Algorithms to optimize advertising strategies

Abstract

This paper evaluates different Machine Learning models which the aim to find out good algorithm for predicting conversion rate in the e-commerce. Several models have been used and compared on the basis of different Data Mining methods and algorithm (Naïve Bayes, K-Nearest Neighbors, Decision Tree, Logistics Regression, Random Forest, and Support Vector Machine). To handle the imbalance in the data, we use Confusion Matrix to evaluate the result beside the accuracy and conversion rate. For the modeling examples we used Mathlab analytical tool and introduced the Python language.