MSCI Uses NLP to Measure Company Innovation

Investment research firm MSCI is using natural language processing (NLP) to measure company exposure to innovation for passive and active management.

Hitendra Varsani, a quantitative investment strategist at MSCI, said that although it is difficult to measure the concept of innovation and translate that into data factors, the index firm has been able to use these alternative methods to evaluate and map portfolio exposures.

“We can quantify that number on home ground, we can quantify it and then normalize it versus the rest of the [investment] universe and say, for example, ‘Tesla is more innovative than say BMW’. Once we can do that, we can measure the new factor exposures, and then we are in home territory and can measure the performance attribution to innovation,” Varsani said.

Varsani was speaking on a panel during the Summit for Asset Management this week.

The global market index firm uses NLP, a subset of artificial intelligence, to screen company information, including business descriptions and standard industrial classification of economic activities (SIC) codes, to identify keywords related to innovation. For example, the AI-based engine will scan words related to research and development activities or projects tied to improving efficiencies, which are then cross-checked with company filings to see how much of those innovative investments are linked to revenues and performances.

MSCI is also measuring other themes that can be linked to company performances, including digitalization programs or aging populations, such as looking at their consumption habits. 

For example, some asset managers have found that elderly people are turning to online services such as streaming websites more than ever as populations are in lockdown due to the coronavirus, Jacques Jenny, portfolio manager at Infusive Asset Management, tells WatersTechnology. Between January 1 and April 22, Netflix saw 16 million new subscribers register on its platform.

“There are many long-term themes that are driving the market today that may not have been available in the past and are difficult to measure but there’s a need to be able to measure them and integrate them into traditional factor-based analysis,” Varsani said.

Sustainability Stream

Varsani said that the MSCI has moved away from simply looking at risk and return when it comes to building out data solutions and capabilities for its clients. Going forward, the firm is also heavily focusing on a third stream: sustainability or environment, social and governance (ESG) factors.

The index firm is integrating new analytics and functionality into its toolkit to allow end investors to have better transparency of their exposure to ESG.

“’I may be generating a return, but did I do so in a sustainable way? What is the carbon emission [footprint] of my portfolio, my carbon intensity and is it worse than the benchmark?’, are just some of the questions being asked by clients and investors,” Varsani said. “That is what asset owners are currently evaluating and scrutinizing benchmarks and managers against, [and they are asking] how do we move to a low carbon and more sustainable world, and how do we measure that?”

But investor demand is not the only driver in this space, said Varsani. The development of better definitions, rating methodologies, and algorithms for defining metrics are all playing a role.

“We are seeing this shift from a bog-standard brag sheet to one that’s more enriched with more transparency across these different perspectives,” he said.

MSCI’s ESG research unit launched its ESG ratings product in May 2015. It is designed to help front office teams to integrate ESG factors into its existing investment processes.

The offering uses a rules-based methodology to identify leaders and laggards when it comes to ESG, rating companies according to their exposure to ESG risk, and how well they manage those risks relative to their peers. The rating also evaluates countries, mutual funds, and exchange-traded funds.