GitPlanet

Cheap and reliable Node.js hosting starts at $3/month, and $1/month static HTML hosting

Created with love in Canada, visit hostnodejs.com today

Feel like to post an Ad? Learn Details
All Projects → melissa135 → mlp_stock

melissa135 / mlp_stock

Licence: other
Stock price prediction using ensemble MLP in PyTorch.

Programming Languages

python
139335 projects - #7 most used programming language

Labels

pytorchstockstock-price-predictionmlpmlp-regressor

Projects that are alternatives of or similar to mlp stock

Personae
📈 Personae is a repo of implements and environment of Deep Reinforcement Learning & Supervised Learning for Quantitative Trading.
Stars: ✭ 1,140 (+4460%)
Mutual labels:  stock, stock-price-prediction
stocktwits-sentiment
Stocktwits market sentiment analysis in Python with Keras and TensorFlow.
Stars: ✭ 23 (-8%)
Mutual labels:  stock, stock-price-prediction
Gekko Strategies
Strategies to Gekko trading bot with backtests results and some useful tools.
Stars: ✭ 1,022 (+3988%)
Mutual labels:  stock, stock-price-prediction
Chase
Automatic trading bot (WIP)
Stars: ✭ 73 (+192%)
Mutual labels:  stock, stock-price-prediction
funcat
Using very simple code to compute indicator of stock\crytocurrency. For example, MA(C, 5) means average closed-price for last 5 days.
Stars: ✭ 19 (-24%)
Mutual labels:  stock, stock-price-prediction
Beibo
🤖 Predict the stock market with AI 用AI预测股票市场
Stars: ✭ 46 (+84%)
Mutual labels:  stock, stock-price-prediction
Paper-Implementation-DSTP-RNN-For-Stock-Prediction-Based-On-DA-RNN
基於DA-RNN之DSTP-RNN論文試做(Ver1.0)
Stars: ✭ 62 (+148%)
Mutual labels:  stock, stock-price-prediction
Steward
A stock portfolio manager that provides neural net based short-term predictions for stocks and natural language processing based analysis on community sentiments.
Stars: ✭ 25 (+0%)
Mutual labels:  stock, stock-price-prediction
Deep-Learning-Models
Deep Learning Models implemented in python.
Stars: ✭ 17 (-32%)
Mutual labels:  mlp
FinanceCenter
Fetching Financial Data （US/China）
Stars: ✭ 26 (+4%)
Mutual labels:  stock
stock-market-scraper
Scraps historical stock market data from Yahoo Finance (https://finance.yahoo.com/)
Stars: ✭ 110 (+340%)
Mutual labels:  stock
StockBar
A menu bar app to track stock prices, currency exchange rates, and cryptocurrency prices.
Stars: ✭ 17 (-32%)
Mutual labels:  stock
RoboBull
A HackRU winner project. a user-friendly web-interface robo-adviser for novice traders that want to focus on day and short term trading. Project is using candlestick and moving average algorithms to predict suggestions (buy, sell, hold) for users. Product is also notifying users via SMS when the suggestion is changed; users are able to subscribe…
Stars: ✭ 12 (-52%)
Mutual labels:  stock
akshare
AKShare is an elegant and simple financial data interface library for Python, built for human beings! 开源财经数据接口库
Stars: ✭ 5,155 (+20520%)
Mutual labels:  stock
Stock-Analyser
📈 Stocks technical analysis code collection and Stocks data platform.
Stars: ✭ 30 (+20%)
Mutual labels:  stock
degiro-trading-tracker
Simplified tracking of your investments
Stars: ✭ 16 (-36%)
Mutual labels:  stock
stocklist
Stock data collection and analysis
Stars: ✭ 27 (+8%)
Mutual labels:  stock
nordnet
Uonfficial wrapper for financial data api from the Scandinavian broker Nordnet
Stars: ✭ 13 (-48%)
Mutual labels:  stock
d3-kagi
An open source javascript library to render beautiful Kagi charts using D3.js and pure Javascript
Stars: ✭ 26 (+4%)
Mutual labels:  stock
sensor.avanza stock
Custom component to get stock data from Avanza for Home Assistant
Stars: ✭ 30 (+20%)
Mutual labels:  stock
View All Similar Projects ➔

mlp_stock

Stock price prediction using ensemble MLP in PyTorch.

Predict the index changes by the fluctuation of index and volume in the last 5 days.
Train data is the daily CISSM (Compositional Index of Shenzhen Stock Market) from 2005/01 to 2015/06, the test data is from 2015/07 to 2017/05.

Requirements

  • Pytorch
  • Numpy
  • Pandas
  • Matplotlib

Usage

  1. Run train_net.py to train a group of MLPs with sz_train.csv, saved in /MLPs.
  2. Run test_net.py to predict stock market trend (in sz_test.csv) using ensemble MLP.

Result

The train error rate (black) and test error rate (red) of a single MLP, changing with epoches.

The red line is asset sequence if we buy/sell CISSM-ETF according to our ensemble MLP, comparing with CISSM (black).

Tips

  • Train samples are limited, using drop-out and early-stop to prevent overfitting.
  • Simulated trading using this strategy, see https://xueqiu.com/P/ZH931230 .
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].