Cost optimized hybrid system in digital advertising using machine learning

Abstract

Digital advertising or Internet marketing is the term used to describe the process of advertising a product or brand through digital medium. It includes promotional advertisements and messages delivered through email, social media websites, search engines, mobile applications, web sites and affiliates programs. This work presents a system that solves the challenge of reaching correct people and optimizing the cost problem using various machine learning techniques. It also explains various research trends in predictive analytics, product pricing and targeting audience for digital advertising. Digital Advertising has captured wide attention from market. It is very powerful tool to reach correct people at correct time. Also it reduces the cost of broadcasting advertisement as the ad is displayed only to people who might be interested in the content. The interest prediction for audience targeting provides 89.44% accuracy using Naive Bayes classifier.