win-probability

Texas Hold'em poker algorithm (hand evaluation, lookup table, 1v1 win probability) with Joker wild-card support, in Java, Go and C++.

Live cricket scores and win probability dashboard. Built using Django and CricketData API, featuring dynamic polling, key rotation, and a custom WASP algorithm.

Was your League of Legends ranked game winnable? Free fairness verdict for any match: FAIR, NOT FAIR or FAVORED, from pre-game data only. Lane-by-lane scores, autofill, duos, smurfs and a win-probability bar.

Predicts UFC fight win probabilities, method of victory and round from historical UFCStats data, using leakage-safe chronological ML, weekly auto-refresh, and a Streamlit app.

Possession-level live win probability model for football using LSTM and GRU on StatsBomb La Liga data, with Poisson goal conversion and proper probabilistic evaluation.

Mechabellum replay and live-match analytics toolkit for data collection, model training, and win probability prediction.

XGBoost win probability model for MLB games, with WPA, Leverage Index, and a benchmark against classical sabermetrics. Live dashboard with pitch-by-pitch game replay.

Interactive NFL fourth-down decision audit using nfl4th and nflverse data. Compare coach decisions with modeled win-probability recommendations, identify conservative and aggressive misses, and explore coach decision fingerprints.

Live win probability, blunder detection, and hidden-team inference for competitive Pokémon Showdown battles — LightGBM on 19k+ ladder replays.

Calibrated live win probabilities for men's T20 run chases from a simple logistic model — Brier 0.1114, 55.4% skill vs base rate, every probability bucket within 5pp of observed win rate. Research code for MIT Sloan SSAC27

An AI-powered IPL match win probability prediction system using XGBoost and live match-state features. The project provides separate predictions for first and second innings and exposes the trained models through a FastAPI backend for real-time web predictions.

Live per-second round win probability for Counter-Strike 2: spatial control, bomb geometry, calibration, and an out-of-time test. Code, results, and preprint.

NFL in-game win probability model on 225k plays from six seasons of nflfastR. XGBoost, log loss 0.485 / AUC 0.841 on the held-out 2023 season. Python + DuckDB.

Steel trading sales, marketing and CRM analytics on a Dynamics 365 export: sales funnel, win-probability model and campaign ROI.

Machine learning dashboard for NBA win probability, covering pre-game predictions, live replay, model evaluation, and automated Finals refreshes with Google Cloud.

NBA win probability, momentum, and turning-point analytics engine.

Multi-level probabilistic framework linking risk-adjusted soccer action values to match-outcome context.

Win-probability curve calibrated to human play — held-out log-loss 0.575 vs Lichess's 0.738, re-validated on 4M off-corpus positions. Static review app runs Stockfish in a Web Worker, no backend.

CS2RB: 4.8M live Counter-Strike 2 round states, with code and results comparing aggregate and individual-player round-win models, including a pre-registered out-of-time holdout.

Calibrated T20 win probability and score projection across five leagues, trained on 5,889 real matches of ball-by-ball data. FastAPI + scikit-learn.