Designing IA for AI - Information Architecture Conference 2024
Data science in baseball
1. D ATA S C I E N C E I N B A S E B A L L
P R O F . A B H A M A R A T H E
2. T E A M
Harsh Tomar – 04
Harshvardhan Mulik – 05
Anushka Hedaoo – 06
Subodh Kadam – 22
Kartik Kakani -25
3. T H E R E ’ S
M O R E T O
W I N N I N G
T H A N
T R A I N I N G
H A R D A N D
S C O R I N G
P O I N T S
• From media contracts to
licensing deals, ticketing
and merchandising, and
even how many beats per
minute a player’s heart
pumps on game day, data
has essential information
for strategic decision
making.
4. W AY S T O U S E D ATA
SCOUTING PLAYER
FITNESS AND
DEVELOPMENT
GAME DAY
STRATEGY
PLAYER
EVALUATION
TICKETING MERCHANDISE
5. P L AY E R
D E V E L O P M E N T
• On-field wins often translates into a team’s financial
success, so developing talent and adding new players
adds obvious value to a club. Teams gather huge
amounts of data on players to track multiple metrics
such as training intensity, game performance, recovery
time, and injuries.
• Whole-team intelligence is important too. How are
players working together? Are there patterns of play? Do
various actions on the field make a difference in the final
score?
• Visualizing this data allows tech-averse coaches to
interpret immediate needs at a glance.
6. G A M E D AY
S T R AT E G Y
• Data science and visualizations don’t just capture
what happened in last week’s game; they can
provide insight while the ball is still in play.
• Dashboards help coaches predict outcomes with
what-if scenarios by combining live data with
historical data.
7. P L AY E R E VA L U AT I O N
Visual dashboards are a powerful tool for accurate individual
player evaluation. How is a player performing relative to last year?
Last week?
This data-driven evaluation clues coaches into who’s likely to play
well and who may be heading for a slump. Coaches can adjust
gameday lineups accordingly.
8. T I C K E T I N G
• It is important to understand single-game
demand for a variety of reasons, whether the
team is thinking about running a promotion, or
whether they are thinking about how to staff the
stadium, it all goes to help produce the most
amount of profit possible.
• The model is trained on 3 years of game data to
predict the number of tickets being sold.
• By understanding the demand, they can
schedule promotions around the most popular
games- which will hopefully optimize the
attendance and profit even more!
9. M E R C H A N D I S E
• The home-team hat and jersey, beer, and bobble
heads—what are people buying once they're inside?
• With merchandising and retail data visualizations,
retailers can adjust inventory on the fly when specific
item revenue starts to dip.
• Merchandise sales also reveal where a team’s fans live.
Data can help identify new areas of the country, or the
world, to concentrate sales efforts
10. S TAT- C A S T
• In 2015, MLB (Major League Baseball), introduced
StatCast in its games henceforth.
• StatCast uses machine learning and computer vision to
measure and evaluate plays during MLB games. We can
see a player’s max speed, distance covered, first step and
route efficiency.
• StatCast has given both fans and teams insight that wasn’t
available before. Players are now judged on hard data as
opposed to subjective scouting feedback — this allows
both players and teams to have a more accurate
assessment of themselves and helps teams truly judge a
player's value.
11. C O N C L U S I O N
Data Science has become an integral part of Baseball over in
years.
Almost every decision may it be before, during or after the match
is made using Data science and Visualization.
It helps players, coaches and even the audience to understand the
game better.