Machine Learning and Heart Disease Prediction

This website project was created for the final project for the University of Minnesota Data Analytics BootCamp our group is going through. This final project was designed to showcase our skills with machine learning and using that to work with the data.

The group is made up of Beryl Kaczmarczik, Farshad Esnaashari, Katherine Rootes, and Matt Pollari.

We ended up taking the Heart Disease data set from the University of California, Irvine machine learning repository. We chose this data set because it had categorical data that we could use to test on and it also had been cleaned up so that it had a much lower bar to entry to actually start doing machine learning projects on the data set.

They have also trimmed down the attributes from the 76 initially there to a smaller subset of 14 attributes they selected. With them already selecting 14 subset of attributes they have largely set the stage for us to start just working with it and not do much processing work.

What we decided to do with this data set and machine learning was to look at different models and methods for predicting and which way would work best for this data set at predicting heart disease. Click on the different models above to see how each of them performed and our analysis.