Advertisement-Click-Through-Rate-prediction

The Internet has become the most prominent and accessible way to spread the news about an event or to pitch, advertise and sell a product globally. The success of any advertisement campaign lies in reaching the right class of target audience and eventually convert them as potential customers in the future. Search engines like Google, Yahoo are a few of the most used ones by the businesses to market their product. The look of the advertisement, advertisement position, the age and gender of the audience and the size of the advertisement are some of the key factors that are available for the businesses to tune. The businesses are predominantly charged based on the number of clicks that they receive for their advertisement while some websites also bill them with a fixed charge per billing cycle. This creates a necessity for the advertising platforms to analyse and study these influential factors to achieve the maximum possible gain through the advertisements. This project presents an advertisement click through rate prediction system that analyses several of the factors mentioned above to predict if an advertisement will receive a click or not. Here we have performed several data wrangling techniques in order to clean the data and visualized with respect to the target variable to make the data more accessible. We used the ensemble models and various classification models with hyperparameter tuning and achieved an ROC score of 0.93 and predicted the probability for an advertisement to receive a click form the user.