Words Matter: The Role of Texts in Online Credit Markets
Posted: 6 Jun 2014 Last revised: 13 Dec 2017
Date Written: July 15, 2016
Texts are prevalent in online markets, but its economic value is far from certain. This paper examines whether linguistic styles of texts can help mitigate issues of information asymmetry, and more importantly, whether investors can “correctly” interpret the economic value of texts. Using data from online debt crowdfunding, we first show that investors indeed take into account the “loan purpose” descriptions that borrowers provide in their loan requests, even though these texts are not verified or legally binding. We then analyze the linguistic features of these descriptions, and show that well-established features that influence reader behaviors (readability, positive tones, and deception cues) all meaningfully relate to loan repayment. Interestingly however, investors do not correctly interpret the economic values of all linguistic features, most notably deception cues. This suggests that even though “texts” are often considered “soft” or “non-standard” information in finance, it can be quantified and standardized into credit risk modeling. Our study points to opportunities for efficiency improvement by leveraging texts that are not yet documented in the literature.
Keywords: texts, peer-to-peer lending, crowdfunding, predictive analysis, sentiment analysis, subjectivity analysis, readability analysis, deception detection, machine learning
Suggested Citation: Suggested Citation