by GCBC Ventures | Nov 4, 2019 | Baseball, Machine Learning
Previous articles in this series: Plate Discipline for Hitters – Data Exploration Plate Discipline for Hitters – Scikit-learn and XGBoost Models Plate Discipline for Hitters – Ensemble of Neural Networks XGBoost New Data, Model, Code Ensembling Results 1. XGBoost We...
by GCBC Ventures | Oct 23, 2019 | Baseball, Machine Learning
Introduction Data Scaling Hyperparameter Search Multilayer Perceptron Main Code Results 1. Introduction Continuing our series of articles exploring the prediction of BB% and K% from plate discipline values, we use the Keras library to construct neural networks. We...
by GCBC Ventures | Oct 6, 2019 | Baseball, Machine Learning
Introduction Load Data Build Pipelines Test Results Analyze 2019 Data 1. Introduction In this article, we will use various preprocessors and machine learning algorithms from scikit-learn, along with the scikit-learn wrapper for XGBoost. We determine which...
by GCBC Ventures | Sep 6, 2019 | Baseball, Machine Learning
Definitions Download and Clean Data Statistics Feature Importances 1. Definitions The goal of this series of articles is to explore various aspects of plate discipline for hitters, including building multiple machine learning models to predict strikeout and walk rates...