Idiosyncrasies and challenges of data driven learning in electronic trading

TL;DR

This paper discusses the unique challenges and specific considerations of applying neural information processing and machine learning techniques to electronic trading in quantitative finance.

Contribution

It highlights the peculiarities of data-driven learning in electronic trading and presents approaches to address fundamental challenges in the field.

Findings

Identification of key idiosyncrasies in neural processing for finance

Proposed approaches to overcome fundamental challenges

Insights into the application of machine learning in electronic trading

Abstract

We outline the idiosyncrasies of neural information processing and machine learning in quantitative finance. We also present some of the approaches we take towards solving the fundamental challenges we face.