The ability to predict customer behavior is a crucial aspect to modern banking, particularly in the realm of targeted marketing for term deposit subscriptions. This study develops a predictive model to enhance targeted marketing of bank term deposits by identifying customers who are more likely to subscribe. Using big data tools, such as Hadoop and Spark, the model addresses scalability, real-time processing, and feature selection to improve prediction accuracy. By incorporating advanced machine learning techniques, the project overcomes latency issues and ensures timely decision-making. The results aim to optimize marketing strategies, allowing banks to allocate resources more efficiently and improve conversion rates.