# VivekPa/AIAlpha

Use unsupervised and supervised learning to predict stocks

Repository: https://github.com/VivekPa/AIAlpha
Canonical: https://ross.abutalabs.com/products/aialpha
Language: Python
License: MIT
License Family: permissive
Topics: artificial-intelligence, artificial-neural-networks, lstm, machine-learning, stock-price-prediction, algorithmic-trading, quantitative-finance, autoencoder, wavelet-transform, yahoo-finance-api, python, trading-strategies
Last push: 2020-06-18T05:37:24+00:00

## Health v2 (maintenance only)
Score: 32/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 0, release rhythm 35, longevity 100
- inputs: {"age_days": 2887, "days_push": 2267, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1955, forks 449 (observed 2026-08-28T04:05:58.954621+00:00)

## What it is
An educational Python project demonstrating a stacked neural network architecture (autoencoder plus LSTM and Random Forest models) for predicting stock returns from tick data. It walks through bar sampling, feature engineering, dimensionality reduction, and model training following the approach of Advances in Financial Machine Learning.

## Use cases
- predict stock prices with machine learning
- learn to build LSTM models for financial data
- use autoencoders for feature reduction in trading
- build algorithmic trading strategies with neural networks
- apply Marcos Lopez de Prado techniques in Python
- classify stock price movement direction with random forest

## When to choose
- you want to learn how stacked neural networks are applied to stock prediction
- you need a reference implementation of bar sampling, feature engineering, and autoencoders for financial data
- you are studying quantitative finance and machine learning concepts

## When to avoid
- you need production-ready live trading software
- you expect maintained code with recent updates or support
- you need the original tick dataset, which is no longer available

## Facets
- artifact type: learning-resource
- maturity: abandoned
- function: machine-learning, deep-learning, data-science, trading
- domain: fintech, machine-learning, artificial-intelligence
- platform: python
- tags: stock-price-prediction, lstm, autoencoder, algorithmic-trading, quantitative-finance, educational-project

## Member repositories
- VivekPa/AIAlpha (main) score 32

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:05:58.954621+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T03:06:26.103313+00:00, confidence not recorded.
  - readme: https://github.com/VivekPa/AIAlpha (fetched 2026-08-28T04:05:58.954621+00:00, sha 2fb8230f8242)
- Data as of 2026-08-30T08:39:29.467469+00:00.