Predictive analytics in customer behavior: Anticipating trends and preferences Hamed GhorbanTanhaei, Payam Boozary * , Sogand Sheykhan, Maryam Rabiee, Farzam Rahmani, Iman Hosseini Amirkabir University of Technology, Department of Management, Science & Technology, Iran A R T I C L E INFO Keywords: Predictive analytics Customer behavior Trend prediction Support vector machines Random forest Logistic regression ABSTRACT In order to effectively manage their customers, businesses need to thoroughly analyze the costs and advantages associated with various alternative expenditures and investments and determine the most effective way to allocate resources to marketing and sales activities over time. Those in charge of making decisions will reap the benefits of decision support models that estimate the value of the customer portfolio and tie expenses to customers’ purchasing behavior. In the current work, various machine learning algorithms such as Decision Tree (DT), Random Forest (RT), Logistic Regression (LR), Support Vector Machines (SVM), and gradient boosting are used to predict customer behavior. The evaluation criteria considered in the work include precision, recall, F1-Score, and ROC-AUC. The accuracy values obtained for DT, RT, LR, SVM, and gradient boosting are 0.787, 0.806, 0.826, 0.826, and 0.823, respectively. The results emphasize RT and LR’s good performance, while the values of 0.620, 1, 0.766, and 0.878 for the precision, recall, F1-score, and ROC-AUC score outperform the rest. The novelty of this work lies in employing a comprehensive set of machine learning algorithms to predict customer behavior, with a particular emphasis on the superior performance of RF and LR models, as demonstrated by their high precision, recall, F1-score, and ROC-AUC values. 1. Introduction 1.1. Background In today’s business environment, firms must comprehend and forecast client behavior to enhance their marketing and sales tactics [22]. This study aims to utilize machine learning algorithms to monitor and forecast customer behavior, thereby aiding organizations in allocating resources and making informed decisions [7,41]. The new adaptive management attempts to be sensitive to local needs and to enable cooperation among diverse stakeholders [24]. This is in contrast to the work done in the past on scientific adaptive management [13]. In the dynamic landscape of modern business, understanding and anticipating customer behavior is paramount to success. The advent of predictive analytics has revolutionized how companies approach this challenge, offering a powerful toolkit to decipher patterns, trends, and preferences from vast datasets. By harnessing historical data and deploying sophisticated algorithms, businesses can comprehend the intricacies of customer behavior and forecast future actions [4]. This proactive approach enables * Corresponding author. E-mail address: Payam.boozary@aut.ac.ir (P. Boozary). Contents lists available at ScienceDirect Results in Control and Optimization journal homepage: www.elsevier.com/locate/rico https://doi.org/10.1016/j.rico.2024.100462 Received 19 April 2024; Received in revised form 15 June 2024; Accepted 9 September 2024 Results in Control and Optimization 17 (2024) 100462 Available online 13 September 2024 2666-7207/© 2024 The Author(s). Published by Elsevier B.V. This is an open access article under the CC BY-NC license (http://creativecommons.org/licenses/by-nc/4.0/).