‘Moore’s Law is disrupting the world of quant investing’

‘Moore’s Law is disrupting the world of quant investing’

16-08-2021 | Entrevista
Increasing computing power is altering the investment landscape. Developments in big data and machine learning are pivotal to the evolution of quant investing. We discussed this topic with Weili Zhou, Head of Quant Equity Research, and Pim van Vliet, Co-Head of Quant Equities.
  • Pim  van Vliet, PhD
    van Vliet, PhD
    Lead Portfolio Manager Conservative Equities and Co-head Quant Investments
  • Weili  Zhou
    Head of Quant Equity Research

Speed read

  • Growth in computing power is facilitating new modelling techniques 
  • Big data and machine learning could unlock uncorrelated alpha sources 
  • Adaptive nature of quant investing allows it to incorporate new evidence

What is the promise of big data and machine learning for investors?

Pim van Vliet: “In 1965, US engineer Gordon Moore predicted that the number of transistors on a chip would double every two years. The realization of his accurate forecast – famously termed Moore’s Law – has resulted in increasing computing power. While this has facilitated the birth of quant investing in the past, it is currently enabling new modelling techniques.”

“For one, systematic and repeatable patterns, which simple linear models do not capture, can now be tested. For example, some variables might only work when they cross a certain threshold, especially when combined with other variables.”

“Most quant models are based on traditional data, with a linear factor structure. Although this approach is effective, it does not consider non-linear patterns. This means that residual alpha may be left on the table. We believe the use of alternative data sources and new modelling techniques potentially increases the opportunity set and leads to better model predictions. Thus, Moore’s Law is disrupting the world of quant investing.”

Manténgase al día de las últimas perspectivas sobre inversión cuantitativa
Manténgase al día de las últimas perspectivas sobre inversión cuantitativa

What is the biggest difference between traditional and machine learning-based quant research?

Weili Zhou: “The role of the researcher changes from instructor to orchestrator. With the traditional approach, the researcher instructs the computer to test specific rules on input data to see whether they can help predict the output. In terms of machine learning, the researcher feeds both the input and output data to the computer for it to assess what the best rule is. This role change allows researchers to deal with more complexities. But you need to be cautious and pay attention to model explainability and overfitting.”

“Overfitting has always been a potential pitfall of quant investing. Many terms refer to this nemesis, such as ‘data mining’, ‘p-hacking’ and ‘factor fishing’. The issue here is that some patterns may come out as statistically significant, when in fact there is no real underlying phenomenon. The problem with overfitting is that a model will correctly explain the past, but fail when used in real-life situations.”

How do you potentially address this?

P.v.V.: “We have found that the cross-validation step, in the research process, can significantly reduce the risk of overfitting. Machine learning selects the model with the best predictive performance when ‘unseen data’ is used during the training phase. This step can be repeated continuously to recalibrate and retrain the model, so that it can adapt over time in a data-driven way.“

“Intensive sampling and resampling methods, such as neural network or random forest models, can therefore make stable predictions that also work out-of-sample. In addition to robust sampling, our proven investment philosophy, based on economic rationale and a prudent approach, helps to address this issue.”

And what about the implications of big data?

W.Z.: “Although it is difficult to measure, the amount of data is also roughly doubling every two years. Given this deluge, significant developments have taken place. Cloud-based data storage costs have plummeted. Highly dynamic investment approaches, such as intra-day momentum strategies, are now documented and implemented by some high-frequency traders. As described in the book Flash Boys, by Michael Lewis, some traders exploit a four-millisecond information advantage to beat market orders.”

“New and useful datasets are cropping up, such as those that house novel economic data on consumers and producers. Innovative techniques can also create new data. For example, natural language processing (NLP) can be used to analyze company filings, central bank statements or earnings call transcripts, and measure investor sentiment.”

“Also, macroeconomic data, which get reported with a few weeks’ delay, can be predicted in real-time with nowcasting using daily data points such as mobility indicators. Such developments are expanding the data available, likely creating alpha opportunities.”

Next-generation quant models could result in improved predictions on returns, sustainability and risk

What does next-generation quant investing look like?

P.v.V.: “Next-generation quant models could result in improved predictions on returns, sustainability and risk. Starting with the latter, risk is often considered to be somewhat easier to predict than return. And yes, risk is often non-linear. For example, leverage might be fine up to a certain threshold, but risk could rise disproportionally beyond this level. Due to next-generation models, we are seeing promising results in this area that can help us better predict stock crashes, on top of existing risk measures.”

“Also, besides absolute risk, forecasts on relative risk can be improved too. Industry classification is a standard way to group stocks, but next-generation models can better cluster similar securities beyond sectors, which should lead to better relative risk control.”

W.Z.: “In terms of sustainability, climate, ESG or SDG objectives can be efficiently implemented in a quant portfolio. Moreover, sustainability data is expanding quickly and improving in quality. Although the data are often backward-looking, nowcasting can be useful in predicting sustainability trends.”

“For example, it can be used to forecast which firms will be most effective at decarbonizing their businesses. New sustainability data can also be created using new techniques. This can be achieved by decomposing the capital expenditure and R&D of firms, or by classifying and linking firms to the 17 SDGs based on company profiles using NLP.”

