New framework predicts financial impact of events on time series data

Researchers have developed EventTime, a novel framework designed to predict the financial impact of discrete events on time series data. This system integrates long-term market context, short-term pre-event dynamics, and event metadata to estimate post-disclosure abnormal losses. EventTime utilizes a dynamic contrastive objective to address sparse supervision and has been tested on the SECURE dataset, which links cybersecurity incidents with stock market data. Experiments indicate that EventTime surpasses existing time-series and event-aware models in predicting financial losses following cybersecurity disclosures. AI

IMPACT Provides a new method for financial forecasting by incorporating discrete external events into time series analysis.

RANK_REASON The cluster contains a research paper detailing a new framework and dataset. [lever_c_demoted from research: ic=1 ai=1.0]

Read on arXiv cs.LG →

• arXiv
• EventTime
• Hugging Face

• paper
• product

AI-generated summary · Google Gemini · from 1 sources. How we write summaries →