Outlined below is a brief summary of the research we carried out in 2019. Some of our research findings are publicly available on our website www.unigestion.com/insights. Others formed part of bespoke research that we undertook at the request of individual clients. Please get in touch if you would like to find out more about these projects, or to discuss your own research requirements.

Responding to Investors’ Need for More Sophisticated Strategies

Developing New Alternative Risk Premia

Alternative risk premia are a core component of our investment offering, both through our standalone Alternative Risk Premia fund and our multi-asset strategies. We constantly research new risk premia and refine existing ones in order to provide efficient, diversifying returns streams for our investors. Over the course of the past year, we refined our commodity carry strategy in order to make it less sensitive to seasonal spreads. We also developed a volatility risk premium, which goes beyond most common implementations that tend to focus solely on equity markets. Our strategy is designed harvest the premium across not only equity markets, but also bonds, commodities, and currency markets using options and futures. In the bonds space, we designed a strategy that aims to harvest a value premium based on mean-reversion of the yield curve structure in the main developed countries. Finally, a collaboration between our Equities and Cross Asset Solutions teams led to the development and implementation of an equity index value strategy, whose main goal is to identify undervalued and overvalued equity indices in developed markets, also taking advantage of well-known mean-reversion effects.

Private Equity Liquid Risk Premia

Interest in private equity investing continues at the same time as investors focus on the liquidity of their investments. To respond to these dual demands, we developed a methodology that aims to add value by providing proxy exposure to a proprietary portfolio of private companies using listed equities. The objective of this transversal research across investment teams is to capture a significant part of the performance premium of private equity over public equity, while limiting exposure to listed equity market risk. Our Equities, Private Equity and Cross Asset Solutions teams collaborated to achieve this by matching each private company with its nearest public equivalent and adjusting risk at the portfolio level. Our results show that we can capture a significant part of the private equity risk premium, including the bias toward small and mid-sized companies, the regional allocation, the industry sector choices and the company style choices.

Using an Optimal Hedging Portfolio to Improve Risk-adjusted Returns

We developed research on how equity derivatives can help investors to protect their equity allocations against market downturns without having to significantly increase their exposure to cash. Before entering into hedging strategies, the first step to reducing the risk in equity investments is to invest in a risk-efficient portfolio. The optimal hedging portfolio involves finding the best trade-off between cost and efficiency at each roll-over date, typically through a combination of index futures. Defining a strategic hedge ratio can reduce market timing risk when hedging downturns. Our research shows that using Nowcasters helps to navigate between a return and a risk objective by enabling dynamic adjustment of the hedge ratio.

A Dynamic Tail Hedging Solution

With equity markets defying the law of gravity, investors are increasingly looking for tail hedging solutions. To reduce the cost of a protective put strategy, we combine attractive long-term put options with a dynamic delta hedging. The residual level of delta is defined using our unified framework for dynamic allocation based on macro, sentiment and valuation indicators. The tail hedge strategy does not affect the strategic asset allocation, exhibits a long exposure to volatility, keeps gap risk hedging properties and dynamically reduces the equity exposure in case of an unexpected deterioration of the macroeconomic environment.

Macro Factor Mimicking Portfolios

The estimation of risk factors and their replication through mimicking portfolios are of critical importance for academics and practitioners in finance. In this paper, we propose a general optimisation framework to construct macro factor mimicking portfolios that encompasses existing portfolio mimicking approaches, such as two-pass cross-sectional regression models (Fama and MacBeth, 1973) and maximal correlation approaches (Huberman et al., 1987, and Lamont, 2001). We incorporate empirical estimation improvements through machine learning methodologies. We provide an application to the construction of tradable portfolios mimicking three global macro factors, namely growth, inflation surprises and financial stress indicators. We show how these macro mimicking factors can be used to improve the risk-return profile of a typical endowment multi-asset portfolio.

Publicly Disclosed Short Positions and Long-Short Equity Strategies

We published a paper entitled ‘Best Short’, which was presented at the European Finance Association meeting in August 2019 and featured in Institutional Investor magazine. The paper uses publicly disclosed short positions for European stock markets from 2012 to 2018 and uncovers that short positions for which hedge funds have high conviction outperform short positions with low conviction. A long-short strategy that replicates this finding generates an excess return of 7% per annum, after controlling for traditional risk factor exposure and adjusting for transaction costs.

Enhanced Asset Allocation and Risk Management

Dynamic Allocation in Private Equity

Private equity fund returns vary over time and knowing when to invest into which fund is crucial for investors. In this research project, we studied the dependence of different private equity fund returns on our Nowcaster regimes, such as inflation and growth. We distinguished different regions, including Europe and the US, as well as different fund types, such as buyout and venture capital funds. The results can then be applied to an asset allocation methodology that takes into account the relative attractiveness of the different regions and fund types in different market regimes.

Dynamic Allocation to Equity Style Factors

The increasing popularity of equity style factors, such as value, momentum, quality, size and low volatility, has put more trading pressure on these strategies and has affected their expected returns. In turn, more crowding pressure on these styles also increases their volatility, hence creating an additional source of return. In this bespoke project for a client, we used our unified framework for dynamic allocation based on macro, sentiment and valuation indicators to develop an approach to harvest not only the mean, but also the variance of equity style factors. Our model has the capacity to allocate dynamically to any style, as well as to offset the exposure to unattractive styles by allocating to the antithetic factor portfolio.

