GPT-3 is a state-of-the-art natural language processing (NLP) model developed by OpenAI. It has the ability to generate human-like text and can perform a wide range of language tasks, such as translation, summarization, report writing and question answering.
Using GPT-3 to analyze BoE MPC minutes and a Goldman Sachs quarterly earnings call.
In the video above (click on '> Play') we use OpenAi's ChatGPT and GPT3 to summarise two types of transcripts.
- Central Bank monetary policy minutes
- Company quarterly earnings calls
When summarising Central Bank Monetary Policy GPT3 is able to effortlessly trawl through thousands of words to pick out and pinpoint the key macro-economic data, policy recommendations and forward guidance.
In analyzing company earnings calls the AI is similarly able to to identify and contextualise fundamental financial data.
In both cases GPT3 is able to output key financial data in either prose or in machine readable form suitable for processing in software applications. In this video you will see how to create simple prompts to distill the essential information and have the AI output it in any format of your choice.
Video links:
Bank of England Dec 2022 minutes: https://www.bankofengland.co.uk/monetary-policy-summary-and-minutes/2022/december-2022
Goldman Sachs Q3 2022 earnings call transcript: https://seekingalpha.com/article/4547268-goldman-sachs-group-inc-gs-q3-2022-earnings-call-transcript
Lucidate primer on sentiment analysis: https://www.lucidate.co.uk/forum/data-visualization/data-visualization-pt5-complex-visualizations