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
Online Document "PROD0000000000464268" not found.
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.