<![CDATA[Ceria Toys faces challenges in efficiently managing the inventory of electric bicycles, as product demand is influenced by factors such as market trends, seasons, and changing consumer preferences. To address this challenge, this research employs data mining techniques with the decision tree algorithm to predict product demand and assist in inventory management. The evaluation results of the predictive model show varying performance across product categories. The precision for the "Hot" category is 58.36%, while for the "Less Popular" category, it is 64.18%. The recall for the "Hot" category reaches 83.71%, but the recall for the "Less Popular" category is only 32.82%. Although the model performs better in predicting hot products, there is still room to improve the detection of less popular products. To enhance effectiveness, Ceria Toys can balance the dataset or adjust the model. With this information, the store can better prepare stock for hot products and optimize the management of less popular products. These steps are expected to maximize sales, reduce excess stock, and improve overall customer satisfaction.]]>
Copyrights © 2025
