<![CDATA[The modern retail sector, such as Transmart, faces difficulties in maintaining stable sales performance due to changes in consumer behavior, variations in product types, and differing store characteristics. To address this issue, this study proposes the use of the Extreme Gradient Boosting (XGBoost) machine learning algorithm to predict retail product sales volumes based on historical data from 2024–2025. The research utilizes the CRISP-DM framework, which consists of the following stages: Business Understanding, Data Understanding, Data Preparation, Modeling, Evaluation, and Deployment. The data cleaning and preprocessing processes involve several steps such as data cleaning, label encoding, feature selection, and data splitting with an 80:20 ratio. The model is further evaluated using the Mean Absolute Error (MAE) and the coefficient of determination (R²) metrics to assess prediction accuracy. The findings indicate that XGBoost is capable of effectively capturing sales patterns and generating accurate predictions to support decision-making strategies in the retail sector, particularly in stock planning and sales optimization. Therefore, the implementation of this data-driven predictive approach is expected to assist companies in enhancing operational management as well as improving competitiveness in the market.]]>
Copyrights © 2025
