Sports Data Science · NFL · MLB

FIELD
MAN

Turning raw sports data into sharp insights — from the gridiron to the diamond.

Scroll
2Sports
5Projects
NFL · MLBLeagues
Python · R · SQLStack
01
Football
Expected
Points Added
4th Down
A machine learning model quantifying 4th-down decision-making across all NFL teams — revealing which coaches leave the most points on the field.
PythonXGBoost nflfastRPlotly
View Project
02
Baseball
Stat Creation: Strategic Control Against Batting (SCAB)
Interactive dashboard breaking down pitcher WAR into FIP, BABIP luck, and strand rate — isolating true performance from noise.
RStatcast Shinyggplot2
View Project
03
Football
WR Separation
Clustering
K-means clustering of NFL wide receivers by route tendencies and separation metrics — mapping archetypes across every roster in the league.
PythonsklearnNGS
View Project
04
Baseball
Exit Velocity
Zone Heatmaps
Pitch-by-pitch Statcast visualizations showing batted ball authority by zone — where hitters do damage and where pitchers can exploit weaknesses.
PythonpybaseballSeaborn
View Project
05
Football
QB Pressure
Performance
Index
Measuring QB performance under pressure using PFF data — a composite index revealing who thrives and who wilts when the pocket collapses.
SQLTableauPFF
View Project
06
Hockey
NHL Shot
Quality
Model
Expected goals model built on Stathletes shot-level data — mapping dangerous zones, scoring probability by angle and distance, and isolating goalie performance from team defense.
PythonMongoHockeysklearn
⏳ Coming Soon
07
Basketball
NBA
Lineup
Optimizer
Stagger analysis using NBA tracking data — identifying five-man unit synergies, optimal rotation windows, and the lineups coaches are sleeping on.
Pythonnba_apiPandas
⏳ Coming Soon
Select Project
01 Football EPA 4th Down
02 Baseball Stat Creation: SCAB
03 Football WR Separation
04 Baseball Exit Velocity
05 Football QB Pressure
06 Hockey NHL Shot Quality Coming Soon
07 Basketball NBA Lineup Opt. Coming Soon
FELDMAN
FIELD
MAN

The name says it all. Feldman — from the Yiddish for "man of the field" — and the field is exactly where the obsession lives. Two fields, actually: the gridiron and the diamond.

I'm a sports data scientist blending statistical modeling, machine learning, and visualization to answer the questions that matter — not the box score questions, but the deeper ones.

Why does your favorite team keep going for it on 4th down when the math says don't? What does a pitcher's stuff look like when you strip out the luck? That's the work.

Languages
Python
R
SQL
ML / Stats
XGBoost
sklearn
Stan
Viz
Plotly
ggplot2
Tableau
Data
nflfastR
Statcast
PFF
LET'S TALK
READY TO
COLLABORATE?
Whether you're a team, a media outlet, or a fellow data nerd — always open to conversations about sports, data, and where the two meet.