The rapid expansion of e-commerce platforms has led to the generation of vast amounts of consumer transaction data, creating a need for intelligent recommendation systems to enhance user experience and drive sales. This study presents a comparative analysis of five widely used recommendation algorithms—K-Nearest Neighbors (KNN) based User-Based Collaborative Filtering, Item-Based Collaborative Filtering, Apriori, FP-Growth, and ECLAT—applied to a grocery purchase dataset. The dataset consists of customer transaction records, which are preprocessed through data cleaning, transformation, and the construction of a user-item interaction matrix. Collaborative filtering techniques (KNN and Item-Based CF) are employed to generate personalized recommendations based on user similarity and item similarity, respectively. In contrast, association rule mining techniques (Apriori, FP-Growth, and ECLAT) are utilized to discover frequent itemsets and identify meaningful relationships between products. The performance of these algorithms is evaluated using key metrics such as accuracy, precision, recall, and processing time to assess both recommendation quality and computational efficiency. Experimental results indicate that FP-Growth and ECLAT outperform Apriori in terms of processing speed while maintaining strong association discovery capabilities. Among collaborative filtering approaches, Item-Based Collaborative Filtering demonstrates improved scalability and consistency compared to User-Based KNN. The findings highlight the strengths and limitations of each approach and emphasize the importance of selecting appropriate algorithms based on dataset characteristics and application requirements. This study contributes to the development of efficient and scalable recommendation systems, enabling e-commerce platforms to deliver personalized shopping experiences and optimize business outcomes.

This study evaluates the performance of multiple recommendation algorithms for analyzing consumer purchase behaviour in the grocery domain. Among the methods considered, FP-Growth achieved the highest accuracy along with the fastest processing time, making it highly suitable for real-time recommendation systems. ECLAT also demonstrated strong performance by efficiently generating frequent itemsets with lower computational cost compared to Apriori. Item-Based Collaborative Filtering showed better scalability and consistent performance than User-Based KNN, while KNN remained effective in delivering personalized recommendations based on user similarity. Apriori, although useful in identifying item associations, was comparatively slower due to its higher computational complexity. Overall, the results indicate that FP-Growth and ECLAT provide the best balance between accuracy and efficiency, whereas collaborative filtering techniques are more suitable for personalization tasks. The study highlights that the selection of an appropriate algorithm depends on factors such as dataset characteristics, scalability requirements, and the need for real-time processing in e-commerce environments.

