1. Research
To listen to the new podcast click here

What does machine learning have in common with cooking feijoda?

Authors
Caio Natividade
+44(20)754-55917
Sorin Ionescu
+44(20)754-72539
Machine learning, with all of their processing power, they’re able to more quickly highlight or find patterns in big data that would have otherwise been missed by human beings. Machine learning is a tool that can be used to enhance humans’ abilities to solve problems and make informed inferences on a wide range of problems, much wider than financial services for example helping diagnose diseases to coming up with solutions for global climate change.
There are also limitations to machine learning like not having access to a large enough data. This is where NLASR comes in. NLASR stands for Non-Linear Adaptive Style Rotation Model. It is a stock selection model that Deutsche Bank Research has been publishing on since 2012. The model uses machine learning to aggregate over 110 alphas and invest in thousands of stocks across the globe.
It is inspired by a technique called ‘adaptive boosting’, which means it is not a stand alone technique but it can be used in conjunction with many other types of learning algorithms to improve performance. What you are doing is creating a strong predictor from many weak predictors. Specifically, you’re boosting the importance of the times your learning model gets it wrong, so that it can focus more and more on the times when you normally get it wrong.
Systematic equity investors normally tilt their exposures according to factors – e.g. value, quality, momentum. In a long-only context, the investor might overweight stocks with good scores based on the factors they favour at a particular point in time. In a long-short context, they would go long stocks with high scores and short stocks with low scores on the factors they want exposure to. With the N-LASR framework, the investor is ‘delegating’ the decision of which factors to favour at any given point in time to the model. For instance the value factor has hurt the vast majority of equity quant portfolios over the last few years – the N-LASR model picked this up and went under-weight value. Investors are also familiar with so-called ‘momentum crashes’ – periods when the momentum factor, which is commonly employed in factor-based allocations, stops working. With N-LASR, the investor can track the ‘factors’ that the model is allocating to over time, which helps with performance attributions, a key requirement for any investment strategy. 
Listen to a new podcast to learn more 
For important disclosure information please see: https://research.db.com/Research/Disclosures/Disclaimer
 

© Copyright 2021. Deutsche Bank AG, Deutsche Bank Research, 60262 Frankfurt am Main, Germany. All rights reserved. When quoting please cite “Deutsche Bank Research”.

The above information does not constitute the provision of investment, legal or tax advice. Any views expressed reflect the current views of the author, which do not necessarily correspond to the opinions of Deutsche Bank AG or its affiliates. Opinions expressed may change without notice. Opinions expressed may differ from views set out in other documents, including research, published by Deutsche Bank. The above information is provided for informational purposes only and without any obligation, whether contractual or otherwise. No warranty or representation is made as to the correctness, completeness and accuracy of the information given or the assessments made. In Germany this information is approved and/or communicated by Deutsche Bank AG Frankfurt, licensed to carry on banking business and to provide financial services under the supervision of the European Central Bank (ECB) and the German Federal Financial Supervisory Authority (BaFin). In the United Kingdom this information is approved and/or communicated by Deutsche Bank AG, London Branch, a member of the London Stock Exchange, authorized by UK’s Prudential Regulation Authority (PRA) and subject to limited regulation by the UK’s Financial Conduct Authority (FCA) (under number 150018) and by the PRA. This information is distributed in Hong Kong by Deutsche Bank AG, Hong Kong Branch, in Korea by Deutsche Securities Korea Co. and in Singapore by Deutsche Bank AG, Singapore Branch. In Japan this information is approved and/or distributed by Deutsche Securities Inc. In Australia, retail clients should obtain a copy of a Product Disclosure Statement (PDS) relating to any financial product referred to in this report and consider the PDS before making any decision about whether to acquire the product.

14.8.0