Quantitative Methods - Articles & White Papers

The econometric canon is poorly suited for conducting investment research because of the unstructured nature of financial data as well as the complex relationships involved in economic systems. Machine learning (ML) techniques offer the numerical power and functional flexibility needed to identify complex patterns in high-…

This paper investigates the determinants of the performance decay of known investment strategies after their publication in academic journals. Recently, several authors have conducted meta-analyses of the literature on stock return predictability. The overwhelming finding of these studies is that return predictability…

The most common models to assess asset returns are a linear combination of risk factors. Amundi has employed tree-based machine learning algorithms to capture nonlinearities and detect interaction effects among risk factors in the EUR and USD credit space.

Machine learning (ML) mispricing models are designed to detect hidden nonlinearities that are important in predicting the fundamental value of stocks. As such, they have the potential to outperform corresponding linear regression (LR) mispricing models. Thus, it is important to allow for nonlinearities and interactions in…

Over the past 50 years, small-cap stocks have returned, on average, about 2% per year more than large-cap stocks, according to Ken French’s data. The inclusion of the small-cap factor to help better explain stock movements was one of Nobel Prize–winner Eugene Fama’s biggest early breakthroughs. This higher return, though,…

The authors provide the first quantitative survey of the empirical literature on hedge fund performance. They examine the impact of potential biases on the reported results. Using a sample of 1,019 intercept terms from regressions of hedge fund returns on risk factors (the 'alpha') collected from 74 studies…

The authors provide empirical evidence that the returns on U.S. equity momentum exhibit a time-varying skewness which deepens during dramatic losses (crashes). As a result, the dynamics of the strategy expected returns reflects the time variation in both conditional volatility and skewness. This has first order implications…

The Australian equities market is one of the most concentrated by stock and sector. The universe is also small relative to global markets. This paper shows that these nuances present challenges when assessing factor strategy efficacy. This paper shows that despite these challenges, there is an alternative way to invest in a…

With a range of quantitative techniques available, the best discretionary managers can enhance their investment process as never before.

The big problem behind thoughtful capital allocation is that there are a wide range of approaches to choose from, where each method relies upon a unique – or purportedly unique –hypothesis to extract 'allocation alpha' and where such hypotheses run the gamut of investment sophistication. Nonetheless, allocators welcome…

Modelling the risk of private assets in a multi-asset class portfolio is notoriously difficult due to the lack of observable, market-traded returns from which volatilities and correlations with other risk factors can be estimated.

Heidrick & Struggles’ first annual survey of data, analytics, and artificial intelligence executives examines both organisational structure and compensation for roles with these responsibilities. Quant roles are also covered.

This study analyses oil price movements through the lens of an agnostic random forest model, which is based on 1,000 regression trees. The results underscore the importance of incorporating financial factors into oil models: US interest rates, the dollar and the VIX together account for 39% of the models' RMSE reduction…

Momentum investing performed well following episodes when value stocks were cheap. Of course, momentum portfolios did not perform nearly as well as value portfolios, but they did still beat the generic market. This article digs into the details.

The authors find that factor momentum concentrates in factors that explain more of the cross section of returns and that it is not incidental to individual stock momentum: momentum-neutral factors display more momentum.

Manager-selected benchmarks are suboptimal as they are not free of conflict of interests. Investors can use sectors to identify more appropriate benchmarks. However, this ignores factors, which are better at explaining investment returns.

The authors examine diseconomies of scale for two different investment approaches: quantitative and fundamental. Using separate account (SA) data where the investment approach is self-identified, they find that fundamental SAs exhibit greater diseconomies of scale than quantitative SAs.

Trend following strategies measure the strength of price trends and take long or short positions in markets that are trending up or down. The authors study the five largest managed futures managers from 2015-2021 to measure turbulence in both magnitude and decomposition.

The authors propose that investment strategies should be evaluated based on their net-of-trading-cost return for each level of risk, which we term the "implementable efficient frontier." While numerous studies use machine learning return forecasts to generate portfolios, their agnosticism toward trading costs leads…

Machine learning is a tool being used for developing trading hedging strategies. This study investigates the use of deep reinforcement learning algorithms to hedge convexity and volatility (gamma and vega) in a system that includes transaction costs. It examines the optimal hedge strategy under three different objective…