This document summarizes a project to classify handwritten digits from the MNIST dataset using a decision tree strategy. It discusses using decision trees to determine informative features and construct a classifier from 60,000 training examples and 10,000 test examples. The implementation loads data, trains on 21,000 items, tests on the remaining items, and displays predictions with 28x28 pixel images. Accuracy is improved further with a nearest neighbor final test, achieving 99.6% classification rate. Screenshots of the running code are provided in an attached folder.