: really loud music, like humping. You know, like if your

193
00:10:04,240 --> 00:10:06,679
Speaker 2: office is anywhere near the gym, like forget it. Like

194
00:10:06,920 --> 00:10:08,760
Speaker 2: you got to wait until everybody goes home before you

195
00:10:08,760 --> 00:10:11,400
Speaker 2: can actually like have a clear thought. So you know,

196
00:10:11,440 --> 00:10:14,640
Speaker 2: that was that was one of the things that we realized,

197
00:10:14,760 --> 00:10:16,720
Speaker 2: is like you can't work on solving these really hard

198
00:10:16,720 --> 00:10:20,240
Speaker 2: problems and like football is really hard to analyze in

199
00:10:20,320 --> 00:10:22,360
Speaker 2: terms of analytics, and like you just you can't do

200
00:10:22,400 --> 00:10:23,480
Speaker 2: it within a club.

201
00:10:24,160 --> 00:10:25,400
Speaker 3: So that's why we want it to be a little

202
00:10:25,440 --> 00:10:26,000
Speaker 3: bit outside.

203
00:10:26,000 --> 00:10:28,319
Speaker 2: And then kind of our our long term vision is

204
00:10:28,360 --> 00:10:32,200
Speaker 2: actually like you know, we're using this consulting business to

205
00:10:32,280 --> 00:10:36,360
Speaker 2: kind of fund the development of our intelligence platform, and

206
00:10:36,400 --> 00:10:38,880
Speaker 2: then the ideas eventually to look for like a set

207
00:10:38,880 --> 00:10:42,600
Speaker 2: of investors or maybe an ownership group and you know,

208
00:10:42,720 --> 00:10:44,920
Speaker 2: take control of a club and run it in kind

209
00:10:44,920 --> 00:10:47,360
Speaker 2: of like the modern progressive way that we think they

210
00:10:47,360 --> 00:10:48,000
Speaker 2: should be run.

211
00:10:48,679 --> 00:10:52,240
Speaker 1: So what you really want to do is basically buy

212
00:10:52,240 --> 00:10:54,720
Speaker 1: a soccer team and run it smarter than everybody else.

213
00:10:54,800 --> 00:10:57,960
Speaker 1: Is that what you're telling me? Yeah, of course, tell

214
00:10:58,000 --> 00:10:59,800
Speaker 1: me more about the big gream. We'll do the pieces.

215
00:10:59,840 --> 00:11:02,559
Speaker 1: But I'm curious, Like that's a big, audacious dream and

216
00:11:02,640 --> 00:11:03,640
Speaker 1: it's fun tell me about it.

217
00:11:03,840 --> 00:11:05,160
Speaker 2: Yeah, I mean, I think you know, one of the

218
00:11:05,160 --> 00:11:08,719
Speaker 2: things that probably everybody in analytics has experienced is that

219
00:11:08,960 --> 00:11:11,920
Speaker 2: unless you're kind of like the key decision maker, it's

220
00:11:12,000 --> 00:11:16,080
Speaker 2: always going to be kind of difficult to influence decisions

221
00:11:16,880 --> 00:11:19,680
Speaker 2: because there's always going to be somebody that has, you know,

222
00:11:19,800 --> 00:11:23,480
Speaker 2: kind of their own perspective and everything. And you know,

223
00:11:23,520 --> 00:11:25,560
Speaker 2: at Arsenal, we were really lucky because we had like

224
00:11:25,600 --> 00:11:27,599
Speaker 2: a lot of resources. But what I see at a

225
00:11:27,640 --> 00:11:30,760
Speaker 2: lot of clubs is that you know, they only hire

226
00:11:30,800 --> 00:11:33,600
Speaker 2: one or two people. The work that they do is good,

227
00:11:33,720 --> 00:11:36,200
Speaker 2: but like there's a limit to what two human beings

228
00:11:36,240 --> 00:11:39,040
Speaker 2: can do, and so like a lot of what they

229
00:11:39,040 --> 00:11:42,840
Speaker 2: produce doesn't necessarily like match the gut, and so it's

230
00:11:42,840 --> 00:11:46,600
Speaker 2: hard to get this buy in. And so then they

231
00:11:46,640 --> 00:11:49,120
Speaker 2: just say like, well, okay, thanks for that. I'm only

232
00:11:49,120 --> 00:11:50,640
Speaker 2: going to listen to you if I agree with it.

233
00:11:50,960 --> 00:11:52,600
Speaker 3: If I disagree with it, I'm going to go with

234
00:11:52,679 --> 00:11:55,760
Speaker 3: my gut, and so it just becomes difficult.

235
00:11:55,800 --> 00:11:58,160
Speaker 2: But I think also, like there's so many issues within

236
00:11:58,200 --> 00:12:02,960
Speaker 2: football clubs that go beyond just analytics or you know,

237
00:12:03,080 --> 00:12:05,120
Speaker 2: making the right decision on players. I mean, there's so

238
00:12:05,200 --> 00:12:08,880
Speaker 2: much in terms of like building good, good cultures, you know,

239
00:12:09,000 --> 00:12:12,640
Speaker 2: kind of making sure that everything is kind of set

240
00:12:12,720 --> 00:12:15,360
Speaker 2: up in like a professional way, because if you think

241
00:12:15,400 --> 00:12:17,240
Speaker 2: about it, clubs are kind of run by people who've

242
00:12:17,240 --> 00:12:18,480
Speaker 2: never worked outside of football.

243
00:12:19,679 --> 00:12:20,719
Speaker 3: But I think there's a lot of.

244
00:12:20,720 --> 00:12:24,520
Speaker 2: Lessons that you can take from working outside of sports

245
00:12:24,840 --> 00:12:28,280
Speaker 2: bring them into football, and we've seen it in every

246
00:12:28,320 --> 00:12:30,040
Speaker 2: other major American sport.

247
00:12:30,440 --> 00:12:33,320
Speaker 3: Not to be like super ruthless.

248
00:12:32,880 --> 00:12:35,160
Speaker 2: And say like we got to maximize profit, maximize profit,

249
00:12:35,920 --> 00:12:39,559
Speaker 2: because I think like they are these weird social institutions

250
00:12:39,600 --> 00:12:42,120
Speaker 2: that have a lot of meaning to a lot of people,

251
00:12:42,160 --> 00:12:44,360
Speaker 2: and so you obviously want to respect that. And you

252
00:12:44,400 --> 00:12:48,000
Speaker 2: also have these amazing platforms to bring positive change into

253
00:12:48,040 --> 00:12:49,760
Speaker 2: the world, and so you want to take advantage of

254
00:12:49,760 --> 00:12:50,280
Speaker 2: that as well.

255
00:12:50,320 --> 00:12:51,760
Speaker 3: But like, there certainly can be a.

256
00:12:51,760 --> 00:12:55,760
Speaker 2: Lot more kind of professionalism in them than what we

257
00:12:55,840 --> 00:12:57,200
Speaker 2: experience at a lot of places.

258
00:12:58,120 --> 00:13:00,480
Speaker 1: So, now you have this company and you want to

259
00:13:00,559 --> 00:13:04,280
Speaker 1: use it eventually to take over the world. Correct, before

260
00:13:04,440 --> 00:13:06,840
Speaker 1: you use your company to take over the world, Like,

261
00:13:06,920 --> 00:13:09,600
Speaker 1: what are the what are the services you're selling to

262
00:13:10,120 --> 00:13:11,160
Speaker 1: teams to clubs?

263
00:13:11,600 --> 00:13:16,599
Speaker 2: Yeah, I mean, so clubs are in really different situations.

264
00:13:16,679 --> 00:13:19,160
Speaker 2: And then also, like you know, it's not like the

265
00:13:19,320 --> 00:13:22,600
Speaker 2: US where like every single major League baseball team is

266
00:13:22,640 --> 00:13:27,800
Speaker 2: like loaded with cash. Typically in European leagues, like you're

267
00:13:27,800 --> 00:13:30,400
Speaker 2: going to have several divisions, so like you're talking about

268
00:13:30,440 --> 00:13:34,520
Speaker 2: anywhere from like a single a baseball team to like

269
00:13:34,760 --> 00:13:39,280
Speaker 2: a Major League baseball team, Like there's huge difference in resources.

270
00:13:38,840 --> 00:13:42,400
Speaker 1: So like orders of magnitude in terms of revenue, how

271
00:13:42,480 --> 00:13:46,320
Speaker 1: much presumably they want to spend on your services, et cetera.

