Что изменилось во время ковид-кризиса в значимости ESG метрик в оценке снижения цен акций: поиск ответа с помощью объяснительного ИИ для российского фондового рынка

Журнал Новой экономической ассоциации. 2026. Т. 70. № 1. С. 157–190.

Teplova T., Sokolova T., Kissa D., Gurov S.

This study is the first attempt to apply Explainable Artifi cial Intelligence (ХAI) to reveal the relationship of different Environmental, Social and Governance (ESG) metrics of stock issuers on downside risk in the Russian market. The methodology is based on the two-stage approach, i. e., neural networks with dense layers and the Shapley values from the game theory to interpret empirical results. This methodological approach has not been applied to the analysis of determinants of downside risk before. The specifi c of our study is the focus on the impact of a wide range of ecological factors with control of financial indicators of companies and macroeconomic indicators. We reveal the change in the ranking of factors during the COVID-19 crisis. We obtained a number of novel results. Before the crisis, the most signifi cant factor was the GDP growth. Environmental responsibility and the integral ESG score occupied the second and the third place, respectively, by strength of impact. However, adherence to some environment- related ESG practices increased downside risk. During the crisis, the ranking of the key drivers of downside risk by their impact power changed, and the debt burden moved to the fi rst place. The role of social responsibility and corporate governance in downside risk grew.

Keywords: нейронная сеть, downside risk, ESG, ESG, Shapley values, вектора Шепли, neural network, Explainable Artificial Intelligence (XAI), COVID 19 crisis, риск снижения цен акций, объяснительный искусственный интеллект (XAI), ковид кризис

Publication based on the results of: Models and methods for identifying patterns in global and national financial markets (2025)