Why Raw Data Traps Football Scouts
About this episode
Why Raw Data Traps Football Scouts
So I want you to picture this. You're standing on the sidelines
of a university football pitch, right?
This is in Nairobi, Kenya and you're watching a 19 year old
kid play just. Raw, unpolished energy.
Exactly. I mean, on the surface it looks
like a standard game, but underneath the jersey of this
specific player, his name is Francis Ozueno, there is a
soccer BGPS tracker and it is quietly collecting thousands of
data points. Thousands.
Every single step. Every sudden stop.
Right. He hits 26 kilometers an hour.
He registers 32 high speed accelerations in on a single
hour. I mean, he's generating a
physical footprint that rivals a European professional.
Which is incredible for a 19 year old in the University
league. It's massive.
But here is the crazy part. The elite sports scout looking
at this data, they decide to well to penalize him.
Yeah, they act suppress his score.
Right. They lowered his metrics and
flag him with a medium risk rating.
And today on the Deep Dive, we are looking at the highly
confidential Afrotech sports technology dossier on Francis.
And it is a fascinating read because what we discover is why,
in the modern era of elite sports science, having
incredibly impressive raw data is, you know, actually the
single biggest trap in the industry.
It really is. I mean this deep dive today,
it's all about the architecture of talent.
We are looking at the exact moment where elite Formula One
level sports science intelligence transitions all the
way down to the grassroots. It's the nuts and bolts of how
talent is engineered. Today, exactly.
So whether you're an aspiring athlete, maybe a coach on a
budget, or just someone who loves the hidden systems behind
world class talent, we are going to look under the hood.
We're going to see how the pros separate the actual signal from
the noise. And to do that, you know, we
really have to look at the structural philosophy of the
AFRITEC TSA integrated scouting model.
Right, because their philosophy completely rejects the old
romanticized idea of scouting. Right.
Oh, completely. I mean, for decades the
narrative around African football, or really any
developing sports ecosystem, was all about raw talent.
The grizzled scout on the touchline, trusting his gut.
Exactly, claiming he can spot a generation layer just by the way
they run. But the Afrotech model violently
rejects that premise. They argue that the gap between
the local pitch and an international stadium isn't
closed by natural gifts, It's closed by systems, by data
architecture. Which brings us to the dossier
itself. Because when I opened this
report, the very first thing I saw was this decision first
structure. And I have to admit I kind of
hated it. A.
Lot of people do it first. Well, yeah, because it feels
completely backwards, right? On Page 1, before I've seen a
single speed metric. The executive decision dashboard
brands Francis with a verdict. It's a scholarship
recommendation plus monitor. It gives you the answer before
the evidence. Exactly.
I mean, isn't that just grading the test before you read the
essay? You're anchoring the reader's
bias before they even evaluate the raw data.
You could definitely see it as anchoring bias, but consider the
alternative reality of the professional football market.
Attention is the single most scarce resource in elite
scouting. I mean, they're looking at
hundreds of players, right? Hundreds, sometimes thousands,
every single month. A sporting director doesn't have
the luxury of going on a 30 page journey of discovery.
If you bury the conclusion at the end of the report, it just
goes in the shredder. So it's basically a survival
mechanism for the data. Exactly.
The decision first matrix forces the scout to clearly define why
they are looking at the data before they get lost in it.
Because Afrotech breaks this down into four specific signals,
right club acquisition, agent representation, federation
selection, and the scholarship signal.
Right. And by stating upfront that
Francis is a monitor for a pro club but a scholarship
recommendation, they're framing the lens.
They're telling the reader, you know, don't expect a Finnish
Champions League starter here. Expect a highly malleable
university prospect. OK, that makes sense from an
efficiency standpoint, but let's actually look at the date of
this kid generated, because it's.
It really is, especially given the sample size.
Right, it's just 45.2 minutes total, spread across 2 entirely
separate sessions. So let's breakdown session one
first. Session 1 is on April 29th.
It's short, just 12.8 minutes to play.
