Data extraction and RAG: leveraging LLM for time series prediction

Borrelli, Fabrizio (A.A. 2024/2025) Data extraction and RAG: leveraging LLM for time series prediction. Tesi di Laurea in Data-driven models for investment, Luiss Guido Carli, relatore Antonio Simeone, pp. 48. [Master's Degree Thesis]

Full text for this thesis not available from the repository.

Abstract/Index

Literature review. Stock market forecasting. Natural language processing in financial contexts. Retrieval-augmented generation (RAG). Graph-based retrieval-augmented generation (GraphRAG). Methodological framework. Data sources and acquisition. NLP-based data enrichment processes. Knowledge graph construction and schema. Knowledge graph support for the multi-agent GraphRAG system. Multi-agent GraphRAG system. System architecture overview. Specialized agents and their roles. Multi-phase reasoning process. Traditional RAG vs. GraphRAG vs. multi-agent GraphRAG. Traditional RAG (document-based retrieval-augmented generation). GraphRAG (knowledge-graph-augmented generation). Multi-agent GraphRAG.

References

Bibliografia: p. 48.

Thesis Type: Master's Degree Thesis
Institution: Luiss Guido Carli
Degree Program: Master's Degree Programs > Master's Degree Program in Data Science e Management (LM-91)
Chair: Data-driven models for investment
Thesis Supervisor: Simeone, Antonio
Thesis Co-Supervisor: Martino, Alessio
Academic Year: 2024/2025
Session: Summer
Deposited by: Alessandro Perfetti
Date Deposited: 30 Sep 2025 10:09
Last Modified: 30 Sep 2025 10:09
URI: https://tesi.luiss.it/id/eprint/43375

Downloads

Downloads per month over past year

Repository Staff Only

View Item View Item