Towards Meta-learning over Data Streams (Abstract)

Modern society produces vast streams of data. Many stream min-ing algorithms have been developed to capture general trends in these streams, and make predictions for future observations, but relatively little is known about which algorithms perform particularly well on which kinds of data. Moreover, it is possible that the characteris-tics of the data change over time, and thus that a different algorithm should be recommended at various points in time. Figure 1 illustrates this. As such, we are dealing with the Algorithm Selection Prob-lem [9] in a data stream setting. Based on measurable meta-features from a window of observations from a data stream, a meta-algorithm is built that predicts the best classifier for the next window. Our re-sults show that this meta-algorithm is competitive with state-of-the-art data streaming ensembles, such as OzaBag [6], OzaBoost [6] and Leveraged Bagging [3]. We first construct a meta-dataset consisting of 49 data streams