But he is explosive. In those 12 minutes, his
distance per minute, his DPM hits 117.8 meters per minute and
he hits a top speed of 26.1 kilometers per hour.
But the key here is the movement signature.
It's heavily deceleration dominant.
He have 8 accelerations but 11 high intensity decelerations.
Right, so he's stopping constantly and this hit me when
I was reading it. Session 1 looks exactly like a
firefighter desperately putting out spot fires.
That is a great analogy. Right, because he's reacting to
emergencies, sprinting backwards, slamming on the
brakes. That is the classic behavior of
a center back. Holding the line and reacting
when the ball breaches the zone. Exactly.
But then you look at Session 2 just a few days later on May
2nd, and it flips completely upside down.
Completely different profile. Session 2 is 32.4 minutes long,
but his DPM drops sharply to 88.6 meters per minute.
And his top speed is lower too, right down to 24 kilometers per
hour. Right.
But the crucial part is his movement signature reverses.
He goes from being deceleration dominant to hyperacceleration
dominant. A staggering 24 accelerations
compared to only 8 decelerations.
Exactly. So if session 1 is a
firefighter, session 2 looks like a guard dog actively
pushing the perimeter. He's proactive, accelerating
into open space to initiate defense, which is the classic
signature of a defensive midfielder.
It's a highly accurate visualization.
And this is where a lazy scout might look at the drop in top
speed and distance from session one to session 2 and just say,
oh, his fitness is poor, right? They'd say he can't sustain his
intensity over 30 minutes. Exactly.
Yeah, but the dossier introduces this critical context variable
called fixture density. The chronological gap between
April 29th and May 2nd is less than four days.
Which for a 19 year old without elite recovery protocols like
ice baths or advanced nutrition, that is a massive physiological
load. Right.
So the physical drop off isn't necessarily a low fitness
ceiling. It's highly likely to be
residual muscle fatigue and more importantly, it's a roll context
shift. A center back slamming on the
brakes generates completely different stress than a
defensive midfielder accelerating to screen the
pitch. You cannot compare the two data
sets without defining the tactical role first.
OK, so the data is telling us a story of a young player adapting
to different roles while tired. But there is another layer.
The dossier applies here and this is where I really need to
push back. The African ecosystem modifier.
Yes, because Afrotech literally deflates his numbers.
Nairobi is at high altitude right?
Roughly 1800 meters. So they apply an 8% manual
deflation to his metrics. Which is the most vital piece of
sport science translation in the whole document?
But wait, hear me out. Marathon runners train in Kenya
specifically because the thinner air gives them a cardiovascular
superpower. It forces the body to make more
red blood cells. That's true for steady state
aerobic endurance, yes. Right.
So if Francis is generating 97 meters a minute at altitude, if
you bring him to sea level in London, his engine should be
limitless. Why would Afrotech deflate his
output? Shouldn't they artificially
inflate his numbers to show his sea level potential?
It's a very common assumption, but you are conflating steady
state aerobic endurance with anaerobic maximal velocity
output. OK, explain the difference in
this context. Football is not a marathon.
It's an alactic and anaerobic sport.
It's a chaotic series of explosive sprints with
incomplete recovery. When Francis sprints at 1800
meters, the thinner air doesn't help him.
It limits his ability to clear metabolic waste.
So he's building up lactic acid way faster.
Exactly. He recovers from oxygen debt
much slower, However, and this is the crucial biomechanical
factor. Air resistance is lower at
altitude. It is physically easier to move
your body mass through the air. Oh.
Wow, I didn't even think about that.
Right, so players can hit artificially High Peak speeds in
short bursts because there is literally less air pushing
against them. So the 8% deflation isn't
punishing his aerobic fitness. No, it's a mathematical
recalibration of his peak velocity.
If you don't suppress that top speed metric, a European club
buys an expected 26 kilometers an hour in the thick, humid sea
level air of an English winter. And you just won't be able to
hit it. OK.
That completely reorients my understanding.
You're protecting the data from environmental inflation.
