Machine Learning Approach to Identify Users Across Their Digital Devices
Thakur Raj Anand, Oleksii Renov · 2015
This paper discusses methods to identify individualusers across their digital devices as part of the ICDM 2015 competition hosted on Kaggle. The competition's data set and prize poolwere provided by http://www.drawbrid.ge/ in sponsorship withthe ICDM 2015 conference. The methods described in this paperfocuses on feature engineering and generic machine learningalgorithms like Extreme Gradient Boosting (xgboost), Follow theReguralized Leader Proximal etc. Machine learning algorithmsdiscussed in this paper can help improve the marketer's abilityto identify individual users as they switch between devices andshow relevant content/recommendation to users wherever they go.