Shahid Beheshti University International Journal of New Political Economy 3060-6233 5 2 2024 10 01 The Evaluation Clustering Algorithm of Iran's Online Shopping Consumer Market 115 151 104717 10.48308/jep.5.2.115 EN Khatereh Khorasani Ph.D Candidate, Department of Management, Ahvaz Branch, Islamic Azad University, Ahvaz, Iran 0009-0001-8218-0425 Mansour Zaranezhad Professor, Department of Management, Shahid Chamran University of Ahvaz, Ahvaz, Iran. 0009-0001-8218-0425 Ghanbar Amirnezhad Associate Professor, Department of Management, South Tehran Branch, Islamic Azad University, Tehran, Iran. 0000-0001-7951-129X Ali Kangarani Farahani Assistant Professor, Department of Management, Ahvaz Branch, Islamic Azad University, Ahvaz, Iran 0000-0003-1895-3005 Journal Article 2024 01 11 With the fast growth of e-commerce and the emerging new retail trend—online and offline integration—it is important to recognize the target market and satisfy customers with different needs by analyzing their online search behaviors. Accordingly, in this study, several internet companies in Iran were investigated. The companies were divided into 5 categories based on their product type: food, cosmetics and luxury goods, industrial goods and their accessories, sanitary goods, detergents, and clothing. Then the trading data of the companies in a certain period are analyzed. The data of this research includes customer transaction records from 2018 to 2019, after removing incomplete and missing data, this number has reached 349 records or the company. According to the inquiry from the Ministry of Mining Industry and Trade, there are 51,307 internet shopping and service sites and 36,200,000 internet buyers in the country.Clustering provides a good understanding of customer needs and helps identify potential customers. Dividing customers into sectors also increases the company's income. It is believed that retaining customers is more important than finding new customers. For example, companies can employ marketing strategies specific to a particular segment to retain customers. This study first performed RFM analysis on transaction data and then applied clustering using k-means. Then the results obtained from the methods were compared with each other. https://jep.sbu.ac.ir/article_104717_d00c9cf8f4cef59b3909cebed7a2eba2.pdf