272
00:13:46,720 --> 00:13:49,200
Speaker 2: Yeah exactly, And so like the main area where we

273
00:13:49,200 --> 00:13:53,200
Speaker 2: can help them is really recruitment, so helping them kind

274
00:13:53,200 --> 00:13:56,839
Speaker 2: of find the best players. So unlike American sports where

275
00:13:56,840 --> 00:14:00,320
Speaker 2: you kind of like trade players and draft them, everything

276
00:14:00,360 --> 00:14:02,280
Speaker 2: here is kind of like an open market where you

277
00:14:02,280 --> 00:14:04,400
Speaker 2: can buy and sell the contracts of these players.

278
00:14:04,440 --> 00:14:06,480
Speaker 3: And so if you're a small team, and you have

279
00:14:06,520 --> 00:14:07,439
Speaker 3: a really really.

280
00:14:07,559 --> 00:14:10,360
Speaker 2: Good player, like you can just sell him keep that cash,

281
00:14:10,440 --> 00:14:12,760
Speaker 2: or you can invest it back into your club.

282
00:14:13,160 --> 00:14:16,960
Speaker 1: Huh. This is this is really echoes of Moneyball. I mean,

283
00:14:16,960 --> 00:14:18,480
Speaker 1: I'm sure I don't know if you're tired of hearing

284
00:14:18,480 --> 00:14:20,680
Speaker 1: about Moneyball. That book came about twenty years ago, but

285
00:14:20,800 --> 00:14:23,320
Speaker 1: like that was the basic idea there, Right, it was

286
00:14:24,640 --> 00:14:27,920
Speaker 1: better scouting essentially, right, Like you had these scouts who

287
00:14:27,920 --> 00:14:29,560
Speaker 1: were sort of using their guts and these kind of

288
00:14:29,560 --> 00:14:33,520
Speaker 1: conventional wisdom heuristics, and then you had what I'm sure

289
00:14:33,520 --> 00:14:37,480
Speaker 1: now seem like primitive analytics coming in and basically doing

290
00:14:37,480 --> 00:14:41,600
Speaker 1: a better job of predicting player success, right at some level.

291
00:14:41,760 --> 00:14:42,560
Speaker 3: Yeah, exactly.

292
00:14:42,600 --> 00:14:44,440
Speaker 2: And so you know, I hate to say that, like

293
00:14:45,040 --> 00:14:47,680
Speaker 2: soccer is twenty years behind baseball, but like in a lot.

294
00:14:47,520 --> 00:14:50,040
Speaker 3: Of ways we are. And so like this is still

295
00:14:50,080 --> 00:14:52,000
Speaker 3: like the main area of.

296
00:14:52,000 --> 00:14:54,640
Speaker 2: Value add for a lot of clubs because you're competing

297
00:14:54,680 --> 00:14:58,760
Speaker 2: in this open market with people with varying amounts of knowledge.

298
00:14:58,840 --> 00:15:02,600
Speaker 2: So sometimes that knowledge is just hey, like we had

299
00:15:02,640 --> 00:15:05,080
Speaker 2: scouts at that game, We've seen this player once, like

300
00:15:05,720 --> 00:15:08,320
Speaker 2: this is our opinion of him. And then you have

301
00:15:08,520 --> 00:15:10,600
Speaker 2: the more sophisticated teams that are like, Okay, well, we

302
00:15:10,640 --> 00:15:14,280
Speaker 2: have a database of you know, six hundred thousand matches

303
00:15:14,640 --> 00:15:17,960
Speaker 2: in the world. We know the fifty best players in

304
00:15:18,040 --> 00:15:20,920
Speaker 2: every league at every position, we know how much they're worth.

305
00:15:21,920 --> 00:15:24,360
Speaker 2: So we help teams kind of go from like the

306
00:15:24,400 --> 00:15:27,040
Speaker 2: former to the latter and just be a little bit

307
00:15:27,080 --> 00:15:29,640
Speaker 2: more sophisticated in terms of the amount of information that

308
00:15:29,680 --> 00:15:29,960
Speaker 2: they have.

309
00:15:30,160 --> 00:15:32,080
Speaker 1: I mean, it's sort of crass to put it this way,

310
00:15:32,120 --> 00:15:35,880
Speaker 1: but it's really like pricing assets right, like the players.

311
00:15:35,960 --> 00:15:38,640
Speaker 1: And again I realized this is kind of dehumanizing. I'm sorry,

312
00:15:38,680 --> 00:15:43,040
Speaker 1: but it is analogous to people valuing a stock or

313
00:15:43,160 --> 00:15:48,360
Speaker 1: valuing anything they might buy. Right, And the better you

314
00:15:48,400 --> 00:15:52,640
Speaker 1: can model the value of the asset, the better you're

315
00:15:52,640 --> 00:15:55,160
Speaker 1: going to be at finding mispriced assets. Right. You want

316
00:15:55,200 --> 00:15:59,400
Speaker 1: to you want to find bargains. You want to get

317
00:15:59,400 --> 00:16:02,440
Speaker 1: the most you can and uh for your dollar.

318
00:16:02,960 --> 00:16:06,080
Speaker 2: Yeah, absolutely, And so you know, there's a lot of

319
00:16:06,800 --> 00:16:09,320
Speaker 2: techniques that we can take from other industries because it's

320
00:16:09,360 --> 00:16:11,680
Speaker 2: not that different from it. Where it gets hard is

321
00:16:11,680 --> 00:16:14,160
Speaker 2: that you have to have those assets work well together.

322
00:16:14,560 --> 00:16:16,000
Speaker 1: They are in fact human beings.

323
00:16:16,640 --> 00:16:18,520
Speaker 3: Yes, that is you know the.

324
00:16:18,880 --> 00:16:20,720
Speaker 2: Kind of joke where it's like, well, the problem with

325
00:16:20,720 --> 00:16:23,080
Speaker 2: football clubs is that it's full of human beings.

326
00:16:23,760 --> 00:16:27,040
Speaker 1: So let's talk about what you can model, Like, what

327
00:16:27,120 --> 00:16:29,480
Speaker 1: are you good at modeling in this context, like in

328
00:16:29,560 --> 00:16:33,280
Speaker 1: helping in scouting, essentially in helping clubs value, you know,

329
00:16:33,360 --> 00:16:34,560
Speaker 1: players they might acquire.

330
00:16:35,120 --> 00:16:38,360
Speaker 2: Yeah, so we're pretty good at modeling everything that happens

331
00:16:38,400 --> 00:16:42,640
Speaker 2: when a player has the ball, and unfortunately in football,

332
00:16:42,760 --> 00:16:45,800
Speaker 2: that's like a very very small portion of the gaming.

333
00:16:46,240 --> 00:16:48,320
Speaker 3: Yeah. And so there was this really cool.

334
00:16:48,040 --> 00:16:51,320
Speaker 2: Development in the last four or five years where a

335
00:16:51,400 --> 00:16:54,720
Speaker 2: number of companies have come out with a data source

336
00:16:55,080 --> 00:16:59,800
Speaker 2: that's basically taking the video feeds from TV and turning

337
00:17:00,280 --> 00:17:04,760
Speaker 2: into tracking data. So basically they're able to track the

338
00:17:04,800 --> 00:17:06,959
Speaker 2: location of every player that's on screen.

339
00:17:07,760 --> 00:17:10,520
Speaker 3: So obviously you don't know all the players, and.

340
00:17:10,440 --> 00:17:12,960
Speaker 2: Then you know, what we've learned is that really what's

341
00:17:13,000 --> 00:17:17,400
Speaker 2: going on off screen tends to not be as relevant

342
00:17:17,440 --> 00:17:21,320
Speaker 2: and the location of those players isn't as relevant. And

343
00:17:21,359 --> 00:17:23,040
Speaker 2: so now all of a sudden, you can start doing

344
00:17:23,119 --> 00:17:26,879
Speaker 2: modeling on what people are doing off the ball and

345
00:17:27,040 --> 00:17:30,159
Speaker 2: use it for recruitment. Because prior to this, similar to

346
00:17:30,200 --> 00:17:32,800
Speaker 2: the NBA, there were cameras in all the stadiums and

347
00:17:32,840 --> 00:17:36,240
Speaker 2: you would get this full data set, but only for

348
00:17:37,040 --> 00:17:38,919
Speaker 2: your league, and so you couldn't really use it for

349
00:17:38,960 --> 00:17:39,440
Speaker 2: a recruitment.

