Sustainable investing is becoming increasingly data-focused as more companies report on the impact of their actions. While this reporting is generally welcomed by the investment community, the lack of standardization in environmental, social, and governance (ESG) data still has many analysts concerned about its reliability and comparability.
To enhance this information’s value, some money managers are turning to advanced quantitative techniques.
What Is Quantitative Finance?
Quantitative finance uses sophisticated calculations to evaluate investment opportunities. Quantitative analysts, also referred to as “quants,” apply advanced mathematics, deep corporate finance knowledge, and technical computing skills to determine risk/reward profiles using multiple data sources.
The Principles for Responsible Investment (PRI) explain that the quantitative investment process features three phases:
- Identifying patterns, correlations, or key factors that appear to affect assets’ price movements using statistical or valuation analysis.
- Creating models, built around algorithms, that test step 1 theories against historical data sets.
- Deploying models that survive step 2 tests to find stocks and bonds with similar characteristics, and building a portfolio that includes appropriate risk-management measures.
Any number of models can drive investment decisions, but each must be monitored for performance in all market conditions, according to PRI. At times, broader market dynamics may render a model moot, forcing an analyst to return to step 1 to discern other patterns.
Within this framework, a quant focuses on how a company’s data relates to the broader models, not the rationale behind the entity’s numbers. This differs from the work of traditional financial analysts, who may leverage tools like qualitative research, industry expertise, and familiarity with a company’s management.
Quantitative Finance and ESG
PRI explains that quants can build carefully weighted portfolios with models that correlate ESG data with other factors, from size and growth to value and volatility. They may underweight securities with low ESG scores or adjust the weight of each security against an ESG data set.
Yet there is currently little standardization in what is measured and reported among companies, industries, and sectors. Still, experts from PanAgora Asset Management argue that because ESG data needs additional advanced processing to be considered “implementable,” quantitative investors have an advantage in ESG strategy. They claim to be able to “extract knowledge” via quantitative finance techniques, “generating alpha from the data deluge.”
Others, such as Acadian Asset Management, are still “investigating.” Before turning its quantitative machine learning techniques to the complexities of ESG with “greater conviction,” Acadian hopes “to identify [the ESG] data points that are more relevant at the sector level, the most critical for corporate success, and the most predictive for returns.”