Machine Learning Approach to Identify Users Across Their Digital Devices

Abstract

This paper discusses methods to identify individual users across their digital devices as part of the ICDM 2015 competition hosted on Kaggle. The competition's data set and prize pool were provided by http://www.drawbrid.ge/ in sponsorship with the ICDM 2015 conference. The methods described in this paper focuses on feature engineering and generic machine learning algorithms like Extreme Gradient Boosting (xgboost), Follow the Reguralized Leader Proximal etc. Machine learning algorithms discussed in this paper can help improve the marketer's ability to identify individual users as they switch between devices and show relevant content/recommendation to users wherever they go.