•  
  •  
 
Journal of the Association for Information Systems

Abstract

Financial intermediaries are essential for investors’ participation in financial markets. Because of their position within the financial system, intermediaries who commit misconduct not only harm investors but also undermine trust in the financial system, which ultimately has a significant negative impact on the economy as a whole. Building upon information manipulation theory and warranting theory and making use of self-disclosed data with different levels of external verification, we propose different classifiers to automatically detect financial intermediary misconduct. In particular, we focus on self-disclosed information by financial intermediaries on the business network LinkedIn. We match user profiles with regulator-disclosed information and use these data for classifier training and evaluation. We find that self-disclosed information provides valuable input for detecting financial intermediary misconduct. In terms of external verification, our classifiers achieve the best predictive performance when also taking regulator-confirmed information into account. These results are supported by an economic evaluation. Our findings are highly relevant for both investors and regulators seeking to identify financial intermediary misconduct and thus contribute to the societal challenge of building and ensuring trust in the financial system.

DOI

10.17705/1jais.00633

Share

COinS