OCA: Ordered Clustering-Based Algorithm for E-Commerce Recommendation System

The industry of e-commerce (EC) has become more popular and creates tremendous business opportunities for many firms. Modern societies are gradually shifting towards convenient online shopping as a result of the emergence of EC. The rapid growth in the volume of the data puts users in a big challenge when purchasing products that best meet their preferences. The reason for this is that people will be overwhelmed with many similar products with different brands, prices, and ratings. Consequently, they will be unable to make the best decision about what to purchase. Various studies on recommendation systems have been reported in the literature, concentrating on the issues of cold-start and data sparsity, which are among the most common challenges in recommendation systems. This study attempts to examine a new clustering technique named the Ordered Clustering-based Algorithm (OCA), with the aim of reducing the impact of the cold-start and the data sparsity problems in EC recommendation systems. A comprehensive review of data clustering techniques has been conducted, to discuss and examine these data clustering techniques. The OCA attempts to exploit the collaborative filtering strategy for e-commerce recommendation systems to cluster users based on their similarities in preferences. Several experiments have been conducted over a real-world e-commerce data set to evaluate the efficiency and the effectiveness of the proposed solution. The results of the experiments confirmed that OCA outperforms the previous approaches, achieving higher percentages of Precision (P), Recall (R), and F-measure (F).

Automated summary

The e-commerce industry has gained popularity, providing great business opportunities. As society leans towards online shopping convenience, the challenge of choosing the best products from a vast selection arises. To address this, a new clustering technique called the Ordered Clustering-based Algorithm (OCA) was proposed to reduce the impact of cold-start and data sparsity issues in e-commerce recommendation systems. Through a comprehensive review of data clustering techniques, OCA utilizes collaborative filtering to cluster users based on their preferences. Experimental results confirmed that OCA outperforms previous approaches, achieving higher percentages of Precision, Recall, and F-measure.