Research Article
Customer Segmentation Using the K-Means Clustering as a Strategy to Avoid Overstock in Online Shop Inventory
@INPROCEEDINGS{10.4108/eai.31-3-2022.2320688, author={Anindhita Dewabharata}, title={Customer Segmentation Using the K-Means Clustering as a Strategy to Avoid Overstock in Online Shop Inventory}, proceedings={Proceedings of the 1st International Conference on Contemporary Risk Studies, ICONIC-RS 2022, 31 March-1 April 2022, South Jakarta, DKI Jakarta, Indonesia}, publisher={EAI}, proceedings_a={ICONIC-RS}, year={2022}, month={8}, keywords={customer segmentation inventory overstock clustering k-means}, doi={10.4108/eai.31-3-2022.2320688} }- Anindhita Dewabharata
Year: 2022
Customer Segmentation Using the K-Means Clustering as a Strategy to Avoid Overstock in Online Shop Inventory
ICONIC-RS
EAI
DOI: 10.4108/eai.31-3-2022.2320688
Abstract
In recent years, the fast-growing internet technology has increased online activities, including online shopping. As a result, many companies doing business in this area successfully earn high profits. With the e-shopping success, many online shops compete to offer more variety products and let customers have more choices. However, if the seller does not know the prospective customers' purchase interests, offering more collections can increase the risk of overstock in inventory. Therefore, this study aims to reduce overstock by focusing on customer segmentation to determine purchase interests. First, as a case study, we use an online shop in one popular online marketplace in Indonesia. Then, we use the k-means algorithm clustering method to determine the segmentation of prospective customers. Finally, we recommend the inventory strategy for online shops to prioritize the top three prospective customers segment as the target market.