Skip to content

Application of Machine Learning Algorithms to Intraday Stock Trading Based on Demand Zones

Notifications You must be signed in to change notification settings

alex01001/Machine-Learning-For-Stock-Trading

Repository files navigation

Machine Learning for Intraday Stock Trading

In this project, I research applicability of Machine Learning methods to intraday stock market trading. Specifically, I focus on evaluating so-called “Demand Zones” in terms of their potential profitability. I’ve built a system which tracks the S&P 500 stock data, detects the Demand Zones (let’s refer to this moment of time as T1), records the technical parameters, including the peak price (at time T2), and generates alerts when the price comes back to the demand zone (time T3).

At the time T3, a trader (or a trading algorithm) has to make a decision whether they should buy the stock. The purpose of my research is to analyze the performance of Machine Learning algorithms in terms of their ability to correctly predict the winning trades.

See the intraday stock trading alerts in action here: http://www.stocksbuyalerts.com/

This is my capstone project for Udacity's Machine Learning Engineer Nanodegree.

alt text

About

Application of Machine Learning Algorithms to Intraday Stock Trading Based on Demand Zones

Topics

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published