Semantic Arts
Investment Bank Data Interpretation and Chatbot Development
Pages
1
Time to read
2 mins
Publication
Language
English
Pages
1
Time to read
2 mins
Publication
Language
English
This document is a technical report that discusses the development of a chatbot for an investment bank aimed at interpreting complex analyst reports. The report outlines the challenges faced by the bank in enhancing the chatbot's capabilities beyond simple queries to more nuanced questions that require an understanding of the analysts' language. It describes the creation of eight ontology modules to differentiate between common business KPIs and sector-specific metrics. The report details the collaboration with a natural language processing (NLP) vendor to extract and convert analysts' reports into a structured format, allowing the chatbot to query a triple store using SPARQL. The results of this initiative have shown promise, and the report mentions plans for a larger-scale project to expand the chatbot's capabilities across more sectors and improve the accuracy of its responses.