350
00:17:39,440 --> 00:17:41,280
Speaker 3: And so this has been like a really big change.

351
00:17:41,320 --> 00:17:45,160
Speaker 2: So you know, we can get much better views into

352
00:17:45,320 --> 00:17:48,440
Speaker 2: what is a player doing physically, what are they doing

353
00:17:48,480 --> 00:17:52,399
Speaker 2: defensively in terms of cutting off passing lanes, things like that.

354
00:17:52,920 --> 00:17:55,280
Speaker 2: There's still a lot we're not good at with that,

355
00:17:56,040 --> 00:17:58,920
Speaker 2: but what it's also done is allowed us to say, well,

356
00:17:58,920 --> 00:18:01,080
Speaker 2: if we're going to move a player from this league

357
00:18:01,080 --> 00:18:04,760
Speaker 2: to that league, how different is it physically? How do

358
00:18:04,800 --> 00:18:07,000
Speaker 2: we think they're going to adapt? And so this has

359
00:18:07,040 --> 00:18:09,119
Speaker 2: really opened up a lot of things. So if we

360
00:18:09,160 --> 00:18:12,840
Speaker 2: want to talk about like risk adjusted pricing of assets,

361
00:18:13,359 --> 00:18:16,200
Speaker 2: now we're starting to be able to quantify a little

362
00:18:16,240 --> 00:18:19,160
Speaker 2: bit like what's the risk of bringing in somebody from

363
00:18:19,240 --> 00:18:23,240
Speaker 2: a really really different environment into this one versus one

364
00:18:23,280 --> 00:18:24,880
Speaker 2: that's more similar, Or.

365
00:18:25,440 --> 00:18:29,199
Speaker 1: So you should apply a larger discount when you're bringing

366
00:18:29,200 --> 00:18:32,000
Speaker 1: a player from a very different league, presumably because you're

367
00:18:32,040 --> 00:18:32,840
Speaker 1: taking more risk.

368
00:18:33,240 --> 00:18:36,520
Speaker 2: Yes, yes, and if not, then it's not an undervalued

369
00:18:36,560 --> 00:18:38,440
Speaker 2: asset and maybe walk away.

370
00:18:39,200 --> 00:18:44,360
Speaker 1: So tell me more, like, is the output you have

371
00:18:45,119 --> 00:18:47,439
Speaker 1: just here is what you should pay for each of

372
00:18:47,480 --> 00:18:51,000
Speaker 1: these players, Like you have whatever ten thousand players or something,

373
00:18:51,040 --> 00:18:53,119
Speaker 1: and you put a dollar value on each one, or

374
00:18:53,240 --> 00:18:54,520
Speaker 1: like what's the output?

375
00:18:55,040 --> 00:18:56,959
Speaker 3: Yeah, I mean I wish it was that simple.

376
00:18:57,000 --> 00:18:59,960
Speaker 2: We're still like pretty far from putting it all together

377
00:19:00,040 --> 00:19:03,199
Speaker 2: there and saying like, by this player at this price.

378
00:19:04,200 --> 00:19:07,000
Speaker 2: You know, a lot of the difficulties is that there's

379
00:19:07,000 --> 00:19:10,200
Speaker 2: no good data set on pricing information.

380
00:19:10,000 --> 00:19:11,960
Speaker 1: So then what do you just have a relative like

381
00:19:12,040 --> 00:19:13,040
Speaker 1: kind of a stack rank.

382
00:19:14,000 --> 00:19:17,040
Speaker 2: I mean, there are like estimates, so in the in

383
00:19:17,080 --> 00:19:20,080
Speaker 2: the media, they'll say like, oh, this guy went for

384
00:19:20,440 --> 00:19:23,160
Speaker 2: ten million, but then a different media source will say

385
00:19:23,160 --> 00:19:27,000
Speaker 2: this guy went for fifteen million, because like the selling

386
00:19:27,040 --> 00:19:29,879
Speaker 2: club wants to report a higher price and the buying

387
00:19:29,920 --> 00:19:31,920
Speaker 2: club wants for lower price.

388
00:19:31,720 --> 00:19:33,560
Speaker 3: So there's real no truth.

389
00:19:33,640 --> 00:19:39,479
Speaker 2: And then salaries for players are not public for most leagues.

390
00:19:39,800 --> 00:19:42,919
Speaker 1: So okay, so that's a very important variable that you

391
00:19:43,000 --> 00:19:45,399
Speaker 1: don't really have access to. That's a problem. So what

392
00:19:45,800 --> 00:19:47,360
Speaker 1: is the output of your model? Then?

393
00:19:47,680 --> 00:19:49,639
Speaker 2: Yeah, I mean, so we we kind of do like

394
00:19:49,680 --> 00:19:53,719
Speaker 2: a stack ranking and like a you know, projected like

395
00:19:53,800 --> 00:19:56,080
Speaker 2: what do we think this player would do in this situation?

396
00:19:56,240 --> 00:19:58,399
Speaker 3: But like the error bars on these things are like

397
00:19:58,640 --> 00:19:59,359
Speaker 3: are pretty big.

398
00:19:59,480 --> 00:20:03,000
Speaker 2: So we're still kind of in the like subjective realm

399
00:20:03,080 --> 00:20:06,040
Speaker 2: of like based on these factors, we think this or

400
00:20:06,080 --> 00:20:08,159
Speaker 2: we think that, and then you know a lot of

401
00:20:08,200 --> 00:20:12,760
Speaker 2: the like the markets change every year in football as well.

402
00:20:12,840 --> 00:20:15,480
Speaker 2: So even if we had like a really precise model

403
00:20:15,520 --> 00:20:17,720
Speaker 2: that said this guy should be worth five million, well

404
00:20:18,040 --> 00:20:20,359
Speaker 2: he should he would be worth five million last year.

405
00:20:20,560 --> 00:20:24,760
Speaker 1: Yeah, I appreciate your candor you know, so the market changes.

406
00:20:24,800 --> 00:20:29,040
Speaker 1: You don't have pricing data, there's big uncertainty even on

407
00:20:29,080 --> 00:20:34,560
Speaker 1: the outputs you do have, Like all of this seems

408
00:20:35,600 --> 00:20:37,639
Speaker 1: so what is the use of what you're doing? How

409
00:20:37,720 --> 00:20:38,760
Speaker 1: is it valuable to people?

410
00:20:39,280 --> 00:20:42,280
Speaker 2: That's the point is that we're competing with people who

411
00:20:43,040 --> 00:20:45,560
Speaker 2: you know, have gone to maybe three or four games

412
00:20:45,920 --> 00:20:51,919
Speaker 2: watch this guy in you know, unknown conditions. The human

413
00:20:52,200 --> 00:20:57,760
Speaker 2: brain is like not conditions to be like very objective

414
00:20:57,800 --> 00:21:00,280
Speaker 2: and so like, you know, there's a host of like

415
00:21:00,440 --> 00:21:03,919
Speaker 2: very known biases that like people can can fall for.

416
00:21:04,000 --> 00:21:07,240
Speaker 2: And so really what we're trying to do is just

417
00:21:07,320 --> 00:21:10,960
Speaker 2: give you like a much more fair and even view

418
00:21:11,040 --> 00:21:15,560
Speaker 2: of a player, taking into account a lot of you

419
00:21:15,560 --> 00:21:19,000
Speaker 2: know the factors that these scouts are trying to account

420
00:21:19,000 --> 00:21:23,000
Speaker 2: for as well, but just doing it more objectively, more rigorously,

421
00:21:23,480 --> 00:21:25,080
Speaker 2: you know, over a longer period of time.

422
00:21:25,800 --> 00:21:29,639
Speaker 1: It seems from what you've been saying, like soccer is

423
00:21:29,840 --> 00:21:34,200
Speaker 1: behind certainly baseball and perhaps other sports in analytics. I

424
00:21:34,240 --> 00:21:36,600
Speaker 1: mean your first paper, you were following somebody who had

425
00:21:36,640 --> 00:21:38,480
Speaker 1: written a paper in American football, and you're like, oh,

426
00:21:38,520 --> 00:21:40,760
Speaker 1: what if we do that for soccer? Is it true

427
00:21:40,760 --> 00:21:41,639
Speaker 1: that soccer is behind?

