Bank Marketing Machine Learning Classification

In this project logistic regression, random forest and support vector machine models are compared for predicting whether a customer will subsribe to a financial product in response to a direct marketing campaign.

A Comparison of Predictive Intervals for Distribution-Free Regression

This school project is based on the paper “Distribution-Free Predictive Inference for Regression” by Lei et al 2017. The project compares the performance of classical linear prediction intervals to three types of conformal prediction intervals in a high dimensional regression setting and over many types of regression estimators such as classical linear regression, the LASSO, the elastic net, and random forests.

*Please view projects on github for detailed discriptions and R code.