BehaviorTracker

Abstract

Visualization of customer behavior is urgently needed for an increasing number of customer orders on O2O (online to offline) platform. Although many works have been done on visualizing customer opinion or customer click events of one store, visualizing customer switching behavior among stores is still challenging. The challenge is to show customer order records over time and structure the inter-connection among different stores when customer switching behavior happens. In this work, we focus on Takeout O2O service to present a novel visual analysis system for retailers focusing on customer switching behavior patterns. Firstly we define five customer segments based on switching behavior. Then this system enables temporal-spatial driver exploration for different segments through several interactive views. Moreover, in order to visualize inter-connection sequences, augmented streamgraph with the bundled parallel coordinates is proposed as one alternative technique to visualize temporal event sequences. Case studies through collaboration with domain experts also demonstrate the usefulness and effectiveness of this system in helping customer relationship management.