# lilianweng/stock-rnn

Predict stock market prices using RNN model with multilayer LSTM cells + optional multi-stock embeddings.

Repository: https://github.com/lilianweng/stock-rnn
Canonical: https://ross.abutalabs.com/products/stock-rnn
Homepage: https://lilianweng.github.io/lil-log
Language: Python
License Family: other
Topics: lstm, rnn-tensorflow, stock-price-prediction, embeddings
Last push: 2022-07-28T06:36:59+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": 3340, "days_push": 1497, "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 1991, forks 673 (observed 2026-08-28T04:06:03.138345+00:00)

## What it is
A tutorial repository demonstrating how to build and train an RNN with multilayer LSTM cells in TensorFlow to predict stock market prices, including optional multi-stock embeddings. It accompanies a two-part blog post and is intended as a learning reference rather than a production prediction system.

## Use cases
- learn how to build an LSTM model in TensorFlow
- predict stock prices with an RNN
- understand multi-stock embeddings for time series
- follow a tutorial on training RNNs on financial data
- get a starting point for stock prediction experiments

## When to choose
- you want a hands-on tutorial for LSTM/RNN in TensorFlow
- you need reference code for time-series prediction with embeddings
- you are learning deep learning on financial data

## When to avoid
- you need a production-grade stock prediction system
- you require modern TensorFlow 2.x or maintained code
- you need accurate, reliable financial forecasts

## Facets
- artifact type: learning-resource
- maturity: abandoned
- function: machine-learning, deep-learning
- domain: machine-learning, fintech, tutorials
- platform: python
- tags: lstm, rnn, tensorflow, stock-price-prediction, time-series, embeddings, educational

## Member repositories
- lilianweng/stock-rnn (main) score 32

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:06:03.138345+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 2026-08-30T03:02:42.567636+00:00, confidence not recorded.
  - readme: https://github.com/lilianweng/stock-rnn (fetched 2026-08-28T04:06:03.138345+00:00, sha cc5c2b3cd828)
  - homepage: https://lilianweng.github.io/lil-log (fetched 2026-08-29T10:42:29.268543+00:00, sha 4ea544322f20)
- Data as of 2026-08-30T08:39:29.467469+00:00.