The document discusses analyzing running data from Strava to predict half marathon times and how runners can improve. It uses linear regression, ensemble methods, and random forests on 22 features from 10,000 runners to benchmark models. The best model was ensemble partial least squares regression with a validation R^2 of 0.72 and RMSE of 6.6 minutes. The most important predictor was average pace over the past month. The analysis aims to provide runners with insights on how to run faster half marathons.