# borisbanushev/stockpredictionai

In this noteboook I will create a complete process for predicting stock price movements. Follow along and we will achieve some pretty good results. For that purpose we will use a Generative Adversarial Network (GAN) with LSTM, a type of Recurrent Neural Network, as generator, and a Convolutional Neural Network, CNN, as a discriminator. We use LSTM for the obvious reason that we are trying to predict time series data. Why we use GAN and specifically CNN as a discriminator? That is a good question: there are special sections on that later.

Repository: https://github.com/borisbanushev/stockpredictionai
Canonical: https://ross.abutalabs.com/products/stockpredictionai
Language: JavaScript
License Family: other
Last push: 2025-08-19T04:04:58+00:00

## Health v2 (maintenance only)
Score: 49/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 37, release rhythm 35, longevity 100
- inputs: {"age_days": 2793, "days_push": 379, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases, no_license
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 5593, forks 1884 (observed 2026-08-28T04:09:22.706610+00:00)

## What it is
An educational Jupyter notebook demonstrating a complete pipeline for predicting stock price movements using a GAN with an LSTM generator and CNN discriminator, plus BERT sentiment analysis, Fourier transforms, autoencoders, and ARIMA. It is a tutorial/learning resource rather than production software.

## Use cases
- learn how to predict stock prices with deep learning
- understand GANs applied to time series forecasting
- see how BERT sentiment analysis feeds into trading models
- study hyperparameter tuning of GANs with Bayesian optimization and reinforcement learning
- example of combining technical indicators with NLP for market prediction

## When to choose
- you want a step-by-step educational walkthrough of AI-based stock prediction
- you want to learn how GANs, LSTMs, and BERT can be combined in one pipeline
- you are studying feature engineering for financial time series

## When to avoid
- you need a production-ready trading system or API
- you want maintained, licensed, reusable software
- you expect guaranteed accurate stock predictions

## Facets
- artifact type: learning-resource
- maturity: maintenance
- function: machine-learning, deep-learning, data-science, nlp, trading
- domain: machine-learning, deep-learning, fintech, data-science, tutorials
- platform: python
- tags: gan, lstm, stock-prediction, notebook, bert, reinforcement-learning, time-series, mxnet, gpu

## Member repositories
- borisbanushev/stockpredictionai (main) score 49

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:09:22.706610+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 2026-08-29T17:55:29.828107+00:00, confidence not recorded.
  - readme: https://github.com/borisbanushev/stockpredictionai (fetched 2026-08-28T04:09:22.706610+00:00, sha 82523beae1e8)
- Data as of 2026-08-30T08:39:29.467469+00:00.