Learning to Trade with Reinforcement Learning

Himanshu Singh (~himanshu61)




Financial data is difficult. It is sensitive to many unknown factors. So we need a good strategy for trading with deep learning. That's where reinforcement leaning comes in. It is quite similar to training agents for multiplayer games such as DotA, and many of the same research problems carry over. By the end of the talk, you will learn:-

  • What trading is?
  • Why it's hard?
  • How Can Deep Learning solve the trading problem?
  • Why is reinforcement learning an effective solution?


  • Willingness to learn
  • Basic python

Content URLs:

Any related material will be shared soon

Speaker Info:

I have always been amazed by computers and how much you can do with soo little. Curiosity lead to passion. Passion lead me to work on some amazing things. AI is the buzzword around and I have been working on AI for quite some time and it's been a really great journey, challenging but rewarding. Recently, I started working with some startups. Currently, I'm working for a Silicon Valley startup, who has been working on making serious predictions on small data. I have also been interested in Fintech data. I started with simple fraud detection models and now I'm working on solving the trading problem with reinforcement learning.

Speaker Links:

Connect on Twitter

Id: 793
Section: Data science
Type: Talks
Target Audience: Intermediate
Last Updated: