Doğan, OnurÖztayşi, BaşarFernandez-Llatas, Carlos2022-02-152022-02-1520201064-12461875-8967https://doi.org/10.3233/JIFS-179440https://hdl.handle.net/20.500.14034/20413th International FLINS Conference on Uncertainity Modeling in Knowledge Engineering and Decision Making (FLINS) -- AUG 21-24, 2018 -- Belfast, NORTH IRELANDThere are some studies and methods in the literature to understand customer needs and behaviors from the path. However, path analysis has a complex structure because the many customers can follow many different paths. Therefore, clustering methods facilitate the analysis of the customer location data to evaluate customer behaviors. Therefore, we aim to understand customer behavior by clustering their paths. We use an intuitionistic fuzzy c-means clustering (IFCM) algorithm for two-dimensional indoor customer data; case durations and the number of visited locations. Customer location data was collected by Bluetooth-based technology devices from one of the major shopping malls in Istanbul. Firstly, we create customer paths from customer location data by using process mining that is a technique that can be used to increase the understandability of the IFCM results. Moreover, we show with this study that fuzzy methods and process mining technique can be used together to analyze customer paths and gives more understandable results. We also present behavioral changes of some customers who have a different visit by inspecting their clustered paths.eninfo:eu-repo/semantics/closedAccessFuzzy c-means clusteringintuitionistic fuzzy setsprocess miningcustomer behaviorsindoor locationsBluetooth TrackingBehaviorTrajectoriesAlgorithmConference Object10.3233/JIFS-179440381675684N/AWOS:0005068562000672-s2.0-85078348795Q2