- 概要Abstract
针对期货交易数据(原数据为用户持仓交易,已转成常用K线数据),利用深度学习方法(seq2seq)进行预测,实验数据由“中农网”提供(卓尔ZHACK比赛数据)。 Prediction of futures(stock) by deep-learning methods, include ARIMA(baseline), lstm and seq2seq model. - 代码Code
arima.py -- ARIMA,BaseLine
lstm_keras.py -- lstm模型KERAS版本
lstm_keras.py -- lstm模型TensorFlow版本
seq2seq_tf.py -- seq2seq模型(即以序列预测序列)
result_output.py -- 预测与输出 - 数据Data
data -- 期货交易数据(文件较大,提供网盘下载,详见txt内) - 结果Result
The Mean Absolute Error is: 81.91800705907733 (Price is about 5000).
-
Notifications
You must be signed in to change notification settings - Fork 2
RilaShu/stock-price-prediction-deep-learning
Folders and files
Name | Name | Last commit message | Last commit date | |
---|---|---|---|---|
Repository files navigation
About
stock price prediction with lstm & seq2seq model
Topics
Resources
Stars
Watchers
Forks
Releases
No releases published
Packages 0
No packages published