• There are many devices that record key fitness performance metrics making it possible to collect a large amount of data about personal activity. Usually the goal is to measure regularly so to improve fitness, health and find new patterns in behaviour.
• One thing that people regularly do is quantify how much of a particular activity they do, but they rarely quantify how well they do it. This project will use data from accelerometers on the belt, forearm, arm, and dumbbell of 6 participants. They were asked to perform barbell lifts correctly and incorrectly in 5 different ways. The goal of this project is to predict, using Trees, Boosting and Random Forest, the manner in which they did the exercises.

Predict Exercise Performance

Link to GitHub Depository