ScottfreeLLC/AlphaPy

Python AutoML for Trading Systems and Sports Betting

What it solves

AlphaPy is a machine learning framework designed to simplify the process of building predictive models for speculators and data scientists, specifically targeting financial markets and sporting events.

How it works

It leverages Python libraries like scikit-learn, pandas, Keras, xgboost, LightGBM, and CatBoost to provide a structured pipeline for model training and evaluation. The framework includes specialized modules like MarketFlow for market analysis and trading system development, and SportFlow for predicting sporting events.

Who it’s for

Data scientists and speculators who want to apply machine learning to financial trading and sports betting.

Highlights

  • Support for multiple ML models including Keras, xgboost, LightGBM, and CatBoost.
  • Ability to generate blended or stacked ensembles.
  • Integrated tools for market analysis and portfolio analysis via pyfolio.
  • Specialized workflows for sports prediction (SportFlow) and financial markets (MarketFlow).

Related

  • Project
    allenai/Olmo-core

    A library of building blocks and training scripts for the OLMo family of large language models, supporting training, annealing, and high-throughput inference.

  • Project
    KEV0143/Comparative-analysis-of-hourly-load-forecasting-using-PatchTST-TFT-NHiTS-and-CatBoost

    A Python research project that compares four modern time‑series models (PatchTST, TFT, N‑HiTS, CatBoost) for hour‑by‑hour electricity‑load forecasting using real Russian utility data. Includes data preprocessing, training pipelines, statistical analysis, and visualisation, and is released under Apache 2.0.

  • Project
    brainflow-dev/brainflow

    A uniform SDK for obtaining, parsing, and analyzing data from biosensors such as EEG, EMG, and ECG, simplifying the development of neurointerfaces.

  • Project
    mlcommons/training

    A repository of reference (unoptimized) implementations for the MLPerf Training benchmark suite, covering vision, language, recommendation, and graph models. Each benchmark includes model code, Dockerfiles, dataset scripts, and a training‑run script that measures time to reach target quality. Intended for benchmark submissions, hardware evaluation, and learning, but not for real‑world performance.