ESG features explain one bit of idiosyncratic price returns

We systematically investigate the links between price returns and ESG features. We propose across-validation scheme with random company-wise validation to mitigate the relative initial lackof quantity and quality of ESG data, which allows us to use most of the latest and best data toboth train and validate our models. Boosted trees successfully explain a single bit of annual pricereturns not accounted for in the traditional market factor. We check with benchmark features thatESG features do contain significantly more information than basic fundamental features alone. Themost relevant sub-ESG feature encodes controversies. Finally, we find opposite effects of betterESG scores on the price returns of small and large capitalization companies: better ESG scoresare generally associated with larger price returns for the latter, and reversely for the former