Preconference Day: Summits & WorkshopsMonday, 18 November 2024 - GMT (Greenwich Mean Time, GMTZ)

Perspectives from across the industry. Aspects of risk and alpha.

How is the post-MiFID II era shaping up the landscape?

This study offers an innovative approach to addressing the challenges of measuring workplace inclusion culture and provides concrete evidence of its impact on innovation, financial performance and stock returns. We leverage alternative data sources—such as online workforce profiles and employee reviews—and employ advanced data science and textual analysis techniques to construct meaningful inclusion culture signals.

Perspectives on allocation strategy.

We study how the global equity markets price physical climate risk associated with tropical cyclones. To assess firms' exposure to this risk, we use a bottom-up, forward-looking measure, based on probabilistic assessments of losses to firms’ geolocalized physical assets. The expected losses by all events or rare events are estimated considering various climate scenarios (RCP 2.6, 4.5, and 6.0). Additionally, we examine the impact of investors' concerns regarding cyclone risks on stock returns. We find that a one standard deviation higher exposure under RCP 4.5 is associated with a 1.5 to 2.2% higher annual return during periods of low cyclone concerns. However, during periods of heightened cyclone concerns, a one standard deviation higher in exposure leads to a drop of 0.8 to 1.7% annual return. Overall, our finding suggests that the global equity markets have started to incorporate physical climate risk related to tropical cyclones. However, during periods of increased cyclone activity, investors' concerns may cause a decrease in demand for stocks that are more exposed to this risk, resulting in a decline in their prices, even if these firms' facilities are not directly affected by cyclone events.

The “Interpretable Supervised Portfolio" framework is an innovative approach to asset allocation by leveraging the RuleFit algorithm to engineer optimal portfolio weights directly, prioritizing optimization before prediction. Contrary to traditional methods that often apply prediction before optimization, the proposed methodology ensures a more strategic asset allocation by using a supervised learning algorithm in a novel manner. The study employs an enhanced version of RuleFit, an intrinsically interpretable algorithm, to transform complex, non-linear predictive models into simpler, linear models that incorporate feature interactions from decision tree ensembles. This shift not only maintains statistical accuracy comparable to that of gradient boosting across various investment universes but also enhances transparency and trust in the models by offering direct insights into the relationship between inputs and outputs. A major finding is the linearized models' ability to perform on par with their non-linear counterparts, debunking the assumption that more complex models necessarily yield better predictions for optimal portfolio weights.

Many asset managers use sell-side brokers to buy and sell shares of common stock. Typically, orders are distributed between several brokers using so-called algo wheels. This allows asset managers to compare brokers, and, thereby, ensure they receive the best possible execution. This paper describes how reinforcement learning techniques can be used to optimally distribute orders between brokers. The methodologies find a balance between exploitation and exploration, i.e., the best performing broker receives most orders, and others receive sufficient orders to determine which broker performs best.

With increasing interest in equity portfolios that prioritize risk and volatility reduction, designing quantitative strategies with ultra-low beta (<0.1) is more crucial than ever. Generating attractive returns while managing downside risk effectively requires forward-thinking approaches, such as dynamic beta trading systems and targeted single-stock management. Quantmade, a global leader in wealthtech, has developed specialized expertise in these low-beta solutions.