Many practitioners are quite disappointed with ML applications to financial markets. We can see hundreds of articles describing how to build a neural network predicting the price of bitcoin for the next day, however very few researchers end-up with positive results. The key reason for bad out-of-sample results is the naive application of traditional algorithms predicting complex financial time series. Computer vision and NLP researchers use domain-specific algorithms and techniques so why would financial machine learning be an exception?
On this webinar, Oleksandr will tell what are the techniques and algorithms used in financial ML and what are the key mistakes made by experienced researchers trying to predict financial markets.
Oleksandr Proskurin, Founder, CIO, Machine Factor Technologies
Oleksandr Proskurin is a Founder and CIO of Machine Factor Technologies, company consulting asset managers in financial machine learning applications, and algorithmic trading. His previous experience includes more than 4 years working in the hedge fund industry, researching and implementing volatility and commodity trading strategies using futures, options, and leveraged ETFs. As a part of Machine Factor Technologies team, Oleksandr develops various algorithmic trading strategies using ML and AI algorithms. Oleksandr is also the co-author of Mlfinlab package — an open-source library that implements various machine learning tools used in investment strategies research. Right now Mlfinlab is Github’s top 7 algorithmic trading packages.