← all repositories

lilianweng/stock-rnn

A multilayer LSTM-based recurrent neural network for predicting stock market prices using TensorFlow.

2k stars Python Domain AppsML Frameworks
stock-rnn
Velocity · 7d
+0.6
★ / day
Trend
steady
star history

This repository implements a recurrent neural network with LSTM cells to forecast stock market prices. It supports optional multi-stock embeddings to learn shared representations across different securities, trains on historical S&P 500 data downloaded from Yahoo Finance, and is built entirely in TensorFlow.

heatdrop uses Google Analytics to see which pages get read — nothing else. Your call. How we handle data.