Identifying Recent Behavioral Data Length in Mobile Phone Log

TL;DR

This paper proposes a method to dynamically identify the most recent segment of mobile phone logs, emphasizing recent behavioral patterns for improved behavior prediction, marking a novel approach in recency-based modeling.

Contribution

It introduces the first dynamic approach to determine recent behavioral data length from phone logs for behavior modeling.

Findings

First dynamic recent log identification method.

Improves recency-based behavior prediction.

Addresses the variability in individual phone usage patterns.

Abstract

Mobile phone log data (e.g., phone call log) is not static as it is progressively added to day-by-day according to individ- ual's diverse behaviors with mobile phones. Since human behavior changes over time, the most recent pattern is more interesting and significant than older ones for predicting in- dividual's behavior. The goal of this poster paper is to iden- tify the recent behavioral data length dynamically from the entire phone log for recency-based behavior modeling. To the best of our knowledge, this is the first dynamic recent log-based study that takes into account individual's recent behavioral patterns for modeling their phone call behaviors.