1.M. Madanchian, “The Impact of Artificial Intelligence Marketing on E-Commerce Sales,” 2024. 2.I. Oktaviani, E. Purawanto, T. E. Triana, “Analysis of AI-Based Big Data for Strategic Decision-Making in E-Commerce,” 2024. 3. J. Nathalie, G. Jacqueline, N. A. Yusuf, and L. W. Ming, “Optimizing Digital Business Processes through Artificial Intelligence: A Case Study in E-Commerce Systems,” 2024. 4.P. Chugh and V. Jain, “Artificial Intelligence (AI) Empowerment in E-Commerce: A Bibliometric Voyage,” 2024. 5.G. Hinton and S. Thrun, “AI-Driven Models for Enhanced Healthcare, Social Analytics, and E-Commerce: Balancing Innovation with Performance and Ethics,” 2024. 6.Y. Amil, “The Impact of AI-Driven Personalization Tools on Privacy Concerns and Consumer Trust in E-Commerce,” 2024. 7.M. A. Raji, H. B. Olodo, T. T. Oke, et al., “E-Commerce and Consumer Behaviour: A Review of AI-Powered Personalization and Market Trends,” 2024. 8.S. K. Mohsin, “The Influence of AI-Driven Personalization on Consumer Decision Making in E-Commerce Platforms,” 2024. 9.J. C. Li, Y. Lin, and Y. C. Yang, “Extending the Theory of Planned Behaviour Model to Explain People’s Behavioural Intentions to Follow China’s AI-Generated Content Law,” 2024. 10.S. Aljarboa, “Factors Influencing the Adoption of Artificial Intelligence in E-Commerce by Small and Medium-Sized Enterprises,” 2024. 11.G. Singh, “Mapping Consumer Behaviour on E-Commerce Platforms through AI,” 2024. 12.E. Labib, “Artificial Intelligence in Marketing: Exploring Current and Future Trends,” 2024. 13.D. Oyekunle, U. O. Matthew, D. Preston, and D. Boohene, “Trust Beyond Technology Algorithms: A Theoretical Exploration of Consumer Trust and Behaviour in Technological Consumption and AI Projects,” 2024. 14.N. S. Ja’afar, N. Khan, V. O. K. Seng, and S. G. Obreja, “AI-Powered Digital Marketing: Elevating Brand Perception in the Event Industry,” 2024. 15.B. J. Keegan, S. Iredale, and P. Naudé, “Examining the Dark Force Consequences of AI as a New Actor in B2B Relationships,” 2023. 16.V. Dunka, “Enhancing E-Commerce with AI in Data Science: Techniques for Customer Segmentation, Personalized Recommendations, and Sales Forecasting,” 2023. 17.V. M. Reddy and L. N. Nalla, “The Future of E-Commerce: How Big Data and AI are Shaping the Industry,” 2023. 18.O. Odeyemi, O. A. Elufioye, N. Z. Mhlongo, et al., “AI in E-Commerce: Reviewing Developments in the USA and Their Global Influence,” 2023. 19.V. Vidhya, S. Donthu, L. Veeran, Y. P. Sai Lakshmi, and B. Yadav, “The Intersection of AI and Consumer Behaviour: Predictive Models in Modern Marketing,” 2023. 20.N. Singh and D. Adhikari, “AI-Driven Personalization in E-Commerce Advertising,” 2023. 21.R. T. D. Jatmikaa, V. Ratnasarib, and R. Nadlifanc, “Empowering Micro-Entrepreneurs through Artificial Intelligence: A Conceptual Framework for AI-Based Marketing,” 2023. 22.A. R. Gonçalves, D. Costa Pinto, P. Rita, and T. Pires, “Artificial Intelligence and Its Ethical Implications for Marketing,” 2023. 23.S. C. Necula and V. D. Păvăloaia, “AI-Driven Recommendations: A Systematic Review of the State of the Art in E-Commerce,” 2023. 24.C. Wang, S. F. Ahmad, E. M. Awwad, et al., “An Empirical Evaluation of Technology Acceptance Model for Artificial Intelligence in E-Commerce,” 2023. 25.S. P. S. Ho and M. Y. C. Chow, “The Role of Artificial Intelligence in Consumers’ Brand Preference for Retail Banks in Hong Kong,” 2023. 26.M. J. Castillo and H. Taherdoost, “The Impact of AI Technologies on E-Business,” 2023. 27.A. Go, L. Querejeta-Lomas, A. Almeida, et al., “Artificial Intelligence in Business-to-Customer Fashion Retail: A Literature Review,” 2023. 28.Y. Liu-Thompkins, S. Okazaki, and H. Li, “Artificial Empathy in Marketing Interactions: Bridging the Human-AI Gap in Affective and Social Customer Experience,” 2022. 29.S. Akter, Y. K. Dwivedi, S. S. Saji, et al., “Algorithmic Bias in Machine Learning-Based Marketing Models,” 2022. R. E. Bawack, S. F. Wamba, K. D. A. Carillo, and S. Akter, “Artificial Intelligence in E-Commerce: A Bibliometric Study and Literature Review,” 2022.

© 2025 International Journal of Engineering and Techniques (IJET).

Digital Object Identifier (DOI)

IJET assigns a unique DOI to every accepted article via Zenodo for persistent linking and citation. Your article’s DOI: https://doi.org/{{doi}}

Open DOI About Zenodo DOI

Close