“AI and machine learning can improve measurement of ESG risks to enhance investment performance, says State Street.
“By using artificial intelligence (AI) and machine learning, new data providers and analyses are popping up to address some of these concerns” says Daniel Gerard, head of advisory solutions at State Street.
ESG is becoming increasingly important in the portfolio investment process, with asset owners rather than asset managers in the vanguard for its promotion.
Many investment managers now routinely advertise the inclusion of ESG analysis into their investment processes, across a widely-recognised range of five styles, namely: exclusionary screening, positive screening, ESG integration, impact investing and active stewardship.
Some managers are also making efforts to disaggregate the specific contribution of ESG factors to a portfolio’s total return.
AI and machine learning techniques should eventually help resolve the divergence between conventional ESG rating agencies.
However, it remains difficult to evaluate the environmental and social impact of companies’ operations, and the quality of governance metrics. Basically, are the tools – that is, the ESG rating agencies – sufficient?
“Most especially, there are ‘intangible risks’ that can’t always be anticipated and so can’t been measured,” Gerard says.”¹
What Daniel Gerard is referring to as “intangible risks”, can become tangible with the power of artificial intelligence.
Suzugia can help defining true ESG investing by identifying the broader set of criteria for adherence. We run very thorough investigations for sourcing and due-diligence of eligible investments vehicles.
AI can significantly improve ESG investment processes and reduce the risks by unifying the definitions and measurement criteria.
Our technology goes much beyond “sentiment analysis” or “positive vs. negative polarity assessment”. Our predicting engine, structures information and facts and learns from them at three levels:
- Knowledge: ESG factors, themes and facts are first learned and represented in a very parsimonious way.
- Relevance and Causality: semi-supervised techniques are used to represent relevance and causal relationships between these factors and facts
- Ranking and Decision Making: structured/directed graphs are learned to guide decision makers through their assessment process. We combine the AI-driven, automated approach with personal preferences of decision makers
By Dr. Francois Oustry