Making words work: Using financial text as a predictor of financial events

2010 | Decision Support Systems | Citations: 34

Authors: Cecchini, Mark; Aytug, Haldun; Koehler, Gary J.; Pathak, Praveen

Abstract: We develop a methodology for automatically analyzing text to aid in discriminati ... Expand

Abstract: We develop a methodology for automatically analyzing text to aid in discriminating firms that encounter catastrophic financial events. The dictionaries we create from Management Discussion and Analysis Sections (MD&A) of 10-Ks discriminate fraudulent from non-fraudulent firms 75% of the time and bankrupt from nonbankrupt firms 80% of the time. Our results compare favorably with quantitative prediction methods. We further test for complementarities by merging quantitative data with text data. We achieve our best prediction results for both bankruptcy (83.87%) and fraud (81.97%) with the combined data, showing that that the text of the MD&A complements the quantitative financial information. Collapse

Topics: knowledge representation accounting fraud detection missing data research and development

Methods: support vector machine ontological modelling WordNet descriptive statistic experiment

Theories: linguistics theory