Company earnings calls are crucial for transparency and can significantly impact stock prices. This post explains how generative AI, specifically large language models (LLMs), can streamline the creation of earnings call scripts. It introduces two methods: few-shot prompt engineering and fine-tuning, both utilizing Amazon Bedrock's capabilities. Through examples and evaluations, it demonstrates the potential of these AI technologies to improve financial communications while considering trade-offs in comprehensiveness, hallucinations, ease of use, and cost.

18m read timeFrom aws.amazon.com
Post cover image
Table of contents
Solution overviewEvaluation of few-shot prompt engineering and fine-tuningConclusion

Sort: