Face Value: Trait Impressions, Performance Characteristics, and Market Outcomes for Financial Analysts

Abstract

Using machine learning–based algorithms, we measure key impressions about sell‐side analysts using their LinkedIn photos. We find that impressions of analysts’ trustworthiness (TRUST) and dominance (DOM) are positively associated with forecast accuracy, especially after recent in‐person meetings between analysts and firm managers. High TRUST also enhances stock return sensitivity to forecast revisions, especially for stocks with high institutional ownership. In contrast, the impression of analysts’ attractiveness (ATTRACT) is only positively associated with accuracy for new analysts or when a firm has a new CEO or CFO. Furthermore, while high DOM helps male analysts’ chances of attaining All‐Star status, it reduces female analysts’ accuracy and the likelihood of winning the All‐Star award. In addition, the relation between TRUST and accuracy is modulated by the disclosure environment and is attenuated by Regulation Fair Disclosure. Our results suggest that face impressions influence analysts’ access to information and the perceived credibility of their reports.

The many faces of social media in business and economics research: Taking stock of the literature and looking into the future

“…Research in this theme has viewed social media primarily as a data source to assess phenomena that are otherwise difficult or impossible to measure. Thus, in this research strand, the focus of the investigation is not social media as a phenomenon per se but rather the data that social media provide to study other phenomena (e.g., Barbos & Kaisen, 2022; Boegershausen et al., 2022; Bourreau et al., 2022; Chau et al., 2020; Dugoua et al., 2022; Ge et al., 2016; Jiang et al., 2018; Kuchler et al., 2022; Lee et al., 2022; Makridis, 2022; Peng, Teoh, et al., 2022; Sinclair et al., 2022; Tambe, 2014; Zhang & Ram, 2020).…”

Machine learning methods in finance: Recent applications and prospects

“…Their main analysis studies the effect of executives' trustworthiness on audit fees. Peng et al (2022) leverage the social network LinkedIn and apply ML to profile photos of sell-side analysts to construct measures of trustworthiness, dominance, attractiveness, etc. Kamiya et al (2019) use ML to first measure the width-to-height ratio of CEOs' faces from portrait photos and then infer a measure of facial masculinity to study its effect on firms' riskiness.…”

CFO facial beauty and bank loan contracting

“…Although many prior studies use measures of beauty based on human ratings (e.g., Eckel & Petrie, 2011;Graham et al, 2017;Mulford et al, 1998), recent studies use machine learningbased facial-feature evaluation (e.g., Hsieh et al, 2020;Peng et al, 2022). In this study, we | 983 follow the latest literature and use a computer-based measure of facial attractiveness, which facilitates data availability and ensures the objectivity and replicability of the results.…”

“…Although beauty is a subjective assessment, we believe that the use of machine learningbased technology is appropriate in the bank loan contracting setting for the following reasons. First, machine learning-based facial-feature evaluation techniques are well developed in the field of computer science (e.g., Eisenthal et al, 2006;Liang et al, 2018) and have been widely used in the recent literature (e.g., Hsieh et al, 2020;Peng et al, 2022). 13 Second, machine learning-based technology is efficient and cost-effective for analysing large samples, is more objective in that it is not sensitive to individual judgements and biases, and allows researchers to replicate previous findings.…”

“…Trustworthiness reflects the observer's perceptions of the individual's ability, benevolence, and integrity (Hsieh et al, 2020); competence concerns perceptions of the individual's ability to carry out their intentions (Oosterhof & Todorov, 2008); and attractiveness (or facial beauty, as we use in this paper) is associated with perceived novelty, initial attraction, and greater attention from the information bearers (Peng et al, 2022).…”