Journal of Investment Strategies

Welcome to the second issue of the eleventh volume of The Journal of Investment Strategies, which contains three research papers.

In our first paper, “Exploring the equity–bond relationship in a low-rate environment with unsupervised learning”, Lucas Baynes and Giulio Renzi-Ricci provide an alternative approach to analyzing the equity–bond relationship in a low interest rate environment by using k-means clustering to identify the patterns in this relationship. According to Baynes and Renzi-Ricci, investors have become concerned about the low-interest-rate environment and its impact on the role that bonds can play in a multi-asset portfolio. In order to analyze the equity hedging property of government bonds, they apply k-means clustering – a simple yet powerful machine learning technique – to periods with low interest rates. Their findings suggest that government bonds in an equity–bond portfolio have historically acted as intended, typically with positive bond performance in equity-down scenarios. Although there are some periods in which both equities and bonds fall, these can be viewed as ordinary elements of market volatility and thus distinct from the typical outcomes that can be considered as recurrent market states. The results of this alternative approach complement the existing literature by providing further evidence of the added value that bonds bring to a strategic multi-asset portfolio.

In the issue’s second paper, “Creating factor clusters in the alternative Undertakings for Collective Investment in Transferable Securities (UCITS) universe”, Pierre Trecourt, Florian Peres and Sameer Singh examine the universe of the largest alternative UCITS funds in order to classify them by risk profile, extract the benchmark for each cluster, and present a multi-asset decomposition framework for their variance and performance. They apply a factor-based approach to split the universe into clusters with similar risk exposures. Each group’s risk and performance drivers are then analyzed, to give the greatest level of transparency and granularity into their behavior. This study provides a detailed analysis of the risk profiles of different clusters of funds. The cluster analysis provides some insights into the behavior of each cluster of funds. The use of factor exposures as features for clustering seems to be an interesting way of separating funds into groups with heterogeneous risk profiles. The empirical findings support such feature selection.

In “A novel derivation and interpretation of the Kelly criterion”, the third and final paper in this issue, Andreas Kull discusses multiperiod investment processes under parameter uncertainty and looks at criteria to maximize exponential growth. By applying an information-theoretical argument to a Bernoulli process, Kull finds the least biased investment strategy that is consistent with an expected exponential growth rate. This strategy is found to be directly linked to the Kelly strategy, thus providing a novel derivation and interpretation of the Kelly criterion. The paper provides a thorough literature review, from Shannon information theory through to the Kelly criterion and its use by practitioners such as Ed Thorp. Kull artfully simplifies the concept, and the way it is laid out is informative. The graphics are also illuminating and helpful in understanding his interpretation of the Kelly criterion. The two directions suggested by the author for future research are also worthy of consideration.

On behalf of the editorial board, we hope you have been doing well throughout the Covid-19 pandemic.We would like to thank you, our readers, for your continued support and keen interest in our journal. We look forward to sharing with you the growing list of practical papers on a wide variety of topics on modern investment strategies that we continue to receive from both academics and practitioners.

You need to sign in to use this feature. If you don’t have a Risk.net account, please register for a trial.

Sign in
You are currently on corporate access.

To use this feature you will need an individual account. If you have one already please sign in.

Sign in.

Alternatively you can request an individual account here: