A Recommendation Agent for Mobile Phone Users Using Bayesian Behavior Prediction

Abstract

This paper presents a novel agent system which provides a user with useful recommendations of behavior and information based on behavior prediction. The agent understands user's context from a GPS sensor and a mobile phone, and predicts user's future behavior based on user's context. And the prediction of user's future behavior can be used to provide the user with the suggestion of performing behavior and/or the recommendation of information which are relevant to the predicted user's behavior. Here, behavior prediction is performed by Dynamic Bayesian Network, which can handle time-series data. The experimental results showed that the proposed agent system was enough to provide convenient recommendation services to users.

Real-Time Prediction of Gamers Behavior Using Variable Order Markov and Big Data Technology: A Case of Study

“…These advantages can be extrapolated for domains different than online social networks. Finally, a work from Kim & Cho [16] proposed a system for providing recommendations to mobile phone users by predicting their behavior using Dynamic Bayes networks, which can handle time-series data. Finally, in the field of online social games (which are closer to the present work), Zhu et al [22] have recently studied theoretically the influence of user behavior in order to determine continuance intention, which is an issue related to churn prediction.…”

Recommendation of Points of Interest from User Generated Data Collection

“…The agent system based described in [4] is based on prediction of the user's future behavior. The system understands the context from the GPS receiver and the prediction is performed by Dynamic Bayesian Networks.…”