Machine Learning for Hedge Fund Selection. Issue 100 (20th March 2019)

• Record Type: Journal Article
• Authors: Huber, Claus
• Is Part Of: Wilmott. Volume 2019:Issue 100(2019)
• Page Start: 74
• Page End: 81
• Publication Date: 2019-03-20
• Subjects: machine learning -- self‐organizing maps -- Kohonen map -- robust portfolios -- hedge funds -- hedge fund selection; Finance -- Periodicals; Financial services industry -- Periodicals; 332
• DOI: 10.1002/wilm.10752
• Languages: English
• ISSNs: 1540-6962

Abstract

Abstract : This paper describes the application of Kohonen's self‐organizing maps (SOMs), a method of machine learning, to the problem of selecting hedge funds to achieve stable portfolio performance. SOMs can help to identify similarities in return structures of hedge fund managers and hence avoid concentrations in a portfolio. The core question is whether SOMs can add any value for manager selection. Two novel yet simple methods to select hedge funds based on the specific properties of SOMs are proposed that both target identifying unique investment strategies. To evaluate their performance relative to other, simpler benchmark methods of portfolio selection, a simulation study finds both SOM‐based methods proposed enhance risk/return profiles and drawdown patterns