One of the most common misconceptions about reinforcement learning (RL) applications is that, once you deploy them, they continue to learn. And, usually, I'm left having to explain this. As part of my explanations, I like to show where it is being used and where not.

I've done a little bit of research on the topic, but the descriptions seem fairly academic, and I'm left with the opinion that reinforcement learning is not really suitable for financial services in regulated markets.

Am I wrong? If so, I would like to know where RL is being used? Also, in those cases, are these RL algorithms adapting to new data over time? How do you ensure they are not picking up on data points or otherwise making decisions that are considered to be unacceptable?

  • 1
    $\begingroup$ Have a look at Wealth Wizards; I believe they are using ML for financial advice. wealthwizards.com -- Disclaimer: I know a few people who work/used to work there, but have nothing to do with the company myself. $\endgroup$ Feb 14 '19 at 8:49
  • $\begingroup$ My opinion (heavily based on personal experiences and anecdotes) is that RL is not used that much in real production environment. I've heard that some bigger tech companies used it successfully but they won't post their methods and results for obvious reasons. And even then, I'm quite skeptical whether they use 100% RL in their systems. $\endgroup$
    – Hai Nguyen
    Feb 19 '20 at 9:14

I know the new bot in JP Morgan uses reinforcement learning:

Machine Learning in FX

There a lot of studies of Reinforcement learning can apply in crypto currency trading. Here is one of many examples:

A Deep Reinforcement Learning Framework for the Financial Portfolio Management Problem


Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Not the answer you're looking for? Browse other questions tagged or ask your own question.