Machine Learning Approach to Assess and Classify Customer's Ability to Purchase Term Plan

As the technologies are evolving the ways of treating the customers has changed drastically. The financial institution has leveraged them to target the appropriate customer. There are n numbers of ways or the technologies through which the customer needs can be analyzed and appropriate services can be recommended. Almost if we look back 5 years ago ,the task was very cumbersome and specific skilled persons were required to full fill the needs of customer and offer appropriate service like investing, banking, trading or SIP. In the current work we have targeted the Term deposit service for the customers and the customers has been segmented on the basis of various features, like age, job, education etc. Total 15 attributes has been considered to train the machine learning model and the parametric evaluation of the data has been done based on the different attributes Time (the length of the sales representative and potential customer's talk), Connection (the number of contacts made with the potential customer during the same marketing campaign), and Period (the month of the year) are the three attributes that our classifier considers to be most crucial. Decision Tree Classifier: The most accurate model to forecast whether or not a potential customer will sign up for a term deposit is the Gradient Boosting classifier. Reliability: 91.7%