Preprint of paper published in Data Mining and Knowledge Discovery Analyzing concept drift and shift from sample data Geoffrey I. Webb, Loong Kuan Lee, Bart Goethals, Franc ¸ois Petitjean the date of receipt and acceptance should be inserted later Abstract Concept drift and shift are major issues that greatly affect the accuracy and relia- bility of many real-world applications of machine learning. We propose a new data mining task, concept drift mapping — the description and analysis of instances of concept drift or shift. We argue that concept drift mapping is an essential prerequisite for tackling concept drift and shift. We propose tools for this purpose, arguing for the importance of quantita- tive descriptions of drift and shift in marginal distributions. We present quantitative concept drift mapping techniques, along with methods for visualizing their results. We illustrate their effectiveness for real-world applications across energy-pricing, vegetation monitoring and airline scheduling. Keywords Concept drift · concept shift · non-stationary distribution · visualisation · mapping 1 Introduction The world is dynamic, in constant flux. But machine learning usually creates static models from historical data. As the world changes, these models can grow increasingly unreliable. A distribution that changes is called non-stationary and a change in the distribution from which a model is learned is called concept drift. Geoffrey I. Webb Faculty of Information Technology, Monash University, Clayton, Vic, 3800, Australia E-mail: geoff.webb@monash.edu Loong Kuan Lee Faculty of Information Technology, Monash University, Clayton, Vic, 3800, Australia E-mail: lklee9@student.monash.edu Franc ¸ois Petitjean Faculty of Information Technology, Monash University, Clayton, Vic, 3800, Australia E-mail: francois.petitjean@monash.edu Bart Goethals Department of Mathematics and Computer Science, University of Antwerp, Belgium, and Faculty of Information Technology, Monash University, Clayton, Vic, 3800, Australia E-mail: goethals@gmail.com