New York City Car Crash Analysis

Background

In Summer of 2022 I took my first machine learning class as part of Master in Computer Science at NYU. We had to complete a project throughout the course to analyse a data set and see what conclusion we could garner from it.

There were three stages to this project: The Exploratory Data Analysis (EDA), Homework 1 where I utilised Machine Learning techniques on the data to train and test the data and lastly Homework 2 where I tried using methods to help refine my findings from Homework 1.

I settled on trying to find if there was any correlation between the given cause of the car crash and all other labels I deemed necessary. Below is my full project paper.

Conclusion

This class project gave me an great opportunity to learn how to utilise Machine Learning techniques to attain usable and helpful data. My overall conclusion was that there appears to be no clear correlation between type of crash and the other factors but more exploration of this data can definitely be done in future.