Skip to content

Winner of OC Science Fair and invitee to prestigious CA State Science Fair - Reinforcement Learning applied to Python stock trading bots

Notifications You must be signed in to change notification settings

MT-GoCode/Reinforcement_Learning_Stock_Trading

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

7 Commits
 
 
 
 
 
 

Repository files navigation

Reinforcement Learning Agent to Choose Optimal Technical Trading Strategies For Stocks

Minh Trinh

Autonomous stock trading commonly uses trading bots - computer programs implementing specific trading strategies based on signals from stock price and volume movements. Which bot can maximize profits? For a particular stock, a certain bot may outperform others on one day, under a particular market condition, but underperform on other days -- there is no all-time winner. Alternating bots daily may yield optimal results. However, selecting the right bot each day isn’t a simple task.

I created an AI system to help retail traders with the bot selection process. For a given stock, it takes in a set of data representing daily stock market conditions and selects one optimal bot from a pool of different bots for each trading day. The bots selected by the AI System achieved a greater total profit than any individual bot over the same multi-day trading periods and a Sharpe Ratio above 1, satisfying my design goals.

See full description here: https://docs.google.com/presentation/d/1_MT5LVD_AWVZpLcKj-x-ZM3Eq0ZpgM0BJrWxmt5T1hE/edit#slide=id.p

About

Winner of OC Science Fair and invitee to prestigious CA State Science Fair - Reinforcement Learning applied to Python stock trading bots

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published