And it's not just altitude. The dossier adjusts for pitch
surface, too. A dry, uneven pitch causes more
chaotic ball movement than a pristine hybrid grass pitch in
the Premier League. Which forces players to run more
just to deal with the disorganization.
Exactly. Afrotex modifier accounts for
that chaos. So if you're a coach listening,
the ultimate take away here is that raw GPS readings are not
universal truths. They're deeply contextual.
If you don't adjust for altitude, pitch friction, and
tactical chaos, you artificially inflate the players market
value. Which leads us to the biggest
problem with this wearable tech. Because even with this adjusted
data, Francis's overall rating is only a 6.8.
He's flagged as medium risk. Why?
Because of what the dossier calls OBS Hold Observation hold.
Right, it's the ultimate reality check for sports analytics, the
dossier states bluntly. GPS activity does not equal ball
of uncertainty. I mean we get so seduced by the
dots moving on the screen the top speeds, we forget the
trackers just measuring a mass moving through space it.
Doesn't tell you what that mass did when a leather ball actually
arrived at its feet. Exactly.
Francis's technical domain is rated a Brutal 5.8 out of 10,
and not because he's technically bad, but strictly because of
missing evidence. The black holes in the data are
staggering. We have no verified passing
data, no data on receiving under pressure, weak foot competency
or ball security. The scout doesn't even know his
physical height, weight or dominant foot just from the GPS.
The tracker proves he has an elite engine, but it offers 0
proof that he can effectively participate in a game of
football. Let's use those 32 accelerations
from session 2 on a spreadsheet that looks phenomenal.
But you're saying those accelerations could actually be
a sign of terrible footballing ability?
Absolutely. The scout has to ask, were those
accelerations proactive, intelligent, pressing triggers?
Did he read the opponent and accelerate to win the ball?
If so, he's a genius, right? Or, conversely, were those 32
accelerations panicked, desperate sprints because his
initial positioning was completely wrong?
Because a panic Sprint looks exactly the same on AGPS tracker
as a brilliant pressing run. Exactly the same.
A line on a graph pointing sharply upwards.
This is why sports science integration is so critical.
You have to pair the wearable tech with synchronized video
tagging. So you take the timestamp of the
acceleration and overlay it onto the video to see the tactical
trigger. Without video to confirm passing
clips, first touch under pressure and aerial dual win
rates, Francis's true tactical value is purely A mathematical
projection. OK, so we've mapped out the
physical machine perfectly. We know we're missing the
technical manual, but what fuels the machine?
Because you can have the engine, but if the player breaks under
pressure it doesn't matter. Which brings us to the DPI
framework. Yes, I was looking at this and
it blew my mind that Afratec is actively trying to quantify what
is inside a 19 year old's head. It's arguably the most forward
thinking element of their methodology.
DPI stands for desire, ability, positioning, intelligence, and
Exit power. And they anchor these in
academic theory, right? It's not just buzzword.
Exactly. They are profiling his
psychological architecture. So let's dissect these His
desire scores A7 point O out of 10.
The dossier roots this in self determination theory.
Now, I know a bit about SDT from organizational psychology about
competence, autonomy and relatedness.
But how does a scout apply that to a dusty pitch in Nairobi?
Well, they use it to separate intrinsic motivation from
extrinsic motivation. If a player only plays hard
because an agent is watching, their effort plummets when
things get difficult. Right, that's extrinsic.
But Francis demonstrates high intrinsic motivation.
The very act of voluntarily putting on this tracking device,
knowing it will ruthlessly expose his flaws, shows a desire
for objective self improvement. He wants that competence and
autonomy. OK, that makes sense.
For the seven point O. Then we have ability which
scores a 6.8, and they anchor this in Anders Erickson's
concept of deliberate practice. Yes, and deliberate practice
isn't just about putting in 10,000 hours, it's about the
quality of those hours. It requires measurable outputs
and continuous adjustment. Because he adapts his physical
output between the center back role and the defensive
midfielder role. Exactly.
He isn't just mindlessly running.
