Inspiration : I always loved programming but was never able to excel in it and build cool applications. This is my first real hackathon and I was able to find people who assisted me into excelling in one of my passions.
What it does: My Tree Decision Model takes past statistics of nba players (ex, points per game, blocks per game) and based on that, decides if the player is a guard, forward, or center.
How I built it: I used python 3.7, Jupyter Notebook and many libraries (ex. NumPy, Pandas, Scikit) via Anaconda. I also used many data frames to represent the statistics.
Challenges I ran into : I ran into many errors, sometimes syntax or logic, and problems with installing libraries came by too often.
Accomplishments that I'm proud of: I'm proud of myself for pushing past the struggles of understanding how to use different libraries and create something that could potentially be part of the future.
What I learned: I learned much more about python, I learned about many different python libraries and how to use them to create ML models and most of all, I learned that fruit is truly sweet when hard work is put in.
What's next for NBA Position Predicting Decision Tree Model: The next step is growing it to accept all the stats and to predict more than just the player's positions with it. This model has the potential of being a machine psychic.
Log in or sign up for Devpost to join the conversation.