All Projects → AkatsukiYamisora → stock-prediction-with-DL

AkatsukiYamisora / stock-prediction-with-DL

Licence: GPL-3.0 license
深度学习与股票分析预测

Programming Languages

python
139335 projects - #7 most used programming language

Projects that are alternatives of or similar to stock-prediction-with-DL

Bulbea
🐗 🐻 Deep Learning based Python Library for Stock Market Prediction and Modelling
Stars: ✭ 1,585 (+12092.31%)
Mutual labels:  stock-market, stock-prediction
TradeTheEvent
Implementation of "Trade the Event: Corporate Events Detection for News-Based Event-Driven Trading." In Findings of ACL2021
Stars: ✭ 64 (+392.31%)
Mutual labels:  stock-market, stock-prediction
stockbot
Alpaca algo stock trading bot
Stars: ✭ 105 (+707.69%)
Mutual labels:  stock-market, stock-prediction
image segmentation dl
🍞 基于深度学习方法的图像分割(含语义分割、实例分割、全景分割)。
Stars: ✭ 76 (+484.62%)
Mutual labels:  deeplearning
Printed-Chinese-Character-OCR
This is a Chinese Character ocr system based on Deep learning (VGG like CNN neural net work),this rep include trainning set generating,image preprocesing,NN model optimizing based on Keras high level NN framwork
Stars: ✭ 21 (+61.54%)
Mutual labels:  deeplearning
financial-asset-comparison-tool
R Shiny app to compare the relative performance of cryptos and equities.
Stars: ✭ 97 (+646.15%)
Mutual labels:  stock-market
ChartTheStockMarket
🔥 📈 💸 Chart the Stock Market - FCC Challenge
Stars: ✭ 39 (+200%)
Mutual labels:  stock-market
Kapsul-Aglari-ile-Isaret-Dili-Tanima
Recognition of Sign Language using Capsule Networks
Stars: ✭ 42 (+223.08%)
Mutual labels:  deeplearning
Articles-Bookmarked
No description or website provided.
Stars: ✭ 30 (+130.77%)
Mutual labels:  deeplearning
Machine-learning
This repository will contain all the stuffs required for beginners in ML and DL do follow and star this repo for regular updates
Stars: ✭ 27 (+107.69%)
Mutual labels:  prediction-model
lightweight-temporal-attention-pytorch
A PyTorch implementation of the Light Temporal Attention Encoder (L-TAE) for satellite image time series. classification
Stars: ✭ 43 (+230.77%)
Mutual labels:  deeplearning
vlainic.github.io
My GitHub blog: things you might be interested, and probably not...
Stars: ✭ 26 (+100%)
Mutual labels:  prediction-model
rembg-greenscreen
Rembg Video Virtual Green Screen Edition
Stars: ✭ 210 (+1515.38%)
Mutual labels:  deeplearning
turbofan failure
Aircraft engine failure prediction model
Stars: ✭ 23 (+76.92%)
Mutual labels:  prediction-model
RFDA-PyTorch
Official Code for 'Recursive Fusion and Deformable Spatiotemporal Attention for Video Compression Artifact Reduction' - ACM Multimedia2021 (ACMMM2021) Accepted Paper Task: Video Quality Enhancement / Video Compression Artifact Reduction
Stars: ✭ 44 (+238.46%)
Mutual labels:  deeplearning
qtrn
⚠️ Deprecated, see https://github.com/piquette/qtrn ⚠️
Stars: ✭ 20 (+53.85%)
Mutual labels:  stock-market
fastapi-template
Completely Scalable FastAPI based template for Machine Learning, Deep Learning and any other software project which wants to use Fast API as an API framework.
Stars: ✭ 156 (+1100%)
Mutual labels:  deeplearning
TFDeepSurv
COX Proportional risk model and survival analysis implemented by tensorflow.
Stars: ✭ 75 (+476.92%)
Mutual labels:  deeplearning
TradingView-Machine-Learning-GUI
Let Python optimize the best stop loss and take profits for your TradingView strategy.
Stars: ✭ 396 (+2946.15%)
Mutual labels:  stock-market
alpha-vantage-cookbook
JavaScript examples to help you with accessing market data from https://www.alphavantage.co/
Stars: ✭ 97 (+646.15%)
Mutual labels:  stock-market

stock-prediction-with-DL/深度学习与股票分析预测

GitHub Python Version Pytorch Version GitHub watchers GitHub Repo stars

目前新增了100多个技术指标,优化了一部分代码,正在做图神经网络部分内容,预计做一个小论文,等论文见刊再更新仓库^-^

data_downloader.py

通过baostock下载上证50,沪深300,中证500的日线数据

backtest.py

回测模块,根据调仓周期,通过模型选股,按开盘价买入卖出(暂定),计算收益,与指数比较并绘图

当前回测结果:

result

strategy.py

按价值因子(选择账面市值比BM)进行选股(效果差,由于BM在大市值公司的效果不佳)

用CNN预测模型进行选股

用动量因子(MF)进行选股

用换手率因子(TR)进行选股(思路参考自Liu et al.(2019) Size and value in China, 修改了数据选取)

用LSTM与reluRNN预测模型进行选股

用GRU与tanhRNN预测模型进行选股(效果不佳已放弃)

用ResNet18,34,50预测模型进行选股

用DenseNet预测模型进行选股

用综合几种网络预测结果的集成学习策略进行选股

其余策略待更新

prediction.py

使用CNN对股票数据进行预测

使用LSTM与reluRNN对股票数据进行预测(GRU与tanhRNN由于效果不佳放弃)

使用ResNet18,34,50对股票数据进行预测(101与152由于效果不佳放弃)

使用DenseNet对股票数据进行预测

当前预测结果

sh.600000,浦发银行

1

sh.600004,白云机场

2

sh.600009,上海机场

3

sh.600010,包钢股份

4

sh.600011,华能国际

5

tushare_apikey.txt

本地保存tushare pro的apikey

/data/hs300_stocks.csv

存放指数股票列表数据

/data/stocks/sh.000300.csv

存放指数日线数据

/data/stocks/*.csv

存放回测个股日线数据

/data/train_data/*.csv

存放训练集个股日线数据

/data/*.pkl

存放训练集数据

/data/*.pt

存放训练完成的模型数据

result.jpg

回测结果展示图片

*_predict.jpg

单只股票预测结果展示图片

Note that the project description data, including the texts, logos, images, and/or trademarks, for each open source project belongs to its rightful owner. If you wish to add or remove any projects, please contact us at [email protected].