428
00:21:41,640 --> 00:21:44,240
Speaker 3: And if so, why, Yeah, it's true.

429
00:21:44,280 --> 00:21:47,160
Speaker 2: And I think, you know, the debate used to be like, well,

430
00:21:47,200 --> 00:21:49,159
Speaker 2: are we making any progress? I think we've made a

431
00:21:49,160 --> 00:21:53,600
Speaker 2: ton of progress, but we're still really far behind other sports.

432
00:21:53,600 --> 00:21:57,280
Speaker 2: And so one answer is that we also don't get

433
00:21:57,320 --> 00:22:00,640
Speaker 2: the funding that other sports get. So so the level

434
00:22:00,680 --> 00:22:03,320
Speaker 2: of investment just isn't there. And so if we were

435
00:22:03,359 --> 00:22:08,359
Speaker 2: behind fifteen years ago, we're certainly not keeping pace, you know.

436
00:22:08,400 --> 00:22:12,040
Speaker 2: And then I think there's other structural issues with it.

437
00:22:12,119 --> 00:22:16,520
Speaker 2: So I love to use this image that somebody else made,

438
00:22:16,600 --> 00:22:19,200
Speaker 2: but it shows the relative size of a basketball court

439
00:22:19,320 --> 00:22:23,040
Speaker 2: to a soccer pitch, And basically a basketball court can

440
00:22:23,080 --> 00:22:26,080
Speaker 2: fit into like the little tiny penalty area on a

441
00:22:26,119 --> 00:22:30,400
Speaker 2: soccer pitch, and so you know, the distances and spacing

442
00:22:30,440 --> 00:22:33,359
Speaker 2: of players is so much more variable in soccer, So

443
00:22:33,400 --> 00:22:35,720
Speaker 2: you can't say, like, oh, ten meters is a good

444
00:22:35,760 --> 00:22:38,480
Speaker 2: distance between me and a teammate, because it depends on

445
00:22:39,000 --> 00:22:42,080
Speaker 2: the situation that's happening where on the pitch, like is

446
00:22:42,119 --> 00:22:44,160
Speaker 2: it a transitional moment, is it kind of a more

447
00:22:44,200 --> 00:22:47,879
Speaker 2: controlled moment, And so there's a lot of complexities like that.

448
00:22:48,280 --> 00:22:49,480
Speaker 3: You know, the game doesn't stop.

449
00:22:49,520 --> 00:22:51,760
Speaker 2: There aren't a lot of these set pieces where it's

450
00:22:51,760 --> 00:22:54,639
Speaker 2: like we have a very choreographed idea of what we

451
00:22:54,680 --> 00:22:58,880
Speaker 2: want to do, and then you know, the sad reality

452
00:22:58,960 --> 00:23:02,479
Speaker 2: is that most leagues only play thirty eight matches a season,

453
00:23:03,000 --> 00:23:05,639
Speaker 2: and so you never see a team in the same

454
00:23:06,040 --> 00:23:07,240
Speaker 2: context twice.

455
00:23:07,560 --> 00:23:10,280
Speaker 3: You either play them at home or away and then that's.

456
00:23:10,080 --> 00:23:12,160
Speaker 2: It, or maybe you play them in a cup game,

457
00:23:12,200 --> 00:23:15,880
Speaker 2: which is like a really different environment, and so all

458
00:23:15,920 --> 00:23:18,280
Speaker 2: of these things just kind of like add up and

459
00:23:18,359 --> 00:23:22,280
Speaker 2: it's like, well, we have fewer resources, it's much more complex, Like,

460
00:23:22,520 --> 00:23:24,280
Speaker 2: of course we're behind on.

461
00:23:24,280 --> 00:23:30,080
Speaker 1: This still to come on the show, the one big

462
00:23:30,119 --> 00:23:34,600
Speaker 1: strategic change that Sarah really really wants someone in soccer

463
00:23:34,640 --> 00:23:46,719
Speaker 1: to try and why nobody has tried it yet. So

464
00:23:46,800 --> 00:23:50,560
Speaker 1: we talked a lot about essentially scouting, evaluating players as

465
00:23:50,640 --> 00:23:53,840
Speaker 1: kind of one of the one of the big things

466
00:23:53,880 --> 00:23:56,439
Speaker 1: you do. What else do you do?

467
00:23:56,720 --> 00:23:59,800
Speaker 2: Yeah, I mean, so there's a number of different services

468
00:23:59,800 --> 00:24:02,760
Speaker 2: that we provide, so you know, it could be doing

469
00:24:02,800 --> 00:24:06,040
Speaker 2: like retrospectives of how did the team play this weekend,

470
00:24:06,520 --> 00:24:10,120
Speaker 2: or maybe some kind of I guess in US terms

471
00:24:10,119 --> 00:24:13,040
Speaker 2: they would call it advanced scouting, but delivering kind of

472
00:24:13,040 --> 00:24:16,280
Speaker 2: like a data profile on their upcoming opponent and then

473
00:24:16,320 --> 00:24:19,040
Speaker 2: going into like on field stuff, like we're doing a

474
00:24:19,119 --> 00:24:22,760
Speaker 2: lot of research now around you know, various things in

475
00:24:22,880 --> 00:24:26,400
Speaker 2: terms of you know, how can we maximize set pieces?

476
00:24:26,640 --> 00:24:29,240
Speaker 1: A set piece is like a play analogous to sort

477
00:24:29,240 --> 00:24:29,960
Speaker 1: of a play.

478
00:24:30,040 --> 00:24:33,320
Speaker 3: Yeah, so, you know, football is really fluid.

479
00:24:33,480 --> 00:24:37,280
Speaker 2: It never really stops except for these certain moments that

480
00:24:37,320 --> 00:24:41,120
Speaker 2: are called dead balls and when a dead ball.

481
00:24:41,000 --> 00:24:44,080
Speaker 3: Happens and kind of like the attacking area when you.

482
00:24:44,040 --> 00:24:46,639
Speaker 1: Have like a throw in or a penalty kick or something.

483
00:24:46,880 --> 00:24:49,719
Speaker 2: Yeah, I mean, penalties are pretty pretty straightforward. They're kind

484
00:24:49,760 --> 00:24:52,200
Speaker 2: of exceptional. It's like we'll just kick it into the goal.

485
00:24:53,119 --> 00:24:56,520
Speaker 2: But corners corner kicks are kind of like the most

486
00:24:58,040 --> 00:25:00,280
Speaker 2: common one because they all happen from the same location.

487
00:25:00,440 --> 00:25:03,680
Speaker 2: They happen fairly frequently. You can analyze them, you can

488
00:25:03,720 --> 00:25:07,160
Speaker 2: prepare for them. So you have this set piece opportunity,

489
00:25:07,240 --> 00:25:09,760
Speaker 2: and then it's you know, what's the strategy we're going

490
00:25:09,840 --> 00:25:11,679
Speaker 2: to use to maximize it.

491
00:25:12,560 --> 00:25:14,080
Speaker 3: So a lot of research into that.

492
00:25:14,240 --> 00:25:17,399
Speaker 1: Has analytics, in a general way changed the way people

493
00:25:17,520 --> 00:25:18,680
Speaker 1: take corners.

494
00:25:19,680 --> 00:25:22,560
Speaker 2: Yeah, I mean, I think it has influenced how much

495
00:25:22,640 --> 00:25:26,920
Speaker 2: time they spend thinking about it and preparing for it.

496
00:25:27,040 --> 00:25:28,480
Speaker 3: So that's another one.

497
00:25:28,720 --> 00:25:33,280
Speaker 2: Ted Kinnutsen, who's the CEO of Statsbomb, he's been shouting

498
00:25:33,320 --> 00:25:37,040
Speaker 2: this from up high for the longest, but set pieces

499
00:25:37,080 --> 00:25:40,560
Speaker 2: for a long time were really valuable, but teams would

500
00:25:40,560 --> 00:25:42,920
Speaker 2: only train them for like ten minutes a week.

501
00:25:43,200 --> 00:25:46,680
Speaker 1: It's an interesting level of analytics. That's an analytical claim, right,

502
00:25:46,680 --> 00:25:50,080
Speaker 1: It's like, your training time is measurable and you should

503
00:25:50,119 --> 00:25:53,000
Speaker 1: be allocating the right proportion of it to the right things.

