Inspiration

Every year, millions of basketball fans from all over the world join the NBA Draft in the hope that their favorite team hits gold and earns the next big NBA star. People in the former offices of these NBA teams spend thousands of hours exploring and testing college and international talent trying to find players who can excel at pro level and contribute to the team. Following the growth of the field of data science, it makes sense to try and test talent over traditional methods

What it does

This project predicts their Points, Rebounds, Assist, Blocks, Steals and Fantasy points of a new set of NBA Rookies. It compares Rookies stats from 2000-2019.

How we built it

We did Exploratory Data Analysis on the dataset and we fitted various Machine Learning models like Linear Regression, Random Forest, Extra Trees, XGBoost.

Challenges we ran into

We scraped data from many sources. So, we expected to get a higher accuracy. This is because, many players will not keep up their standards when it comes to International level.

Accomplishments that we're proud of

Though the accuracy is quite less, the model predicted well for the top players like Ja Morant and Zoin Williams. We are proud that we are able to do a good analysis on the sports data and able to provide a good prediction rate for NBA Rookies. This also helps NBA scouts for better talent identification and selection.