The rapid development of information and communication technology has driven the need for information services that are more relevant and adaptive to user behaviour. This research aims to integrate data analytics in the study of user behaviour to support the development of effective information services. The dataset used is Kaggle's Online Retail Dataset, which includes sales transaction data of online retail companies in the UK from December 2010 to December 2011. The analysis was conducted through customer segmentation using K-Means Clustering algorithm and predictive analysis with Association Rule Mining. The segmentation results successfully grouped customers into four main clusters, namely loyal customers, potential customers, passive customers, and low-spending customers. Model evaluation showed optimal performance with an accuracy rate of 85%, precision of 82%, recall of 78%, and F1-Score of 80%, and Silhouette Score of 0.62, indicating effective customer segmentation. The findings prove that the application of data analytics can provide deep insights into customer behaviour and support the development of more personalised and adaptive information services. This research is expected to be a reference in designing data-driven information service development strategies in various sectors.