504
00:25:53,000 --> 00:25:59,240
Speaker 1: And he's essentially arguing that you're underfunding in time corners. Yeah.

505
00:25:59,320 --> 00:26:02,080
Speaker 2: Yeah, the number of goals scored from corners or conceded

506
00:26:02,119 --> 00:26:06,119
Speaker 2: from corners was not at all proportional to the amount

507
00:26:06,160 --> 00:26:10,040
Speaker 2: of time spent training them. And so like that's been

508
00:26:10,040 --> 00:26:13,560
Speaker 2: a big focus on teams lately. And you know, I

509
00:26:13,600 --> 00:26:16,159
Speaker 2: still don't think they spend enough time training it. But

510
00:26:16,280 --> 00:26:19,360
Speaker 2: now you'll see, you know, certain clubs even hiring set

511
00:26:19,400 --> 00:26:20,520
Speaker 2: piece specialists.

512
00:26:20,560 --> 00:26:23,720
Speaker 3: So they'll have a member of coaching staff whose job.

513
00:26:23,800 --> 00:26:26,280
Speaker 2: Whose only job is really kind of like thinking about

514
00:26:26,280 --> 00:26:28,840
Speaker 2: these things and helping prepare the players for it.

515
00:26:28,920 --> 00:26:32,360
Speaker 1: If that person basically the corner kick coach, I.

516
00:26:32,280 --> 00:26:34,240
Speaker 2: Mean they you know, there is a guy who's like

517
00:26:34,280 --> 00:26:36,920
Speaker 2: a throwing coach as well, so you can even have

518
00:26:37,000 --> 00:26:39,160
Speaker 2: like some specialties to them.

519
00:26:39,280 --> 00:26:41,280
Speaker 1: But like guy dreams of being the corner kick.

520
00:26:41,200 --> 00:26:43,640
Speaker 3: Coach, Yeah, gets promotion too.

521
00:26:44,760 --> 00:26:48,280
Speaker 1: So I mean just thinking more generally, like it seemed

522
00:26:48,320 --> 00:26:53,679
Speaker 1: well other sports, my US centric sports knowledge, which itself

523
00:26:53,720 --> 00:26:59,160
Speaker 1: is somewhat limited. Like clearly analytics have changed. You know football,

524
00:26:59,200 --> 00:27:02,040
Speaker 1: you see people going for it on fourth down. More basketball,

525
00:27:02,119 --> 00:27:06,560
Speaker 1: obviously the demise of the mid range shot, right, somebody

526
00:27:06,640 --> 00:27:09,760
Speaker 1: just realized analytically some years ago, like don't shoot from

527
00:27:09,840 --> 00:27:12,320
Speaker 1: whatever twelve feet out right, shoot from under the basket

528
00:27:12,400 --> 00:27:14,480
Speaker 1: or take a three. And in baseball there was the shift,

529
00:27:14,480 --> 00:27:17,800
Speaker 1: like there are these big, big changes in the way

530
00:27:17,800 --> 00:27:21,360
Speaker 1: the games look because of analytics. Is there anything analogous

531
00:27:21,440 --> 00:27:22,280
Speaker 1: in soccer?

532
00:27:22,800 --> 00:27:25,520
Speaker 2: Yeah, probably, Like the earliest one was that the distance

533
00:27:25,560 --> 00:27:27,479
Speaker 2: from which people are shooting has changed.

534
00:27:27,680 --> 00:27:27,880
Speaker 1: Huh.

535
00:27:28,440 --> 00:27:29,440
Speaker 3: So you're not going.

536
00:27:29,400 --> 00:27:32,040
Speaker 2: To see a Charlie Adam taking a shot from forty

537
00:27:32,080 --> 00:27:35,680
Speaker 2: yards too often. And lets you know, there's like a oh,

538
00:27:35,680 --> 00:27:37,760
Speaker 2: the goalkeepers off his line is out of position. I

539
00:27:38,119 --> 00:27:42,040
Speaker 2: can get it in there, but because of you.

540
00:27:40,880 --> 00:27:41,639
Speaker 3: You know, I can't.

541
00:27:41,760 --> 00:27:45,480
Speaker 2: I can't take credit for it. It feels like, you know,

542
00:27:45,520 --> 00:27:47,280
Speaker 2: the invention of calculus, where there were a lot of

543
00:27:47,280 --> 00:27:49,040
Speaker 2: people kind of coming to this conclusion.

544
00:27:49,760 --> 00:27:52,199
Speaker 1: So you're saying, you might not be Newton, but if

545
00:27:52,240 --> 00:27:54,200
Speaker 1: you're not Newton, your liibnitz.

546
00:27:53,760 --> 00:27:58,960
Speaker 2: Yes, okay, fair enough, I'll take that. Yeah, that's probably

547
00:27:59,040 --> 00:28:02,200
Speaker 2: like the earliest one. And then again, like you can't

548
00:28:02,280 --> 00:28:05,760
Speaker 2: prove causality, but there's been a shift to this tactic

549
00:28:05,840 --> 00:28:08,800
Speaker 2: of teams putting a lot of pressure up high. So

550
00:28:10,080 --> 00:28:12,199
Speaker 2: if they have the ball in the attacking area of

551
00:28:12,240 --> 00:28:15,320
Speaker 2: the pitch and they lose it, they immediately put pressure

552
00:28:15,359 --> 00:28:16,920
Speaker 2: on the other team to try to win it back

553
00:28:17,400 --> 00:28:18,480
Speaker 2: as quickly as possible.

554
00:28:18,600 --> 00:28:20,359
Speaker 1: Uh huh, kind of a full court press.

555
00:28:20,600 --> 00:28:21,480
Speaker 3: Yeah, exactly.

556
00:28:21,640 --> 00:28:23,840
Speaker 2: And so I don't know if the origin of that

557
00:28:24,000 --> 00:28:27,200
Speaker 2: is based in analytics, but like analytics will tell you, yeah,

558
00:28:27,240 --> 00:28:28,880
Speaker 2: you're more likely to score a goal if you win

559
00:28:28,920 --> 00:28:30,240
Speaker 2: the ball back up pie.

560
00:28:31,240 --> 00:28:32,160
Speaker 3: So that's another one.

561
00:28:32,560 --> 00:28:34,840
Speaker 1: Huh, why do you think people didn't do it before?

562
00:28:35,000 --> 00:28:37,200
Speaker 1: Is it not intuitively obvious that that's good?

563
00:28:37,760 --> 00:28:41,160
Speaker 2: Yeah, because if you don't want to be tired, well yeah,

564
00:28:41,200 --> 00:28:44,000
Speaker 2: so one, it makes you tired and there is like

565
00:28:44,040 --> 00:28:46,280
Speaker 2: a risk of injury. Trying to kind of like make

566
00:28:46,320 --> 00:28:49,640
Speaker 2: the guys super fit to do this. But two, kind

567
00:28:49,640 --> 00:28:52,080
Speaker 2: of going back to like the fourth down analogy, if

568
00:28:52,080 --> 00:28:54,479
Speaker 2: you don't win the ball back, then you've committed so

569
00:28:54,480 --> 00:28:58,720
Speaker 2: many players upfield that you're going to concede kind of.

570
00:28:58,640 --> 00:29:00,000
Speaker 3: Like silly looking up.

571
00:29:00,120 --> 00:29:01,000
Speaker 1: It's risky.

572
00:29:01,120 --> 00:29:03,040
Speaker 3: It's risky. Yeah, it's a calculated.

573
00:29:02,640 --> 00:29:05,840
Speaker 1: Risk, but you expected value is positive, but the variance

574
00:29:05,920 --> 00:29:06,320
Speaker 1: is high.

575
00:29:06,520 --> 00:29:08,880
Speaker 3: Exactly what's what's what are.

576
00:29:08,760 --> 00:29:11,920
Speaker 1: Some interesting frontier problems? I mean they're sort of getting

577
00:29:11,960 --> 00:29:13,959
Speaker 1: people to listen to you, which we've talked about, but

578
00:29:14,080 --> 00:29:17,160
Speaker 1: just on the analytics side, Like, what are you trying

579
00:29:17,160 --> 00:29:20,880
Speaker 1: to figure out on on the analytics side, what's a

580
00:29:20,880 --> 00:29:22,480
Speaker 1: big problem You're trying to solve.

