Autopilot: Simulating Changing Concepts in Real Data

An increasingly important area in supervised incremental learning is learning in the presence of changing concepts. Research into concept drift is hampered by the lack of availability of controllable `real life' datasets. In this paper we propose an approach for generating real life data over which we have control of the concept and can generate data exhibiting different types of concept drift. The approach uses a 3-D driving game to produce a data stream of instances describing how to drive around a track. The classification problem is learning the driving technique of the driver, which can be affected by changes in the driving environment causing changes to the concept. The paper gives illustrations of different types of concept drift and how standard concept drift handling techniques can adapt to the concept drift.