VivekPa/AIAlpha
Use unsupervised and supervised learning to predict stocks
This project helps quantitative traders and financial engineers understand how to build a multi-layered machine learning model to predict stock price movements. It takes raw tick data, processes it into statistically robust bars, engineers features, and then uses a neural network (LSTM) or a Random Forest model to predict future stock returns or direction. The output is a prediction of stock movement or direction, designed for advanced practitioners in algorithmic trading.
1,907 stars. No commits in the last 6 months.
Use this if you are a quantitative trader or financial engineer looking to develop or enhance your understanding of applying advanced machine learning techniques, specifically stacked neural networks, to predict stock returns from tick data.
Not ideal if you are looking for a plug-and-play solution for live trading or if you do not have a strong background in machine learning and financial data analysis.
Stars
1,907
Forks
447
Language
Python
License
MIT
Category
Last pushed
Jun 18, 2020
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/VivekPa/AIAlpha"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Related frameworks
polakowo/vectorbt
⚡️ Lightning-fast backtesting engine to find your trading edge.
asavinov/intelligent-trading-bot
Intelligent Trading Bot: Automatically generating signals and trading based on machine learning...
Drakkar-Software/OctoBot-Script
Quant trading framework by OctoBot. Write, backtest & automate Python trading strategies like...
paperswithbacktest/pwb-toolbox
The toolbox for developing systematic trading strategies. It includes datasets and strategy...
ScottfreeLLC/AlphaPy
Python AutoML for Trading Systems and Sports Betting