Throughout the world, banking institutions employ diverse marketing strategies to advertise their products, gain new customers and/or retain the old ones. Telemarketing is one such method utilized by banks where individual customers are contacted by bank representatives with offers. The work undertaken in the project deals with finding solution to such problems which may help to re-design telemarketing strategies. This can be done when telemarketing strategies are based on data science and machine learning methods which can predict the outcome- whether a customer will buy the product or not. The work focuses on the various aspects of the dataset and endeavors to come up with a structured approach to derive proper insights from the data that would help in solving problems which are similar to this. In the end extensive comparative analysis is presented to aid in the understanding of different classification algorithms and various performance parameters that were employed for this problem.