Customer Shopping Behavior Analysis Using RFID and Machine Learning Models

Abstract

Analyzing customer shopping habits in physical stores is crucial for enhancing the retailer–customer relationship and increasing business revenue. However, it can be challenging to gather data on customer browsing activities in physical stores as compared to online stores. This study suggests using RFID technology on store shelves and machine learning models to analyze customer browsing activity in retail stores. The study uses RFID tags to track product movement and collects data on customer behavior using receive signal strength (RSS) of the tags. The time-domain features were then extracted from RSS data and machine learning models were utilized to classify different customer shopping activities. We proposed integration of iForest Outlier Detection, ADASYN data balancing and Multilayer Perceptron (MLP). The results indicate that the proposed model performed better than other supervised learning models, with improvements of up to 97.778% in accuracy, 98.008% in precision, 98.333% in specificity, 98.333% in recall, and 97.750% in the f1-score. Finally, we showcased the integration of this trained model into a web-based application. This result can assist managers in understanding customer preferences and aid in product placement, promotions, and customer recommendations.

Classifications of Offline Shopping Trends and Patterns with Machine Learning Algorithms

“…Numerous algorithms are at one's disposal, and in this investigation, three were scrutinized: K-Nearest Neighbor (K-NN), Naive Bayes, and Artificial Neural Network (ANN) [11], [12]. Some previous research related to analysis and case studies namely, [13] in this study using the integration of iForest Outlier Detection, ADASYN data balancing, and Multilayer Perceptron (MLP) with an accuracy value of 97.778% these results can help store owners in understanding customer preferences in offline shopping. Research [14] shows the Artificial Neural Network (ANN) algorithm produces the highest accuracy value of 88% compared to the SVM and LR algorithms in processing customer perception data on online and offline shopping.…”

Radio-Frequency Identification Traceability System Implementation in the Packaging Section of an Industrial Company

“…Returning to the RFID reader devices, this component is the most complex because it is responsible not only for reading the information transmitted by the tags but also for communicating with external agents, i.e., transmitting the data received to the respective servers [20]. In turn, some of the obstacles to the adoption of this technology include the following aspects: the phenomenon of electromagnetic interference, in the sense that automatic identification and data collection through RFID, for its success, also depends on the type of objects in which the tags are inserted, where objects with metallic or liquid content may absorb the radio-frequency energy emitted by the reader, causing shorter transmission ranges or even the product not being identified; and, in terms of sustainability, the non-recycling and non-reuse of the tags may be a condition to be taken into consideration, so that if the tags are integrated into the object to be identified, it may not be possible to use them again, and the non-reuse of electronic waste (which includes these tags) may constitute a serious environmental risk [21]. In addition, the fact that the technology under study uses different operating frequencies in different parts of the world could make interconnection and compatibility between equipment significantly more difficult [22].…”