581
00:29:23,400 --> 00:29:26,520
Speaker 2: One area that we haven't really exploited yet, but I'm

582
00:29:26,640 --> 00:29:27,320
Speaker 2: curious about.

583
00:29:27,360 --> 00:29:29,520
Speaker 3: But we always have this problem that like we.

584
00:29:29,520 --> 00:29:33,960
Speaker 2: Can't always learn from the data because everybody's doing the

585
00:29:33,960 --> 00:29:34,440
Speaker 2: same thing.

586
00:29:34,600 --> 00:29:37,720
Speaker 1: You can't really do an ab test because everybody does a.

587
00:29:38,240 --> 00:29:40,640
Speaker 3: Yeah exactly, and so it's really frustrating.

588
00:29:40,640 --> 00:29:44,120
Speaker 2: I mean, like the biggest example would be substitution patterns.

589
00:29:44,160 --> 00:29:48,280
Speaker 2: Everybody makes roughly the same type of substitution at the

590
00:29:48,280 --> 00:29:49,040
Speaker 2: same time.

591
00:29:49,200 --> 00:29:52,719
Speaker 1: And presumably it's not optimal, right, it's just conventional wisdom.

592
00:29:52,800 --> 00:29:54,640
Speaker 1: You're like, there could be a whole better world that

593
00:29:54,720 --> 00:29:55,680
Speaker 1: nobody's ever tried.

594
00:29:56,000 --> 00:29:59,200
Speaker 2: Yeah, exactly, And so I think, you know, with generative AI,

595
00:29:59,480 --> 00:30:01,640
Speaker 2: like now you're kind of talking about, like what can

596
00:30:01,680 --> 00:30:05,680
Speaker 2: we do really smart, really realistic simulations on these.

597
00:30:05,560 --> 00:30:07,160
Speaker 1: Sorts of things synthetic data.

598
00:30:07,520 --> 00:30:09,520
Speaker 3: Yeah, yeah, that's what we're hoping.

599
00:30:09,720 --> 00:30:12,760
Speaker 1: Oh so are you trying to figure out a better

600
00:30:13,440 --> 00:30:16,560
Speaker 1: way to do substitutions? Yes, yeah, you feel like you

601
00:30:16,640 --> 00:30:18,000
Speaker 1: got it? Do you feel like you have one in

602
00:30:18,000 --> 00:30:19,560
Speaker 1: your pocket? Or you're not quite ready to say.

603
00:30:20,040 --> 00:30:22,600
Speaker 2: I mean, we have some theories, we haven't proven them,

604
00:30:22,640 --> 00:30:25,200
Speaker 2: but like we also need somebody to say, like, yeah,

605
00:30:24,960 --> 00:30:27,680
Speaker 2: go ahead, like mess with our substitution patterns.

606
00:30:27,720 --> 00:30:28,800
Speaker 3: We feel comfortable with us.

607
00:30:28,880 --> 00:30:32,040
Speaker 1: H It is amazing how I mean, like if you

608
00:30:32,040 --> 00:30:35,120
Speaker 1: think of the shift in baseball or whatever, like a

609
00:30:35,200 --> 00:30:37,920
Speaker 1: game can just exist for one hundred years and there

610
00:30:37,920 --> 00:30:40,920
Speaker 1: can be a way better way to do it, and

611
00:30:40,960 --> 00:30:44,040
Speaker 1: nobody ever does it just because they don't have the

612
00:30:44,080 --> 00:30:45,560
Speaker 1: imagination or the courage.

613
00:30:46,040 --> 00:30:46,960
Speaker 3: Yeah, it's it's.

614
00:30:46,840 --> 00:30:48,680
Speaker 2: Wild and I think, you know, that sort of thing,

615
00:30:48,920 --> 00:30:51,920
Speaker 2: like I hope in soccer is less common because it's

616
00:30:51,960 --> 00:30:55,920
Speaker 2: more of like an adversarial game, but it.

617
00:30:55,840 --> 00:30:59,200
Speaker 1: Maps to the world more generally, right, Like I think

618
00:30:59,240 --> 00:31:01,120
Speaker 1: a lot of it is just fear, like you won't

619
00:31:01,120 --> 00:31:03,520
Speaker 1: get in trouble if you do the thing everybody else

620
00:31:03,560 --> 00:31:05,720
Speaker 1: did and you have a bad outcome, like you see

621
00:31:05,720 --> 00:31:09,800
Speaker 1: it in you know, in finance certainly, right, Like a

622
00:31:10,160 --> 00:31:14,240
Speaker 1: financial advisors just exhibit herd behavior because the way the

623
00:31:14,240 --> 00:31:16,440
Speaker 1: incentives are structured, Like if you do what everybody does

624
00:31:16,440 --> 00:31:18,080
Speaker 1: and you lose money, you're like, I was just doing

625
00:31:18,160 --> 00:31:19,200
Speaker 1: what everybody else did.

626
00:31:20,520 --> 00:31:23,160
Speaker 3: Yeah, yeah, and it's it's really frustrating.

627
00:31:23,160 --> 00:31:25,760
Speaker 2: And so you know, I think that again goes back

628
00:31:25,760 --> 00:31:28,360
Speaker 2: to like why we want to get control of a club,

629
00:31:28,400 --> 00:31:31,640
Speaker 2: because you know, I think there is a lot of

630
00:31:32,400 --> 00:31:36,400
Speaker 2: ways that we can optimize things, and if we're only

631
00:31:36,400 --> 00:31:40,600
Speaker 2: reporting to ourselves, then it's like, well, you know, I'm

632
00:31:40,640 --> 00:31:43,720
Speaker 2: not going to fire myself just because the theory didn't

633
00:31:43,720 --> 00:31:44,120
Speaker 2: work out.

634
00:31:44,280 --> 00:31:47,120
Speaker 1: Yes, it's hard to get to a big enough end though, right,

635
00:31:47,160 --> 00:31:48,959
Speaker 1: it's hard to get to a big enough samplicized there

636
00:31:49,040 --> 00:31:53,400
Speaker 1: just aren't that many games. So let's talk about the

637
00:31:53,440 --> 00:31:57,520
Speaker 1: sort of happy outcome for you. Say it's whatever, five

638
00:31:57,600 --> 00:32:01,800
Speaker 1: years from now and you have found capital, You've found

639
00:32:01,840 --> 00:32:03,920
Speaker 1: somebody who wants to essentially bet on you, which is,

640
00:32:03,920 --> 00:32:06,360
Speaker 1: if I understand correctly, what would have to happen, and

641
00:32:06,480 --> 00:32:12,560
Speaker 1: you are, you know, with your financy financierer partners running

642
00:32:12,600 --> 00:32:14,520
Speaker 1: a club. What's that look like?

643
00:32:15,960 --> 00:32:19,280
Speaker 2: Yeah, I mean I think it would look really really different.

644
00:32:20,160 --> 00:32:22,280
Speaker 2: I think that the typical profile of who would be

645
00:32:22,280 --> 00:32:24,560
Speaker 2: working in that club would be quite different.

646
00:32:24,640 --> 00:32:25,160
Speaker 3: So I think the.

647
00:32:25,120 --> 00:32:31,440
Speaker 2: First thing is, yeah, nerdier for sure, fresh are It's

648
00:32:31,440 --> 00:32:33,840
Speaker 2: hard because like, you know, I've played a lot of

649
00:32:33,840 --> 00:32:36,000
Speaker 2: sports growing up, and so it's like, well, you know,

650
00:32:36,080 --> 00:32:41,280
Speaker 2: I'm not that nerdy. And then it's like, oh yeah, yeah,

651
00:32:41,600 --> 00:32:43,479
Speaker 2: but yeah, I mean I think it would look nerdier,

652
00:32:43,480 --> 00:32:45,520
Speaker 2: but I think it would be a lot more like

653
00:32:45,680 --> 00:32:49,360
Speaker 2: just a totally different mindset. Really a lot more people

654
00:32:49,360 --> 00:32:51,560
Speaker 2: who are like, yeah, let's do things differently, Let's have

655
00:32:51,640 --> 00:32:55,920
Speaker 2: the courage to try new things, and then let's have

656
00:32:56,040 --> 00:32:59,720
Speaker 2: kind of the thinking power behind it to not just

657
00:32:59,760 --> 00:33:02,760
Speaker 2: like let's try random things, but let's try really well

658
00:33:02,800 --> 00:33:06,000
Speaker 2: thought out, creative but courageous things.

