Alex Kim, Maximilian Muhn, and Valeri Nikolaev (2023)

Chicago Booth Working Paper, Fama-Miller Center Working Paper, Becker Friedman Institute for Economics Working Paper

Ask GPT about this paper [Link]

We probe the economic usefulness of generative AI in summarizing complex corporate disclosures. The summaries are more effective at explaining stock market reactions to the disclosed information. We show that bloated disclosure is associated with adverse capital market consequences.

Alex Kim, Maximilian Muhn, and Valeri Nikolaev (2023)

Chicago Booth Working Paper, Fama-Miller Center Working Paper, Becker Friedman Institute for Economics Working Paper

Ask GPT about this paper [Link]

We explore the value of generative AI tools in helping investors uncover dimensions of firm-level corporate risk. Using the GPT 3.5 model to generate risk summaries and assessments from the context provided by earnings call transcripts, we show that GPT-based measures possess significant information content and outperform the existing risk measures in predicting (abnormal) firm-level volatility and firms' choices such as investment and innovation.

Alex Kim, Maximilian Muhn, and Valeri Nikolaev (2024)

Chicago Booth Working Paper, Fama-Miller Center Working Paper, Becker Friedman Institute for Economics Working Paper

Companion App [Link]

We investigate whether an LLM can successfully perform financial statement analysis in a way similar to a professional human analyst. We provide standardized and anonymous financial statements to GPT4 and instruct the model to analyze them to determine the direction of future earnings. Even without any narrative or industry-specific information, the LLM outperforms financial analysts in its ability to predict earnings changes. The LLM exhibits a relative advantage over human analysts in situations when the analysts tend to struggle. Furthermore, we find that the prediction accuracy of the LLM is on par with the performance of a narrowly trained state-of-the-art ML model. 

Alex Kim, Maximilian Muhn, Valeri Nikolaev, and Yijing Zhang (2024)

Chicago Booth Working Paper, Fama-Miller Center Working Paper, Becker Friedman Institute for Economics Working Paper

We introduce a novel approach to learning the information that investors react to when processing textual information. We use the attention mechanism that learns to identify content that triggers market reactions to disclosed information. The explanatory power of the attention-based model significantly exceeds that of attention-free models. We then develop and analyze a comprehensive set of topics discussed in companies' annual reports. Segment information, goodwill and intangibles, revenues, and operating income are the topics that receive the most attention from investors. Despite their prominence in the public discourse, sustainability and governance are consistently among the least important topics judging by market reactions. Building on our approach, we show that regulatory interventions can successfully enhance the relevance of textual communication. We also show that firms strategically position information within MD\&A to influence investor focus.

Alex Kim, David Kim, Maximilian Muhn, Valeri Nikolaev, and Eric So (2024)

Chicago Booth Working Paper, Fama-Miller Center Working Paper

We explore how generative AI shapes both overall performance and disparities in investment tasks. When investors are given AI summaries aligned with their sophistication, they become better at processing financial information and making investment decisions. Conversely, misaligned summaries generally have an adverse effect, suggesting AI's ability to benefit investors hinges on personalization of information. We also show AI's benefits accrue disproportionately to individuals with higher financial expertise, which stems from an inherent tradeoff between accessibility for less sophisticated investors and technical precision used by more sophisticated investors.