VideoConviction: A Multimodal Benchmark for Human Conviction and Stock Market Recommendations
This addresses the challenge of evaluating multimodal AI in financial discourse for researchers and practitioners, though it is incremental as it builds on existing multimodal and financial analysis methods.
The paper tackles the problem of analyzing financial influencers' stock recommendations by introducing VideoConviction, a multimodal dataset with 6,000+ expert annotations, and finds that while multimodal inputs improve ticker extraction, models struggle to distinguish conviction, with an inverse betting strategy outperforming the S&P 500 by 6.8% in annual returns but at higher risk.
Social media has amplified the reach of financial influencers known as "finfluencers," who share stock recommendations on platforms like YouTube. Understanding their influence requires analyzing multimodal signals like tone, delivery style, and facial expressions, which extend beyond text-based financial analysis. We introduce VideoConviction, a multimodal dataset with 6,000+ expert annotations, produced through 457 hours of human effort, to benchmark multimodal large language models (MLLMs) and text-based large language models (LLMs) in financial discourse. Our results show that while multimodal inputs improve stock ticker extraction (e.g., extracting Apple's ticker AAPL), both MLLMs and LLMs struggle to distinguish investment actions and conviction--the strength of belief conveyed through confident delivery and detailed reasoning--often misclassifying general commentary as definitive recommendations. While high-conviction recommendations perform better than low-conviction ones, they still underperform the popular S\&P 500 index fund. An inverse strategy--betting against finfluencer recommendations--outperforms the S\&P 500 by 6.8\% in annual returns but carries greater risk (Sharpe ratio of 0.41 vs. 0.65). Our benchmark enables a diverse evaluation of multimodal tasks, comparing model performance on both full video and segmented video inputs. This enables deeper advancements in multimodal financial research. Our code, dataset, and evaluation leaderboard are available under the CC BY-NC 4.0 license.