659
00:33:06,160 --> 00:33:09,600
Speaker 1: When you talk about, like, you know, being bold and

660
00:33:09,640 --> 00:33:13,000
Speaker 1: creative and different, is there some particular thing you have

661
00:33:13,120 --> 00:33:15,480
Speaker 1: in mind? Is there's like one thing where you're like

662
00:33:15,640 --> 00:33:18,320
Speaker 1: that one thing I wish somebody would just try it.

663
00:33:19,360 --> 00:33:21,760
Speaker 2: I mean, right now, it's probably the substitution thing, because

664
00:33:21,760 --> 00:33:25,000
Speaker 2: that's like the lowest hanging fruit, and it like really

665
00:33:25,040 --> 00:33:26,920
Speaker 2: really drives me nuts.

666
00:33:27,000 --> 00:33:29,600
Speaker 1: What's your secret theory? What do you think would be better?

667
00:33:29,760 --> 00:33:31,200
Speaker 3: Oh, I think you should do early.

668
00:33:31,280 --> 00:33:33,120
Speaker 2: I think you should kind of treat it like line

669
00:33:33,200 --> 00:33:37,160
Speaker 2: changes in hockey. So I mean, like right now, what

670
00:33:37,200 --> 00:33:40,080
Speaker 2: they do is they typically try to bring on maybe

671
00:33:40,120 --> 00:33:42,920
Speaker 2: like a fast player late in the game that you

672
00:33:42,960 --> 00:33:45,560
Speaker 2: know would theoretically be running against tired legs.

673
00:33:46,120 --> 00:33:48,000
Speaker 3: But the problem is that like it's.

674
00:33:47,920 --> 00:33:50,720
Speaker 2: Too late, and so you know, our ideas basically like

675
00:33:50,840 --> 00:33:53,560
Speaker 2: bring on people who like know that they only have

676
00:33:53,600 --> 00:33:56,840
Speaker 2: thirty minutes, run as hard as you can, as crazy

677
00:33:56,840 --> 00:34:00,400
Speaker 2: as you can, get that one goal advantage, your two

678
00:34:00,400 --> 00:34:03,080
Speaker 2: goal advantage, and then adapts.

679
00:34:02,840 --> 00:34:06,240
Speaker 1: And nobody has tried that. That doesn't seem crazy, Like

680
00:34:06,320 --> 00:34:09,439
Speaker 1: there's one hundred soccer teams, all you need is one

681
00:34:09,560 --> 00:34:11,520
Speaker 1: verson to try it. It's like a free idea.

682
00:34:11,600 --> 00:34:12,279
Speaker 3: I know, I don't.

683
00:34:12,320 --> 00:34:14,480
Speaker 2: Well, you know, if we see like a change in

684
00:34:14,520 --> 00:34:18,400
Speaker 2: substitution patterns after this content, yeah, that's right. Yeah, but

685
00:34:18,640 --> 00:34:20,360
Speaker 2: you know, like the crazy thing is there used to

686
00:34:20,360 --> 00:34:22,920
Speaker 2: only be three substitutions in soccer, and so you always

687
00:34:22,920 --> 00:34:25,759
Speaker 2: wanted to keep at least one in case a player

688
00:34:25,800 --> 00:34:28,799
Speaker 2: gets injured, so that really leaves you with two. But

689
00:34:28,880 --> 00:34:31,759
Speaker 2: during COVID, they upped it to five, and so now

690
00:34:31,760 --> 00:34:32,359
Speaker 2: it's like, well you.

691
00:34:32,320 --> 00:34:37,239
Speaker 1: Have that has persisted. Yeah, so they've almost doubled the

692
00:34:37,320 --> 00:34:41,680
Speaker 1: number of substitutions allowed. Has the strategy in using them changed?

693
00:34:41,960 --> 00:34:46,640
Speaker 2: No, it's like very slightly changed, And a lot of

694
00:34:46,640 --> 00:34:49,919
Speaker 2: coaches don't even take advantage of all substitutes.

695
00:34:50,400 --> 00:34:54,399
Speaker 1: Why do you think nobody has, you know, dramatically significantly

696
00:34:54,480 --> 00:34:57,719
Speaker 1: changed their strategy around substitutions even though the rule has

697
00:34:57,800 --> 00:34:59,279
Speaker 1: changed so significant.

698
00:34:59,680 --> 00:35:02,200
Speaker 3: One, I mean, I guess there's like two explanations.

699
00:35:02,200 --> 00:35:04,480
Speaker 2: The easiest one is like, well, it's always been the

700
00:35:04,520 --> 00:35:05,600
Speaker 2: way that we've done it, so.

701
00:35:06,520 --> 00:35:07,880
Speaker 3: You know why change?

702
00:35:08,719 --> 00:35:11,480
Speaker 2: I think part of what's driving that though, is that

703
00:35:11,600 --> 00:35:16,200
Speaker 2: the way that rosters are constructed hasn't changed. And so

704
00:35:16,480 --> 00:35:18,520
Speaker 2: you know, depending on like the finances of a team,

705
00:35:18,560 --> 00:35:22,920
Speaker 2: you might not have as many like quality players to

706
00:35:23,000 --> 00:35:27,120
Speaker 2: go that deep onto the bench. But you know, if

707
00:35:27,120 --> 00:35:29,360
Speaker 2: this is your strategy, then you can change how you recruit,

708
00:35:29,400 --> 00:35:32,200
Speaker 2: you can change the profile of that squad composition.

709
00:35:32,560 --> 00:35:35,239
Speaker 1: The second answer is interesting, right, because it requires you

710
00:35:35,320 --> 00:35:38,120
Speaker 1: to think more systematically. It's like, oh, the rules are different,

711
00:35:38,200 --> 00:35:41,120
Speaker 1: so therefore we should build a different team, which is

712
00:35:41,200 --> 00:35:42,080
Speaker 1: kind of next level.

713
00:35:42,280 --> 00:35:46,560
Speaker 2: Yeah, and yeah, that's that's not typically how teams operate.

714
00:35:50,040 --> 00:35:52,160
Speaker 1: We'll be back in a minute with the lightning round.

715
00:36:01,680 --> 00:36:06,240
Speaker 1: We're gonna finish with the lightning round. Okay, soccer or football?

716
00:36:06,840 --> 00:36:11,120
Speaker 1: I say football, frieser chips, chips, Cookies are biscuits.

717
00:36:12,160 --> 00:36:14,279
Speaker 3: So my husband is from India and he will kill

718
00:36:14,320 --> 00:36:15,440
Speaker 3: me if I say cookies.

719
00:36:15,480 --> 00:36:19,799
Speaker 1: But cookies are there other britishisms. You sign your emails cheers.

720
00:36:20,440 --> 00:36:24,560
Speaker 3: Sometimes I hate doing it. Mate is another one?

721
00:36:24,840 --> 00:36:25,080
Speaker 1: Mate?

722
00:36:25,200 --> 00:36:27,000
Speaker 3: Yeah, yeah, because that's what.

723
00:36:27,080 --> 00:36:29,479
Speaker 1: You call everything brilliant. I love talking to British people

724
00:36:29,480 --> 00:36:31,120
Speaker 1: because they say everything I say is brilliant, but they

725
00:36:31,160 --> 00:36:32,000
Speaker 1: don't mean it. The way I think.

726
00:36:32,239 --> 00:36:36,800
Speaker 3: Yeah, it's brilliant, bloody. Yeah, just little things.

727
00:36:36,600 --> 00:36:39,719
Speaker 1: By British guy once said blind I loved that.

728
00:36:40,239 --> 00:36:43,240
Speaker 2: Yeah, I've not not done.

729
00:36:43,000 --> 00:36:43,480
Speaker 3: That, but yeah.

730
00:36:43,480 --> 00:36:45,279
Speaker 2: I think when I was little, my brother and I

731
00:36:45,360 --> 00:36:48,759
Speaker 2: used to antagonize my dad until he would like yell

732
00:36:48,760 --> 00:36:52,080
Speaker 2: at us in British slang, and that was like success

733
00:36:52,080 --> 00:36:52,520
Speaker 2: for us.

734
00:36:53,280 --> 00:36:54,960
Speaker 1: Give me your impression of your dad yelling at your

735
00:36:55,040 --> 00:36:55,600
Speaker 1: British slang.

