An entry-level project of testing various machine learning models in particle identification

A little bit introduction about myself and this project: I am a university graduate major in mathematical physics and after graduation I joined a data science diploma program hopefully to start my professional career as a data scientist. This particle identification project was also my capstone project for that diploma program. During the job searching period, now I have more time to learn about data science and keep on refining my skills. I started to look back on this project I finished 2 months ago, and decided to write a story post as a milestone on the road of becoming a real data scientist :)

First, the source of the dataset is from the link as following: https://www.kaggle.com/lavanyashukla01/particle-identification

I was inspired by one of the blog posts (link as below): https://lavanya.ai/2019/05/31/searching-for-dark-matter/

In the post above, AdaBoost and Neural Network models were tested and already showed relatively good results. But for me, 2 months ago, as a beginner, I still wanted to see how other types of machine learning models performed on this enormous particle identification dataset. Although I knew that the some of the model’s results might be poor but I called my project ‘A Ninja Road of Modelling’ as an…