Expected Shortfall Asset Allocation: A Multi-dimensional Risk Budgeting Framework

Risk-based investment strategies, such as low-risk, maximum diversification or risk parity, have attracted considerable attention from both investor and academic communities since the 2008 crisis. To date, much of the research in this area has considered only one specific dimension of risk. In this article, we propose a generalised expected shortfall risk-budgeting investing framework, which makes it possible to deal in a simple and flexible way with various risks beyond volatility, namely valuation, asymmetry, tail and illiquidity risks. We empirically illustrate the methodology by proposing a risk-based strategic allocation for a multi-asset portfolio made of traditional and alternative assets with different degrees of liquidity.

Minimum Variance Portfolio: Choosing the Right Currency

In a minimum variance equity portfolio, choosing the right currency for optimisation can have a significant impact on construction and performance. Our backtested analysis shows that performance of equity portfolios using home or USD currencies can vary. Both can be optimal, depending on the context and client preferences. As part of this research project, we developed a third option that achieves a trade-off between the benefits of home currency and international USD optimisation.

Using Machine Learning to Strengthen Investment Decision-making

A Quantitative Approach to Private Equity Fund Selection

As the private equity industry reaches maturity and faces growing scrutiny from investors in terms of fees and returns, it is becoming increasingly important for investors to make accurate, high conviction decisions in a fast and efficient manner. Drawing on decades of private equity market experience, we have developed a machine-driven scoring tool to substantiate our human decision-making in the private equity fund selection process. The scores produced can be turned into investment decisions through an economic cost/benefit analysis to create a framework that can be calibrated according to business needs. The tool should allow our investment team to screen a larger pool of potential opportunities and focus more on value-creating activities.

Using Fundamental Variables and Machine Learning to Forecast Stock Returns Distribution and Enhance Low Risk Portfolios

Building on our research on forecasting stock-specific risk, we focused our attention this year on forecasting average stock returns. The purpose of the project was to create a filter that would screen out companies with low expected returns before applying our portfolio optimisation process. We used more than 100 fundamental and technical variables, as well as alternative data variables, such as stock-specific news sentiment and news volume provided by Ravenpack. We found that by using machine learning and this enlarged group of stock-specific variables, we were able to better forecast average stock returns. Importantly, by excluding the stocks with the lowest expected return forecast, we were able to improve the resulting risk-adjusted portfolio performance after transaction costs.

Forecasting Beta using Machine Learning and Equity Sentiment Variables

In a recent project, we applied machine learning, fundamental equity variables and big data equity sentiment variables to forecast equity beta. We found that machine learning algorithms are better at forecasting future stock beta than linear models. Big data variables, such as stock level sentiment and news volume, are significant in several models in addition to other fundamental variables. The results are statistically significant. The research will be published in a Wiley book entitled “Machine Learning and Asset Management”.

Important Information

This document is provided to you on a confidential basis and must not be distributed, published, reproduced or disclosed, in whole or part, to any other person.

The information and data presented in this document may discuss general market activity or industry trends but is not intended to be relied upon as a forecast, research or investment advice. It is not a financial promotion and represents no offer, solicitation or recommendation of any kind, to invest in the strategies or in the investment vehicles it refers to. Some of the investment strategies described or alluded to herein may be construed as high risk and not readily realisable investments, which may experience substantial and sudden losses including total loss of investment.

The investment views, economic and market opinions or analysis expressed in this document present Unigestion’s judgement as at the date of publication without regard to the date on which you may access the information. There is no guarantee that these views and opinions expressed will be correct nor do they purport to be a complete description of the securities, markets and developments referred to in it. All information provided here is subject to change without notice. To the extent that this report contains statements about the future, such statements are forward-looking and subject to a number of risks and uncertainties, including, but not limited to, the impact of competitive products, market acceptance risks and other risks.

Data and graphical information herein are for information only and may have been derived from third party sources. Although we believe that the information obtained from public and third party sources to be reliable, we have not independently verified it and we therefore cannot guarantee its accuracy or completeness. As a result, no representation or warranty, expressed or implied, is or will be made by Unigestion in this respect and no responsibility or liability is or will be accepted. Unless otherwise stated, source is Unigestion. Past performance is not a guide to future performance. All investments contain risks, including total loss for the investor.

Unigestion (UK) Ltd. is authorised and regulated by the UK Financial Conduct Authority (FCA) and is registered with the Securities and Exchange Commission (SEC). Unigestion Asset Management (France) S.A. is authorised and regulated by the French “Autorité des Marchés Financiers” (AMF). Unigestion Asset Management (Canada) Inc., with offices in Toronto and Montreal, is registered as a portfolio manager and/or exempt market dealer in nine provinces across Canada and also as an investment fund manager in Ontario and Quebec. Its principal regulator is the Ontario Securities Commission. Unigestion Asia Pte Limited is authorised and regulated by the Monetary Authority of Singapore. Unigestion Asset Management (Copenhagen) is co-regulated by the “Autorité des Marchés Financiers” (AMF) and the “Danish Financial Supervisory Authority” (DFSA). Unigestion Asset Management (Düsseldorf) SA is co-regulated by the “Autorité des Marchés Financiers” (AMF) and the “Bundesanstalt für Finanzdienstleistungsaufsicht” (BAFIN). Unigestion SA has an international advisor exemption in Quebec, Saskatchewan and Ontario. Unigestion SA is authorised and regulated by the Swiss Financial Market Supervisory Authority (FINMA). Unigestion SA’s assets are situated outside of Canada and, as such, there may be difficulty enforcing legal rights against Unigestion SA.