
Igor Halperin – 08/12/22
Quantcast – a Risk.net Cutting Edge podcast
Using Reinforcement Learning to Model Stock Market Dynamics
"In what sense the models are wrong uh so this model start with the famous geometric Brownian motion model by samosin and his logic was pretty simple," he says. "The bad thing is that you know the model itself doesn't give you any indication where it's from like you see like like Newtonian mechanics right?" He continues: "If you have more general model which produces non-linear drift due to interactions and imperfections in the market then you can look back at the some else model and say oh this is what was missing there."
00:00
Transcript
Play full episode
Remember Everything You Learn from Podcasts
Save insights instantly, chat with episodes, and build lasting knowledge - all powered by AI.