736
00:36:56,120 --> 00:36:58,640
Speaker 3: It would just say, like, oh, bugger off, the.

737
00:36:58,719 --> 00:37:03,439
Speaker 1: Bugger off is good. What's one thing you learned working

738
00:37:03,480 --> 00:37:04,600
Speaker 1: at Microsoft?

739
00:37:06,280 --> 00:37:09,120
Speaker 3: It's hard to get things done in large companies.

740
00:37:10,560 --> 00:37:12,320
Speaker 1: Do you have any tips for getting things done in

741
00:37:12,400 --> 00:37:14,280
Speaker 1: large companies? Or is it just leave?

742
00:37:15,560 --> 00:37:18,960
Speaker 2: I mean my answer was leave, But yeah, I mean

743
00:37:19,000 --> 00:37:22,520
Speaker 2: I think there's there's certain behaviors that maybe I don't

744
00:37:22,560 --> 00:37:26,720
Speaker 2: necessarily possess or like love, but like aggressive, loud people

745
00:37:26,800 --> 00:37:28,440
Speaker 2: tend to get things done.

746
00:37:28,719 --> 00:37:33,960
Speaker 1: There were there in the Balmer area era. That's very

747
00:37:33,960 --> 00:37:40,839
Speaker 1: Steve Balmer vibes. Who's the most underrated player you've ever seen?

748
00:37:41,800 --> 00:37:46,040
Speaker 2: Ooh, it might be this guy named Manu Tregueros. He

749
00:37:46,120 --> 00:37:51,120
Speaker 2: plays for a club in Spain called Viriao, and I

750
00:37:51,160 --> 00:37:54,080
Speaker 2: think he's brilliant he was kind of born at a

751
00:37:54,120 --> 00:37:57,280
Speaker 2: time when Spain had like loads of really really talented

752
00:37:57,280 --> 00:37:59,960
Speaker 2: players in his position, so he never got called up

753
00:38:00,120 --> 00:38:01,839
Speaker 2: the national team or anything like that.

754
00:38:02,360 --> 00:38:04,400
Speaker 3: But his running style is like a little bit nerdy,

755
00:38:04,520 --> 00:38:05,359
Speaker 3: Like he runs very.

756
00:38:05,360 --> 00:38:08,840
Speaker 2: Much on his toes, and you know, he doesn't look

757
00:38:08,960 --> 00:38:13,279
Speaker 2: like an athlete. He actually is like a like while

758
00:38:13,320 --> 00:38:16,640
Speaker 2: he was playing professionally, he was doing his master's in education,

759
00:38:16,800 --> 00:38:18,040
Speaker 2: so he was like a student teacher.

760
00:38:18,080 --> 00:38:20,120
Speaker 1: Like, it's just it's just that you love him. It's

761
00:38:20,160 --> 00:38:22,640
Speaker 1: not that he's an amazing player. Is that I love him?

762
00:38:22,760 --> 00:38:26,400
Speaker 2: I love him, but like he was also an amazing player,

763
00:38:26,440 --> 00:38:29,440
Speaker 2: but I think like having this air of like nerdiness

764
00:38:29,480 --> 00:38:32,279
Speaker 2: around him kind of kept him a little bit under

765
00:38:32,280 --> 00:38:32,720
Speaker 2: the radar.

766
00:38:33,160 --> 00:38:35,279
Speaker 1: Who's the most overrated player you've ever seen?

767
00:38:36,400 --> 00:38:43,839
Speaker 2: Ooh, that's a yeah, that's a really hard one.

768
00:38:45,400 --> 00:38:46,920
Speaker 1: Are you afraid of getting in trouble? Is there a

769
00:38:47,000 --> 00:38:48,440
Speaker 1: name in your mind and you just don't want to

770
00:38:48,480 --> 00:38:50,760
Speaker 1: say it because you don't want to antagonize anybody.

771
00:38:51,080 --> 00:38:53,000
Speaker 3: Yeah, definitely, there's some of that.

772
00:38:53,080 --> 00:38:55,520
Speaker 2: And then there's like a little bit of like hindsight bias,

773
00:38:55,560 --> 00:38:58,520
Speaker 2: where it's like there were guys who were overrated at.

774
00:38:58,360 --> 00:39:02,680
Speaker 3: The moment and then like kind of crumbled and failed.

775
00:39:02,680 --> 00:39:05,480
Speaker 2: So it's like, well, if I say like Marlon Shamack,

776
00:39:05,560 --> 00:39:09,520
Speaker 2: who was a kind of like a notoriously disastrous signing

777
00:39:09,560 --> 00:39:11,920
Speaker 2: for Arsenal, everyone would say like.

778
00:39:11,920 --> 00:39:16,320
Speaker 1: Oh, yeah, too easy. Yeah, what's one piece of advice

779
00:39:16,400 --> 00:39:20,520
Speaker 1: you have for women working in male dominated fields?

780
00:39:21,520 --> 00:39:25,400
Speaker 3: Oh, that's a really good one.

781
00:39:26,200 --> 00:39:29,120
Speaker 2: It would probably be that just you belong and know

782
00:39:29,200 --> 00:39:32,879
Speaker 2: that you belong, and don't let people try to make

783
00:39:32,920 --> 00:39:35,920
Speaker 2: you feel that you don't. And one of the ways

784
00:39:35,920 --> 00:39:38,640
Speaker 2: that you can do that is talk to other women.

785
00:39:39,440 --> 00:39:42,000
Speaker 2: When I got started fifteen years ago, like there weren't

786
00:39:42,160 --> 00:39:46,000
Speaker 2: any other women. Now there's loads of women working in

787
00:39:46,040 --> 00:39:50,719
Speaker 2: all different sports and all different sorts of roles. And

788
00:39:51,040 --> 00:39:53,759
Speaker 2: a couple of years ago there's conference started called Women

789
00:39:53,800 --> 00:39:56,759
Speaker 2: in Sports Data. This year it's could be held in

790
00:39:56,840 --> 00:40:00,520
Speaker 2: Philadelphia September seventh, I think. But it's like a great

791
00:40:00,560 --> 00:40:03,600
Speaker 2: place to connect with people because to me, I find

792
00:40:03,640 --> 00:40:06,960
Speaker 2: it really powerful to be in like a gymnasium with

793
00:40:07,400 --> 00:40:10,200
Speaker 2: like a room literally full of women who are interested

794
00:40:10,239 --> 00:40:15,560
Speaker 2: in sports and data and technology. And yeah, just I

795
00:40:15,560 --> 00:40:18,680
Speaker 2: don't know, it's good for your mental health, it's good

796
00:40:18,680 --> 00:40:22,000
Speaker 2: for you know, your self esteem and everything. But yeah,

797
00:40:22,080 --> 00:40:24,239
Speaker 2: just know that that you belong, that you can do it,

798
00:40:25,719 --> 00:40:27,880
Speaker 2: and that yeah, nobody should tell you otherwise.

799
00:40:29,440 --> 00:40:33,000
Speaker 1: So Brad Pitt played Billy Bean and Moneyball. Who's going

800
00:40:33,080 --> 00:40:36,040
Speaker 1: to play you in Moneyball too? Don't call it soccer?

801
00:40:37,400 --> 00:40:41,680
Speaker 2: Oh yeah, I have I have no idea. I don't

802
00:40:41,680 --> 00:40:43,800
Speaker 2: watch a lot of movies, So, like, I couldn't even

803
00:40:44,280 --> 00:40:47,719
Speaker 2: name an actress right now. Maybe maybe Kiera Knightley because

804
00:40:47,760 --> 00:40:51,920
Speaker 2: she was in Bendettlake Beckham, So I'll go with Kiera Knightley.

805
00:40:54,680 --> 00:40:58,440
Speaker 1: Sarah Rudd is the co founder and CEO of Source Football.

806
00:40:59,600 --> 00:41:02,880
Speaker 1: Today's show was produced by Gabriel Hunter Cheng. It was

807
00:41:03,160 --> 00:41:06,640
Speaker 1: edited by Lyddy jeene Kott and engineered by Sarah Brugeer.

808
00:41:07,120 --> 00:41:10,680
Speaker 1: You can email us at Problem at Pushkin dot Fm.

809
00:41:10,840 --> 00:41:13,160
Speaker 1: I'm Jacob Oldstein and we'll be back next week with

810
00:41:13,239 --> 00:41:28,240
Speaker 1: another episode of What's Your Problem