<![CDATA[In the era of digitalization, data has become a crucial asset in strategic decision-making within the banking sector. Financial institutions face challenges in understanding customer preferences and behavior more personally when conducting product promotion campaigns. This research aims to analyze and uncover the influence patterns of job type and account balance on customer responses to bank campaigns using the Decision Tree algorithm. A data-driven analytical approach is needed to uncover hidden patterns from collected customer information. The Decision Tree algorithm was chosen for its ability to provide predictions and present decision-making logic in an easily understandable tree structure, as well as its flexibility in handling both categorical and numerical data. The simplified dataset focuses on the 'job' and 'balance' features, which are then processed using label encoding for categorical features. The model was trained using the fit method and evaluated using Accuracy, precision, recall, and F1-score metrics. The evaluation results show that the model's overall Accuracy reached 92%. For the 'yes' response class, recall reached 97% and precision 88%, indicating the model's good ability to identify potentially positive customers. Interpretation of the results from the Decision Tree structure explicitly indicates that job type and customer balance have different patterns of inclination towards marketing campaigns, where customers with high balances tend to respond positively. This research is expected to contribute to the development of a more accurate, effective, and efficient data-driven decision support system for marketing activities in the banking sector, based on the revealed influence patterns.]]>
