Identifying Product Bundle from Market Basket Analysis


  • Ashish Neupane Himalaya College of Engineering, Nepalgunj, Nepal
  • Bibek Dhakal Himalaya College of Engineering, Pokhara-4, Pokhara, Nepal
  • Bijay Aryal Himalaya College of Engineering, Kaligandaki-1, Gulmi, Nepal
  • Nabin Kandel Himalaya College of Engineering, Kathekhoal-6, Baglung, Nepal



Bundles, Clustering


Bundling has emerged as an increasingly popular promotional strategy, offering numerous benefits to buyers and sellers and aligning perfectly with the goals of a transaction process. From the consumer’s perspective, bundling enables them to enjoy substantial savings, with an average percentage off, when purchasing a bundle package at a discount price. This significant cost reduction serves as a critical motivator for embracing bundling. Furthermore, bundling allows customers to streamline their purchasing experience by minimizing search costs. They can conveniently find all the desired products and services in a comprehensive package offered by the seller. Additionally, bundles are favorable to some individuals due to their ability to mitigate compatibility risks between various components. From the seller’s view, adopting bundling can lead to increased sales and a broader customer base. Bundling facilitates the attraction of buyers, while simultaneously raising awareness and acceptance of newly released products...The scope of this project, titled "Identifying Product Bundles from Sales Data using Market Basket," a highly performant model has been developed to aid in the identification of product bundles and market basket determination. Recognizing the multitude of prediction challenges during product sales, this project utilizes historical sales data to predict optimal product bundles. Leveraging a dataset obtained from Instacart, the project incorporates clustering and analysis processes. By thoroughly analyzing the data, the model can predict the most effective product bundles, enabling the selling company to boost its sales potential. This project specifically caters to e-commerce websites seeking to address product bundling and market basket analysis challenges. It provides a valuable platform for applying various techniques to solve problems associated with product bundling, generating comprehensive theoretical and practical resources for research-based studies. Ultimately, this project empowers businesses to make more reliable predictions about the future, enhancing their decision-making processes.  


Download data is not yet available.




How to Cite

Neupane, A., Dhakal, B., Aryal, B., & Kandel, N. (2023). Identifying Product Bundle from Market Basket Analysis. International Journal on Engineering Technology, 1(1), 129–138.