He demonstrates A cognitive ability to absorb instructions
and alter his behavior based on tactical requirements.
But then we hit the final metric, and this is wild exit
power. This gets the lowest score in
his entire profile, a 5.7 out of 10, and the dossier links this
to agency theory. This is where the business of
modern scouting is absolutely cutthroat.
Great, because Exit power isn't measuring his psychology or his
speed, it's actively measuring his commercial leverage in the
global market. Why does he have practically 0
leverage? In economic terms, agency theory
deals with the relationship between a principal, like a
club, and an agent. The player leverage is dictated
by verified information and market demand.
And Francis doesn't have verified info.
Exactly. He doesn't possess A
commercially packaged video portfolio of his technical ball
events, his biometric data isn't publicly confirmed by a
federation, and he lacks formal, legally binding contract
representation. He is commercially invisible.
He's like a high performance engine sitting in a garage with
No title, no registration and no license plates.
That is the tragedy of developing ecosystems.
He has the mental architecture. He embraces the sport science,
but until it's paired with technical video and packaged
commercially, his exit power remains a 5.7.
He cannot force a transfer to a bigger club.
He can't demand a massive salary.
He has zero agency in the open market.
So if you're handed this specific profile, you have a kid
who is highly trainable, has massive physical potential, huge
data gaps regarding technical skills, and absolutely 0 market
leverage. What is his monetizable value
today? This leads directly to the
scholarship signal verdict on Page 1.
He is not ready for a professional club acquisition.
Hence the monitor status. Exactly.
But the dossier explicitly stays He holds immense institutional
value for a university sports science program.
OK, walk me through that business case.
Because if I'm the athletic director at Strathmore
University and my budget is super tight, why am I giving a
full academic scholarship to a kid whose technical skills are a
giant question mark? Because for the university,
Francis represents a live biological case study.
Funding talent here isn't about paying for a star striker to
guarantee a trophy. It's a strategic investment.
You're investing in a player who has the mental architecture to
act as a catalyst for your entire performance intelligence
system. It's an institutional hack.
A university in Nairobi likely cannot afford $100,000 stadium
wide optical tracking system. So you fund the kid who is
willing to wear the wearable tech, you fund the Guinea pig.
Exactly. By bringing Francis into the
program on a scholarship, Strathmore University
fundamentally transitions its entire football operation.
They move away from the subjective era of a coach.
Just saying. Oh, Francis looks sharp today.
Right. And they transition to the era
of measurable development evidence.
It creates this beautiful symbiotic relationship.
Francis this gets a free higher education, which is a massive
safety net, and he gets a structured environment to fill
in his technical black holes. And the university gets to build
an internal EPTS database from scratch.
They establish physical benchmarks for their region.
They elevate their coaching staff, their sports science
department, their physiotherapy students.
Francis. Becomes the living, breathing
anchor point for the university's data literacy
program, which is just incredible.
But it brings us to the execution.
The most critical part? The scholarship is offered.
Francis signs the paperwork. He has the tracker strapped to
his chest. What exactly do the coaches do
with him on Monday morning at 80 AM?
This is where the dossier provides a hyperactionable 90
day EPTS road map. And if you are a coach listening
right now at any level, this blueprint is something you can
replicate tomorrow. Let's look at phase one,
stabilization days, one through 30.
The directive is blunt. Stop guessing the.
Stabilization phase is entirely about data integrity.
For the 1st 30 days, every single match or training session
that Francis participates in must be meticulously recorded
both with GPS and video. And they have to use exact role
tags right? The analyst has to input whether
he is playing center back or defensive midfielder before the
whistle blows. If you do not tag the positional
role, your benchmarks are utterly useless.
If you compare his physiological output on a Tuesday playing
center back against the Saturday playing defensive midfielder,
you misinterpret the data. Like the firefighter and guard
dog analogy. Exactly.
Phase one creates a clean, pristine baseline of his true
physical outputs in a singular defined role.
Then we move to phase two, repeatability days 31 through
60, and this phase attacks those physiological red flags like the
severe high speed running drop off we saw.
