Sistem Rekomendasi Pada E-Commerce Menggunakan K-Nearest Neighbor


Chandra Saha Dewa Prasetya



Semakin banyaknya informasi produk yang ada di internet menghadirkan tantangan baik pembeli maupun pebisnis online dalam lingkungan e-commerce. Pembeli sering mengalami kesulitan saat mencari produk di internet karena banyaknya produk yang dijual di internet. Selain itu, pebisnis online sering mengalami kesulitan karena memiliki data mengenai produk, pembeli, dan transaksi yang sangat banyak, sehingga menyebabkan pebisinis online mengalami kesulitan untuk mempromosikan produk yang tepat pada target pembeli tertentu. Sistem rekomendasi dikembangkan untuk mengatasi permasalahan tersebut dengan berbagai metode seperti Collaborative Fltering, Content based, dan Hybrid. Metode Collaborative Fltering menggunakan data rating pembeli, Content Based menggunakan konten produk seperti judul atau deskripsi, dan Hybrid menggunakan keduanya sebagai dasar rekomendasi. Dengan menggunakan basis data graf, maka model sistem rekomendasi dapat dirancang dengan berbagai metode pendekatan sekaligus. Pada penelitian ini, algoritma k-Nearest Neighbor digunakan untuk menentukan top-n rekomendasi produk untuk setiap pembeli. Hasil dari penelitian ini metode Content Based mengungguli metode lain karena data yang digunakan sparse, yaitu kondisi dimana jumlah rating yang diberikan pembeli relatif sedikit terhadap banyaknya produk yang tersedia pada e-commerce.

Kata kunci: sistem rekomendasi, k-nearest neighbor, collaborative filtering, content based.


The growing number of product information available on the internet brings challenges to both customer and online businesses in the e-commerce environment. Customer often have difficulty when looking for products on the internet because of the number of products sold on the internet. In addition, online businessman often experience difficulties because they has much data about products, customers and transactions, thus causing online businessman have difficulty to promote the right product to a particular customer target. A recommendation system was developed to address those problem with various methods such as Collaborative Filtering, ContentBased, and Hybrid. Collaborative filtering method uses customer’s rating data, content based using product content such as title or description, and hybrid using both as the basis of the recommendation. In this research, the k-nearest neighbor algorithm is used to determine the top-n product recommendations for each buyer. The result of this research method Content Based outperforms other methods because the sparse data, that is the condition where the number of rating given by the customers is relatively little compared the number of products available in e-commerce.

Keywords: recomendation system, k-nearest neighbor, collaborative filtering, content based.

Teks Lengkap:

PDF (English)


ALKHATIB, K., NAJADAT, H., HMEIDI, I. & SHATNAWI, M.K.A. 2013. Stock price prediction using k-nearest neighbor (kNN) algorithm. International Journal of Business, Humanities and Technology, 3(3), 32-44.

CHOI, K., YOO, D., KIM, G. & SUH, Y. 2012. A hybrid online-product recommendation system: Combining implicit rating-based collaborative filtering and sequential pattern analysis. Electronic Commerce Research and Applications, 11(4), 309-317.

CHRISTOPHER, D.M., PRABHAKAR, R. & HINRICH, S.C.H.Ü.T.Z.E. 2008. Introduction to information retrieval. An Introduction To Information Retrieval, 151, 177.

DANISMAN, T. & ALPKOCAK, A. 2008, April. Feeler: Emotion classification of text using vector space model. In AISB 2008 Convention Communication, Interaction and Social Intelligence (Vol. 1, p. 53).

DESYAPUTRI, D.M., ERWIN, A., GALINIUM, M. & NUGRAHADI, D. 2013, October. News recommendation in Indonesian language based on user click behavior. In Information Technology and Electrical Engineering, 164-169.

HUANG, A. 2008, April. Similarity measures for text document clustering. In Proceedings of the sixth new zealand computer science research student conference (NZCSRSC2008), Christchurch, New Zealand. 49-56.

IMANDOUST, S.B. & BOLANDRAFTAR, M. 2013. Application of k-nearest neighbor (knn) approach for predicting economic events: Theoretical background. International Journal of Engineering Research and Applications, 3(5), 605-610.

KNIJNENBURG, B. P., WILLEMSEN, M. C., GANTNER, Z., SONCU, H., & NEWELL, C., 2012. Explaining the user experience of recommender systems. User Modeling and User-Adapted Interaction, 22(4-5), 441-504.

LUND, S.S. & TANDBERG, Ø. 2015. Design of a Hybrid Recommender System: A Study of the Cold-Start User Problem (Master’s thesis, NTNU).

MA, K. 2016. Content-based Recommender System for Movie Website.

MOBASHER, B. 2007. Data mining for web personalization. In The adaptive web, 90-135. Springer Berlin Heidelberg.

SAHAL, R., SELIM, S. & ELKORANY, A. 2014. An Adaptive Framework for Enhancing Recommendation Using Hybrid Techniques. International Journal of Computer Science & Information Technology, 6(2), 51.

SU, X. & KHOSHGOFTAAR, T.M. 2009. A survey of collaborative filtering techniques. Advances in artificial intelligence, 2009, 4.

TANG, J., HU, X. & LIU, H. 2013. Social recommendation: a review. Social Network Analysis and Mining, 3(4), 1113-1133.

VAINIONPÄÄ, I., & DAVIDSSON, S. 2014. Stock market prediction using the K Nearest Neighbours algorithm and a comparison with the moving average formula.

YANG, X., GUO, Y. & LIU, Y. 2013. Bayesian-inference-based recommendation in online social networks. IEEE Transactions on Parallel and Distributed Systems, 24(4), 642-651.

Yin, H., Sun, Y., Cui, B., Hu, Z. & Chen, L. 2013, August. Lcars: a location content- aware recommender system. In Proceedings of the 19th ACM SIGKDD international conference on Knowledge discovery and data mining, 221-229. ACM.

YUAN, Q., CONG, G. & LIN, C.Y. 2014, August. COM: a generative model for group recommendation. In Proceedings of the 20th ACM SIGKDD international conference on Knowledge discovery and data mining, 163-172. ACM.