Document Type : Original Article (Mixed)
Authors
1
Master of Business Administration graduate, Faculty of Humanities and Social Sciences, Shomal University, Amol, Iran
2
Associate Professor,Department of Management, Faculty of Humanities and Social Sciences, University of Shomal, Amol, Iran
3
Associate Professor,Department of Management, Faculty of Humanities and Social Sciences, Shomal University, Amol, Iran
4
Assistant Professor, Department of Management, Faculty of Humanities and Social Sciences, Shomal University, Amol, Iran
5
Department of Accounting, Faculty of Management and Accounting, College of Farabi, University of Tehran, Qom, Iran
10.22034/jnamm.2026.569389.1240
Abstract
Abstract
This research was conducted with the aim of predicting the products needed by e-commerce customers in Kalleh Meat Products Company using machine learning algorithms. The present study is applied in terms of purpose and was carried out with a quantitative approach. The data used included historical online purchase records of Kalleh Company's customers, comprising the variables "product price", "past purchase weight volume", "product type", "past purchase frequency", and "past purchase amount in Rials". To predict the "required product" as the output variable, four machine learning algorithms including Artificial Neural Network (ANN), Random Forest, Decision Tree, and K-Nearest Neighbors (KNN) were implemented and evaluated using Accuracy, Precision, Recall, and F1-Score metrics. The model evaluation results showed that the Artificial Neural Network algorithm achieved the highest scores across all evaluation metrics (Accuracy: 95.1%, Precision: 94.2%, Recall: 95.9%, and F1-Score: 95.5%), indicating that the Artificial Neural Network had the best performance in predicting the products needed by customers. The research models were implemented and validated in the Python 3.x programming environment using specialized libraries Scikit-learn and Keras based on TensorFlow. Subsequently, the Random Forest, Decision Tree, and K-Nearest Neighbors algorithms ranked next, respectively. Moreover, the feature importance analysis revealed that "past purchase weight volume" and "past purchase frequency" had the greatest impact on the model's prediction. The proposed model based on the Artificial Neural Network has the potential to be developed into an accurate and efficient product recommender system for Kalleh Company. Implementation of this model can lead to optimized inventory management, increased customer satisfaction, and ultimately sales growth for the company by accurately predicting future customer demand.
Keywords
Subjects
