Score: 0

ORACLE: Time-Dependent Recursive Summary Graphs for Foresight on News Data Using LLMs

Published: December 17, 2025 | arXiv ID: 2512.15397v1

By: Lev Kharlashkin , Eiaki Morooka , Yehor Tereshchenko and more

Potential Business Impact:

Finds important news changes for schools weekly.

Business Areas:
Predictive Analytics Artificial Intelligence, Data and Analytics, Software

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.

Country of Origin
🇫🇮 Finland

Page Count
5 pages

Category
Computer Science:
Computation and Language