The road map prescribes introducing 2 to 4 controlled
recovery sprints per half into his weekly training regimen.
So sports science moves from observation to intervention.
They are actively trying to improve his body's ability to
clear hydrogen ions at altitude. But crucially, Phase 2 is also
where they begin solving the OBS hold.
The coaching staff must start pairing the raw GPS data with
the video footage they need to visually code his acceleration
clusters. So the coach literally sits
down, pulls up the timestamp of those 32 accelerations, looks at
the video and asks Francis at minute 14.
Were you pressing intelligently or panicking because you were
out of position? You marry the objective spatial
data with the subjective tactical context.
Wow. And once you identify the
behavioral flaws in phase two, you move into phase three, the
development dossier days 61 to 90.
Now the training becomes hyper specific to his tactical
deficiencies. The road map mandates training,
2 specific behaviors for him, pressing trigger timing and his
first pass completion after regaining possession.
Because if his job is to be the proactive defensive midfielder,
he has to aggressively win the ball back and immediately secure
possession with a safe first pass.
OK, but reading through this highly regimented 90 day
biological and tactical programming, I have to ask about
the human element. How does a 19 year old process
being treated like a science experiment?
It is incredibly taxing. I mean, he's being probed,
measured, video tagged and adjusted daily.
That has to be exhausting. Which is why the road map
includes the single most important action item in the
entire dossier, the implementation of the data
literacy habit. What does that look like in
practice? The blueprint legally mandates a
15 minute weekly player review session.
The player is not allowed to just hand over the vest and go
home. Francis must sit down in a room
and actively look at his own metrics.
Because if he doesn't understand his DPM or his high speed
running ratio, the tracker is just a piece of plastic.
The data is just noise on a spreadsheet.
It's just a report card, he gets yelled.
At for precisely. But if the coaching staff
educates him, it triggers A profound psychological shift.
He stops viewing the data as a weapon used to criticize him and
he starts viewing his own body and decision making as
controllable variables. It shifts him from being a
passive passenger to the active pilot of his own career.
He knows exactly what the European market demands and
where he falls short. Education is the ultimate
mechanism for building that exit power we discussed.
Once a player understands their data, they can intentionally
generate the exact metrics the professional market wants to
buy. I mean, let's just take a step
back and look at the scale of this journey.
We started on a dusty university pitch with a microscopic 45
minute sample of GPS data. Just a handful of raw numbers.
117.8 distance per minute, 32 accelerations, A medium risk
score of 6.8. Right.
And from that tiny sliver of telemetry, we unpacked the
entire philosophy of elite sports scouting.
We navigated the harsh economic realities of the decision First
matrix. We.
Explore the African ecosystem modifier, understanding why
thinner air demands a support. Depression of top speed metrics.
We stared into the OBS hold black holes of missing technical
evidence, realizing that running fast means nothing if you can't
control the ball. We saw how psychological
resilience and market leverage are quantified through the DAPI
framework. And finally, we saw how this
tech doesn't just judge a player, it provides A
meticulously structured 90 day scholarship blueprint designed
to actively forge international caliber intelligence from the
ground up. It fundamentally changes talent
identification. The future of a sports
recruitment isn't about having a better eye for the game, It is
entirely about possessing a superior architectural system
for processing data. Which leaves us with a massive
concept to consider. Think about the trajectory of
this tech right now. A Soccer B tracker and an
Afritech analysis is highly specialized, but what happens in
five years? When wearable biometric
technology becomes universally affordable.
Exactly. Imagine a world where every
single high school, university, and Academy player on the planet
is wearing one of these devices under their jersey.
When high fidelity spatial data is absolutely everywhere, the
competitive advantage will no longer belong to whoever simply
possesses the data, because everyone will have it.
The advantage will belong exclusively to whichever
institution has the rigorous discipline to organize that data
manually, adjust it for their specific ecosystem, and build a
relentless 90 day development system around it.
Are we entering an era where the very concept of raw talent is
practically obsolete? Think about it.
Podbean