HFA Icon

Deutsche Bank Dives Deep Into Machine Learning In Investing

HFA Padded
Mark Melin
Published on
Updated on
Sign up for our E-mail List and Get FREE Access to Exclusive Investment E-books and More!

As machine learning in finance has been harshly questioned of late, Deutsche Bank, noting the repeated discussions in the media, issues their own take in a 110-page report out September 30. The is that while machine learning can be “very relevant” in finance, “dangerous pitfalls” exist.

After defining machine learning – “machine learning is an empirical, algorithmic approach to the problems already tackled by Statistics” – the report explained the nuance. The more the topic is explained the more the strengths and weaknesses in adaptive trading and investment methods are clear.

db-algo-9-30-long-short-exposure

Supervised and unsupervised machine learning is not about human involvement

Understanding how an algorithmic approach in investing can, to various degrees, be dependent...

Login required to continue reading.

Setup a free account to get access to this article (no credit card required).

View Full Article
Already a member? Log in here
HFA Padded

Mark Melin is an alternative investment practitioner whose specialty is recognizing the impact of beta market environment on a technical trading strategy. A portfolio and industry consultant, wrote or edited three books including High Performance Managed Futures (Wiley 2010) and The Chicago Board of Trade’s Handbook of Futures and Options (McGraw-Hill 2008) and taught a course at Northwestern University's executive education program.