Translate location and efficiency data into clearer shot-quality and player tendency views.
Basketball analytics
Basketball
Shot quality, lineup combinations, spatial tracking, and possession-level storytelling.
Lucas Pichardo
Basketball Co-Chair
Stats & Data Science · 2027
Raja Kavasseri
Basketball Co-Chair
Stats & Data Science · 2027
Workstreams
What this team studies
Compare combinations, role fit, and possession outcomes across different groups.
Use statistical profiles to find comparable players, team needs, and development paths.
Featured work
NBA "What-If" Analyzer and Play Editor
A full-stack interactive web application with a React frontend, Flask API, and an ONNX-deployed MLP neural network to model real-time NBA win probability and simulate hypothetical game-state edits.
Problem
Existing win-probability graphs are static post-game visualizers that do not allow users or analysts to test counterfactual scenarios (e.g. 'what if the missed 3-pointer went in?').
Approach
Combined a React + Vite user interface with a Flask backend powered by nba_api data and an ONNX MLP neural network trained on historical play-by-play momentum curves to dynamically recompute win probability graphs when users edit historical game events.
Result
Open project Built a real-time interactive sandbox where analysts can alter play outcomes, view live win probability shifts, and compare prediction market odds from Kalshi and The-Odds-API.
Active projects
Current work
NBA Game-State Probability & Arbitrage Engine
April 22, 2026Basketball · 2025-26
A probability model and React prototype for evaluating NBA game states, player prop probabilities, and parlay arbitrage against sportsbook pricing.
ReactTypeScriptPython
Tool
UCLA Women's Basketball Transfer Intelligence Report
January 21, 2026Women's Basketball · 2025-26
An interactive five-tab dashboard built for UCLA Women's Basketball that maps transfer portal movement, compares first-year transfer vs. freshman on-court impact, and tracks career development across 8,300 freshman seasons and 1,354 transfer arrivals in Power 5 programs.
PythonPandasNetlify
Consulting
NBA "What-If" Analyzer and Play Editor
April 17, 2026Basketball · 2025-26
A full-stack interactive web application with a React frontend, Flask API, and an ONNX-deployed MLP neural network to model real-time NBA win probability and simulate hypothetical game-state edits.
ReactViteFlask
Tool
Forecasting NBA Player Fantasy Points
October 14, 2025Basketball · 2025-26
A predictive modeling framework for forecasting season-average NBA player statistics using gradient boosting, allowing fantasy projections under any custom scoring system.
PythonJupyter NotebookGradient Boosting
Research
Freshman Recruit Impact in Women's Basketball
March 15, 2026Women's Basketball · 2025-26
A 2017-2026 women's basketball recruiting study that evaluates ESPN SC Next 100 recruits by freshman usage, minutes, conference and position distribution, Big Ten context, and transfer timing.
PythonWeb scrapingSports Reference
Research
Archive
Past work
UCLA Women's Basketball RAG Analytics Chatbot
June 13, 2025Women's Basketball · 2024-25
An intelligent Retrieval-Augmented Generation (RAG) chatbot for UCLA Women's Basketball statistics and analytics, powered by Anthropic Claude 3.5 Sonnet, Flask, and ChromaDB.
PythonFlaskClaude 3.5 Sonnet
ToolArchived
What Makes an All-NBA Player?
September 11, 2020Basketball · 2020-21
A model of All-NBA selection using 10 seasons of NBA.com and Basketball-Reference data, testing variable-selection methods and logistic regression to identify the box-score and advanced stats most tied to All-NBA voting.
RPythonscikit-learn
ResearchArchived
Basketball on a Budget
June 14, 2017Basketball · 2016-17
A salary-efficiency roster builder that ranks 2015-16 NBA players by position, performance, and cost, then creates an example low-cost lineup and shot-chart comparisons against elite teams.
Big Data BallSalary dataShot charts
ResearchArchived
Statistically-Grounded All-NBA Defensive Team Selection Model
April 3, 2025Basketball · 2024-25
A statistical framework for predicting All-NBA Defensive Teams and Defensive Player of the Year by modeling possession-level matchup data rather than media narrative or box-score totals.
Pythonpandasscikit-learn
ResearchArchived
NBA Player PER Report
December 15, 2017Basketball · 2017-18
A PER ranking study that tests how touches, position, scoring, assists, and other player statistics explain PER rank across the 2013-14 through 2015-16 NBA seasons.
RRegressionANOVA
ResearchArchived
NBA Team Synergy Analysis
June 3, 2016Basketball · 2015-16
An exploratory study of 2011-12 NBA playoff teams that compares Eastern and Western contenders, team touches, roster composition, and predictors of player rank.
Rt-testsRegression
ResearchArchived
Predicting basketball shot probability based on player behavior and situational factors
October 22, 2024Basketball · 2024-25
Foundational research code and exploratory data analysis notebooks focusing on college and professional basketball efficiency metrics.
PythonJupyter Notebookpandas
ResearchArchived
Abolishing NBA Conferences
August 4, 2017Basketball · 2017-18
A playoff-seeding study showing that NBA conference alignment excluded deserving teams in 12 of 15 seasons, then comparing wildcard, conference-free, and tennis-style bracket alternatives.
Basketball-ReferencePlayoff seedingSchedule analysis
ResearchArchived