Case Study: Lead Conversion of Digital Marketing Data Using Predictive Analytics

Abstract

In view of the digital revolution and market dynamics, organizations started focusing more on developing strategies to find new customer segments through digital marketing mediums [1]. Acquiring new customers is difficult in any competitive industry. Also, the dynamic nature of growing digital marketing it even more challenging for organization to know right insights of data. In this context, it is essential for an organization to have knowledge about customers, attract more profitable customers and increase the bottom line. Information Technology (IT)-driven data analytics now has the capability to discover knowledge hidden inside very large amount of data to help in making business decisions which are customized to any organization needs. This paper is an attempt to create a machine learning model for customers training lead data which will help in identifying and predicting customer conversion and important attributes influencing lead conversion [2]. For the development analytical model CRISP methodology followed and explained each step in details. The Machine learning algorithm Logistic Regression technique applied to find to find the prospective leads. Used R for data Pre-processing, model development and prediction. In detail provided & discussed the steps involved in model development. For the model validation applied confusion matrix and ROC curve and outcome of the metrics discussed [3]. The advantage of using Machine learning model to get the better lead conversion and the benefits of the model discussed.