A Bayesian Model for Activities Recommendation and Event Structure Optimization Using Visitors Tracking

TL;DR

This paper introduces a Bayesian model leveraging visitor tracking and complex network theory to optimize event activity placement and recommend activities with high accuracy, improving visitor engagement and event management.

Contribution

It presents a novel Bayesian approach combined with complex network analysis for activity recommendation and event structure optimization, validated with an artificial database.

Findings

Recommendation system achieves approximately 95% accuracy.

The proposed method outperforms random baseline approaches.

Effective identification of popular activities and optimal placements.

Abstract

In events that are composed by many activities, there is a problem that involves retrieve and management the information of visitors that are visiting the activities. This management is crucial to find some activities that are drawing attention of visitors; identify an ideal positioning for activities; which path is more frequented by visitors. In this work, these features are studied using Complex Network theory. For the beginning, an artificial database was generated to study the mentioned features. Secondly, this work shows a method to optimize the event structure that is better than a random method and a recommendation system that achieves ~95% of accuracy.