Process Mining to Discover Shoppers’ Pathways at a Fashion Retail Store Using a WiFi-Base Indoor Positioning System

We present a preliminary report of a customer pathway analysis in an off-line store. Smart phone WiFi-based positioning technology is used to identify each customer’s pathway behavior. The log data containing the space-time information are analyzed using process mining, a tool that provides a comprehensive view of an entire process. The main benefit of process mining is that it provides the topological structure of the processes. We installed a WiFi signal-capturing device in a retail store of a fashion brand in South Korea and collected data over a two-month period. Halfway through the experimental period, we swapped a set of mannequins displayed at the entrance to the store with an item stand. We then compared the customers’ pathway behavior before and after the change. Through an analysis based on process mining, we observed a change in the topological structure of the pathway behavior following the change in the display setting. This paper demonstrates the possibilities of analyzing customer behavior using WiFi-based technology and the process mining technique.Note to Practitioners—The main goal of this paper is to demonstrate the possibility of WiFi-based positioning technology and analytical methodology for analyzing indoor movement in the era of Big Data and the Internet of Things. Recently, with advances in communication, sensors, and wearable computing technologies, strong interest has been shown in marketing and retail behavior studies that can capture customer travel data in off-line stores to inform and improve sales and marketing. As the application of off-line store behavior analysis for behavior studies and marketing gains momentum, this paper can be used as a foundation for the development of sensor-based location analysis systems or devices for off-line stores. The focus of this paper is not to investigate customer behavior related to the display change nor the behavioral science related to retail. Rather, we experimentally demonstrate the value of the proposed technology and the process mining technique for future research.

[1]  Romit Roy Choudhury,et al.  SurroundSense: mobile phone localization via ambience fingerprinting , 2009, MobiCom '09.

[2]  Boudewijn F. van Dongen,et al.  Towards Improving the Representational Bias of Process Mining , 2011, SIMPDA.

[3]  Boudewijn F. van Dongen,et al.  A genetic algorithm for discovering process trees , 2012, 2012 IEEE Congress on Evolutionary Computation.

[4]  R. E. Milliman,et al.  Atmospheric Effects on Shopping Behavior: A Review of the Experimental Evidence , 2000 .

[5]  Sander J. J. Leemans,et al.  Discovering Block-Structured Process Models from Event Logs - A Constructive Approach , 2013, Petri Nets.

[6]  Parth H. Pathak,et al.  Analyzing Shopper's Behavior through WiFi Signals , 2015, WPA@MobiSys.

[7]  Peter Bak,et al.  Understanding customer behavior using indoor location analysis and visualization , 2014, IBM J. Res. Dev..

[8]  Carles Gomez,et al.  Overview and Evaluation of Bluetooth Low Energy: An Emerging Low-Power Wireless Technology , 2012, Sensors.

[9]  Xiaolan Xie,et al.  Discovery of patient pathways from a national hospital database using process mining and integer linear programming , 2015, 2015 IEEE International Conference on Automation Science and Engineering (CASE).

[10]  Wil M. P. van der Aalst,et al.  Process Mining Applied to the Test Process of Wafer Scanners in ASML , 2009, IEEE Transactions on Systems, Man, and Cybernetics, Part C (Applications and Reviews).

[11]  M.A. Sotelo,et al.  Indoor Robot Localization System Using WiFi Signal Measure and Minimizing Calibration Effort , 2005, Proceedings of the IEEE International Symposium on Industrial Electronics, 2005. ISIE 2005..

[12]  Sander J. J. Leemans,et al.  Discovering Block-Structured Process Models from Event Logs Containing Infrequent Behaviour , 2013, Business Process Management Workshops.

[13]  Wil M. P. van der Aalst,et al.  Workflow mining: discovering process models from event logs , 2004, IEEE Transactions on Knowledge and Data Engineering.

[14]  Bernardo Nugroho Yahya,et al.  Domain-driven actionable process model discovery , 2016, Comput. Ind. Eng..

[15]  Boudewijn F. van Dongen,et al.  Process Discovery using Integer Linear Programming , 2009, Fundamenta Informaticae.

[16]  Juan Miguel García-Gómez,et al.  Process Mining for Individualized Behavior Modeling Using Wireless Tracking in Nursing Homes , 2013, Sensors.

[17]  Wil M. P. van der Aalst,et al.  Process Mining in Healthcare: Data Challenges When Answering Frequently Posed Questions , 2012, ProHealth/KR4HC.

[18]  San-Yih Hwang,et al.  A process-mining framework for the detection of healthcare fraud and abuse , 2006, Expert Syst. Appl..

[19]  Chong Meng Samson See,et al.  A Real-Time Indoor WiFi Localization System Utilizing Smart Antennas , 2007, IEEE Transactions on Consumer Electronics.

[20]  Jing Liu,et al.  Survey of Wireless Indoor Positioning Techniques and Systems , 2007, IEEE Transactions on Systems, Man, and Cybernetics, Part C (Applications and Reviews).

[21]  Hassane Alla,et al.  Discrete, continuous, and hybrid Petri Nets , 2004 .

[22]  Wil M.P. van der Aalst,et al.  Process mining with the HeuristicsMiner algorithm , 2006 .

[23]  Wil M. P. van der Aalst,et al.  Process mining: a research agenda , 2004, Comput. Ind..

[24]  Wil M. P. van der Aalst,et al.  Service Mining: Using Process Mining to Discover, Check, and Improve Service Behavior , 2013, IEEE Transactions on Services Computing.