This website use cookies and similar technologies to improve the site and to provide customised content and advertising. By using this site, you agree to this use. To learn more, including how to change your cookie settings, please view our Cookie Policy
Pocketmags Digital Magazines
Pocketmags Digital Magazines
   You are currently viewing the United Kingdom version of the site.
Would you like to switch to your local site?
Digital Subscriptions > The Hedge Fund Journal > Issue 134 – Aug 2018 > Machine Learning

Machine Learning


For visual risk analysis and hedge fund selection

One of the main principles to build portfolios of financial assets is to achieve stable long-term performance and avoid large drawdowns. This article describes how a method of Machine Learning, Kohonen’s Self-Organising Maps, can be applied to visualise risk and to build robust portfolios of hedge fund managers. Essentially, it documents a feasibility study that was conducted to gauge whether Machine Learning can add any value to the investment process of an investor in hedge funds.

Robust portfolios can be created by avoiding concentrations and by diversifying across hedge fund managers and hedge fund styles: a portfolio comprising only, for example, long/short equity managers will suffer larger drawdowns when equity markets fall than a portfolio that invests partly also, for example, in credit or macro strategies. How can we avoid concentrations in the portfolio? A statistical tool for identifying similarities in data are the Self- Organising Maps (SOM). SOM were developed in the 1980s by Teuvo Kohonen (Kohonen, 1982). They project objects onto a 2-dimensional map with similar objects being placed closely together. SOM can be used to identify similarities in risk behaviour of hedge funds: managers with similar risk behaviour and hence similar investment strategies appear on near-by units, i.e., near-by areas on the map. A potentially important feature of SOM is that they are able to exploit non-linearity in the data, as hedge funds deploy trading strategies and instruments that lead to non-linear return profiles. SOM can be interpreted by visual inspection and can process incomplete and noisy data. The tools required for Machine Learning have become commoditised, as several toolboxes are available free on the internet. All network training and calculations discussed here were conducted with the R package “kohonen”. Fig.1 shows a SOM with 5 x 5 = 25 units which was created with hedge fund return data from Oct 2009 to Sep 2013 (48 months). We call this 4-year period vintage year 2014. Vintage year 2008 would comprise the 48 monthly returns from Oct 2003 to Sep 2007, etc.

Purchase options below
Find the complete article and many more in this issue of The Hedge Fund Journal - Issue 134 – Aug 2018
If you own the issue, Login to read the full article now.
Single Issue - Issue 134 – Aug 2018
Or 11999 points
6 Month Digital Subscription
Only £ 120.00 per issue
Or 59999 points

View Issues

About The Hedge Fund Journal

Informing the Hedge Fund Community. With access to some of the industry’s biggest names and an astute and talented group of writers and contributors, The Hedge Fund Journal has established itself as a trusted source of information on the hedge fund industry.