Distilled ChatGPT Topic & Sentiment Modeling with Applications in Finance
This work addresses the need for efficient and interpretable models in quantitative finance, though it is incremental as it applies existing distillation and transfer learning methods to a specific domain.
The study tackled the problem of creating interpretable features for financial analysis by using ChatGPT to develop lightweight topic and sentiment classification models, achieving results without significant accuracy loss as assessed on an expert-annotated dataset.
In this study, ChatGPT is utilized to create streamlined models that generate easily interpretable features. These features are then used to evaluate financial outcomes from earnings calls. We detail a training approach that merges knowledge distillation and transfer learning, resulting in lightweight topic and sentiment classification models without significant loss in accuracy. These models are assessed through a dataset annotated by experts. The paper also delves into two practical case studies, highlighting how the generated features can be effectively utilized in quantitative investing scenarios.