PERANCANGAN MODEL PRODUCT BUNDLING UNTUK PT X MENGGUNAKAN TEKNIK DATA MINING

• Main Author: Maudisa Lastyo, Kayla
• Format: Final Project
• Language: Indonesia
• Online Access: https://digilib.itb.ac.id/gdl/view/56434
• Institution: Institut Teknologi Bandung

PT X is a private banking institution operating in Indonesia. As an attempt to continuously respond towards Retail Banking customers’ demands in the digital era, PT X has implemented a number of marketing strategies, one of them being product bundling. Product bundling is a strategy that combines multiple products or services as part of a single priced package, in order to increase the value offered to customers. With the high variety of products and services offered by PT X, an accurate and structured method is needed to decide which product satisfies the customers’ needs and increases their loyalty. Therefore, this research intends to build a model capable of deciding the most appropriate product combination for the product bundling strategy used by PT X. The research methodology used in this research is developed using the Cross Industry Standard Process for Data Mining (CRISP-DM) structure, utilizing k-modes clustering to identify customer groups with similar demographic characteristics, and association rule mining with Apriori algorithm to discover rules which show association between products that should be grouped into a bundle between the aforementioned customer groups. The developed model resulted in 7 clusters of Mass Banking customers, 6 clusters of Aspire customers, and 3 clusters of Premium Wealth clusters, with a combination of 2 products recommended for each cluster. After designing the model, an application prototype capable of model execution and outcome display is developed using Python programming language.