search

sachink2010 / AutomatedStockTrading-DeepQ-Learning

Every day, millions of traders around the world are trying to make money by trading stocks. These days, physical traders are also being replaced by automated trading robots. Algorithmic trading market has experienced significant growth rate and large number of firms are using it. I have tried to build a Deep Q-learning reinforcement agent model to do automated stock trading.
MIT License
257 stars 79 forks source link

Some questions #3

Closed SergioSV96 closed 5 years ago

SergioSV96 commented 5 years ago

Thanks for your work, I like your approach for trading stocks, could this be ported to trading cryptocurrencies instead?

What are your thoughts on this, are there any better approaches than DeepQLearning?

Thanks in advance!

sachink2010 commented 5 years ago

Thanks for your positive feedback. I am not a seasoned programmer, started to learn Machine Learning, so these postive comments gives extra motivation to do more :-)

Regarding your comment on possibility of using above approach for cryptocurrencies, yes it is indeed possible to do it. There are few problems I see:

  1. cryptocurrencies are quite new, so there is not as much data as normal stocks for robot to learn.
  2. Price volatility in crypto can be too high. Bitcoin shot up to $20,000 then fell to $1000, and now again around $10,000. So, it might not be easy for robot to decide when to buy/sell But, I like the idea, so may be it can be tested with atleast the important cryptos like Bitcoin, Ether, Litecoin etc. I would be hesitant to use it on smaller market cap cryptos.