ORACLE: Time-Dependent Recursive Summary Graphs for Foresight on News Data Using LLMs
By: Lev Kharlashkin , Eiaki Morooka , Yehor Tereshchenko and more
Potential Business Impact:
Finds important news changes for schools weekly.
ORACLE turns daily news into week-over-week, decision-ready insights for one of the Finnish University of Applied Sciences. The platform crawls and versions news, applies University-specific relevance filtering, embeds content, classifies items into PESTEL dimensions and builds a concise Time-Dependent Recursive Summary Graph (TRSG): two clustering layers summarized by an LLM and recomputed weekly. A lightweight change detector highlights what is new, removed or changed, then groups differences into themes for PESTEL-aware analysis. We detail the pipeline, discuss concrete design choices that make the system stable in production and present a curriculum-intelligence use case with an evaluation plan.
Similar Papers
FLAIRR-TS -- Forecasting LLM-Agents with Iterative Refinement and Retrieval for Time Series
Computation and Language
Helps computers guess future numbers better.
Toward Reasoning-Centric Time-Series Analysis
Artificial Intelligence
Helps computers understand why things change.
Time Series Forecasting as Reasoning: A Slow-Thinking Approach with Reinforced LLMs
Machine Learning (CS)
Teaches computers to predict future events better.