محمد امينيان

Services to increase customer satisfaction, the design of intelligent systems for the optimal management of bank deposits has become increasingly important. This research focuses on the design and implementation of an intelligent recommender system for managing bank deposits. The proposed system utilizes machine learning algorithms and clustering techniques to provide optimized recommendations for deposit management. Initially, customer data from a bank was collected and preprocessed. Six classification algorithms, including Decision Tree, Random Forest, Support Vector Machine (SVM), Neural Networks, Gradient Boosting, and XGBoost, were eva‎luated. Ultimately, the XGBoost model was selected due to its superior accuracy. In the clustering phase, the K-Means algorithm was chosen for its high speed, ease of implementation, and effective performance. The optimal number of clusters, determined by the elbow method, was set to six. A case study was conducted on six time-deposit products from Bank Maskan, and the features related to these deposits were mapped to customer clusters with input from banking experts. The results showed that the designed recommender system can effectively help banks provide personalized services, ultimately leading to increased customer satisfaction.

سيستم توصيه‌گر , دادهكاوي , خوشه‌بندي , طبقه‌بندي , سپرده‌هاي بانكي

Recommender System , Data mining , Clustering , Classification , Bank Deposits

Mohammad Aminian

Dr. Saeed Mirzamohammadi