RQYM / portfolio-optimization

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

Portfolio Optimization using Reinforcement Learning

Experimenting with RL for building optimal portfolio of 3 stocks and comparing it with portfolio theory based Markowitz' approach

Pls checkout the medium article for a quick overview.

To train RL model:

python train.py

To download data: https://www.dropbox.com/s/jy1bid7tcg0vv4n/cleaned_preprocessed.csv?dl=0 Take a look at pre_process.py if you want to get an idea on how this file was cleaned and compiled.

Problem Statement

I will be formulating this as a portfolio optimization problem :  Given histories of 3 different stocks, how would we allocate a fixed amount of money between these stocks every day so that maximize the likelihood of returns. 

The objective is to develop of policy (strategy) for building a portfolio. The portfolio is essentially an allocation of available resources across various stocks. The policy then needs to restructure the portfolio over time as new information becomes available.

Pic of Model

RL agent training

Pic of training

Results

Pic of results

About


Languages

Language:Python 100.0%