Machine learning and social action in markets: From first- to second-generation automated trading
Christian Borch, Bo Hee Min
Abstract
Machine learning (ML) models are gaining traction in securities trading because of their ability to recognize and predict patterns. This study examines how ML is transforming automated trading. Drawing on 213 interviews with market participants (including 94 with people working at ML-employing firms) as well as ethnographic observations of a trading firm specializing in ML-based automated trading, we argue that ML-based (‘second-generation’) automated trading systems are different to previous (‘first-generation’) automated trading systems. Where first-generation systems are based on human-defined rules, second-generation systems develop their trading rules independently. We further argue that the use of such second-generation systems prompts a rethinking of established concepts in economic sociology. In particular, a Weberian notion of social action in markets is incompatible with such systems, but we also argue that second-generation automated trading calls for a reconsideration of the notion of the performativity of financial models.