Show HN: DeepShot – an open-source NBA predictor with ML, EWMA, and live UI

5 days ago 1

An advanced NBA game predictor powered by historical data from Basketball Reference, rolling statistics, and machine learning — built with NiceGUI for a seamless experience.

TL;DR • Key Features • Quickstart • Credits • License

DeepShot is a machine learning-based NBA game predictor using advanced rolling stats (like EWMA) and real historical performance. It helps forecast matchups with visual insights and a clean interactive GUI.

💡 Why DeepShot Stands Out

Uses Exponentially Weighted Moving Averages (EWMA) to capture recent form and momentum
Visually highlights the key statistical differences between teams
Clean, real-time NiceGUI-powered web interface
Works locally across platforms (Windows, macOS, Linux)
Based entirely on free and public data

Data-Driven Predictions – Powered by real NBA stats from Basketball Reference.
Real-Time Interface – Visualize upcoming matchups and model predictions with a sleek NiceGUI web frontend.
Weighted Stats Engine – Uses Exponentially Weighted Moving Averages (EWMA) to reflect recent performance trends.
Key Stat Highlighting – Automatically surfaces differences between teams to help you identify strengths and weaknesses fast.
Cross-Platform Support – Works smoothly on all major OSes.

git clone https://github.com/saccofrancesco/deepshot.git cd deepshot pip install -r requirements.txt # Train model by running the notebook # Open `model.ipynb` and run the cell to generate `deepshot.pkl` python main.py # Launches the NiceGUI web app