MachineLearning-BaseballPrediction-BlazorApp and MLDotNet-BaseballClassification
These are ecosystem siblings where the second project (ML.NET classifier training) provides the trained machine learning models that the first project (Blazor web app) consumes and deploys for real-time predictions.
About MachineLearning-BaseballPrediction-BlazorApp
bartczernicki/MachineLearning-BaseballPrediction-BlazorApp
Machine Learning over historical baseball data using latest Microsoft AI & Development technology stack (.Net Core & Blazor)
This application helps baseball analysts, sports journalists, or enthusiastic fans make data-driven decisions about player performance, specifically around Hall of Fame induction probabilities. It takes historical player statistics as input and provides predictions and 'what-if' analysis, leveraging machine learning to offer a quantitative edge over purely human judgment. The end result is a deeper understanding of player potential and more informed decision-making.
About MLDotNet-BaseballClassification
bartczernicki/MLDotNet-BaseballClassification
Machine Learning training job using historical baseball data & ML.NET to build a complete set of classifiers.
This project helps baseball analysts and enthusiasts predict future Hall of Fame outcomes for players. By analyzing historical MLB career statistics from 1876-2023, it determines if a batter will appear on the Hall of Fame ballot and whether they will ultimately be inducted. The output is a set of classification models that can be used to evaluate new player careers.
Scores updated daily from GitHub, PyPI, and npm data. How scores work