P.v.V.: “Moving on to returns, the pursuit of alpha is the most challenging goal. Unlike risk and sustainability, returns are very unstable. Still, the breadth and depth of return databases is increasing. Datasets are going further back in time with a higher frequency level. This should increase the likelihood of successfully exploring and potentially exploiting repeating, non-linear patterns. Moreover, next-generation techniques also confirm the strength of traditional styles such as momentum interacting with low volatility.”

Next-generation quant strategies may be used to find alpha sources that are uncorrelated to existing factors

“Finally, next-generation quant strategies may be used to find alpha sources that are uncorrelated to existing factors. For instance, short-term signals tend to be uncorrelated, simply because they change frequently. These alpha signals can be captured and possibly exploited, although trading costs may limit potential capacity. Therefore, forecasting and reducing trading costs, another application of next-generation models, will also become more important when predicting short-term timing signals.”

Why is quant investing well equipped to handle changing investment landscapes?

W.Z.: “Quant investing has never been very dogmatic or normative and has evolved considerably over the last decades. In the past, we have seen many quant investors update their beliefs based on new evidence. 

For example, by including low volatility and sustainability variables in their strategies. With more data and better techniques available, we believe quant investors will continue to learn and adapt to changing landscapes.”

Los temas relacionados con este artículo son:

Información importante

Los Fondos Robeco Capital Growth no han sido inscritos conforme a la Ley de sociedades de inversión de Estados Unidos (United States Investment Company Act) de 1940, en su versión en vigor, ni conforme a la Ley de valores de Estados Unidos (United States Securities Act) de 1933, en su versión en vigor. Ninguna de las acciones puede ser ofrecida o vendida, directa o indirectamente, en los Estados Unidos ni a ninguna Persona estadounidense en el sentido de la Regulation S promulgada en virtud de la Ley de Valores de 1933, en su versión en vigor (en lo sucesivo, la “Ley de Valores”)). Asimismo, Robeco Institutional Asset Management B.V. (Robeco) no presta servicios de asesoramiento de inversión, ni da a entender que puede ofrecer este tipo de servicios, en los Estados Unidos ni a ninguna Persona estadounidense (en el sentido de la Regulation S promulgada en virtud de la Ley de Valores).

Este sitio Web está únicamente destinado a su uso por Personas no estadounidenses fuera de Estados Unidos (en el sentido de la Regulation S promulgada en virtud de la Ley de Valores) que sean inversores profesionales o fiduciarios profesionales que representen a dichos inversores que no sean Personas estadounidenses. Al hacer clic en el botón “Acepto” que se encuentra en el aviso sobre descargo de responsabilidad de nuestro sitio Web y acceder a la información que se encuentra en dicho sitio, incluidos sus subdominios, usted confirma y acepta lo siguiente: (i) que ha leído, comprendido y aceptado el presente aviso legal, (ii) que se ha informado de las restricciones legales aplicables y que, al acceder a la información contenida en este sitio Web, manifiesta que no infringe, ni provocará que Robeco o alguna de sus entidades o emisores vinculados infrinjan, ninguna ley aplicable, por lo que usted está legalmente autorizado a acceder a dicha información, en su propio nombre y en representación de sus clientes de asesoramiento de inversión, en su caso, (iii) que usted comprende y acepta que determinada información contenida en el presente documento se refiere a valores que no han sido inscritos en virtud de la Ley de Valores, y que solo pueden venderse u ofrecerse fuera de Estados Unidos y únicamente por cuenta o en beneficio de Personas no estadounidenses (en el sentido de la Regulation S promulgada en virtud de la Ley de Valores), (iv) que usted es, o actúa como asesor de inversión discrecional en representación de, una Persona no estadounidense (en el sentido de la Regulation S promulgada en virtud de la Ley de Valores) situada fuera de los Estados Unidos y (v) que usted es, o actúa como asesor de inversión discrecional en representación de, un inversión profesional no minorista. El acceso a este sitio Web ha sido limitado, de manera que no constituya intento de venta dirigida (según se define este concepto en la Regulation S promulgada en virtud de la Ley de Valores) en Estados Unidos, y que no pueda entenderse que a través del mismo Robeco dé a entender al público estadounidense en general que ofrece servicios de asesoramiento de inversión. Nada de lo aquí señalado constituye una oferta de venta de valores o la promoción de una oferta de compra de valores en ninguna jurisdicción. Nos reservamos el derecho a denegar acceso a cualquier visitante, incluidos, a título únicamente ilustrativo, aquellos visitantes con direcciones IP ubicadas en Estados Unidos.

Este sitio Web ha sido cuidadosamente elaborado por Robeco. La información de esta publicación proviene de fuentes que son consideradas fiables. Robeco no es responsable de la exactitud o de la exhaustividad de los hechos, opiniones, expectativas y resultados referidos en la misma. Aunque en la elaboración de este sitio Web se ha extremado la precaución, no aceptamos responsabilidad alguna por los daños de ningún tipo que se deriven de una información incorrecta o incompleta. El presente sitio Web podrá sufrir cambios sin previo aviso. El valor de las inversiones puede fluctuar. Rendimientos anteriores no son garantía de resultados futuros. Si la divisa en que se expresa el rendimiento pasado difiere de la divisa del país en que usted reside, tenga en cuenta que el rendimiento mostrado podría aumentar o disminuir al convertirlo a su divisa local debido a las fluctuaciones de los tipos de cambio. Para inversores profesionales únicamente. Prohibida su comunicación al público en general.

No estoy de acuerdo