Tutorial 6

Data Reduction Methods in Data Mining

Abstract:

Data Mining is characterized by big data. While theoretically this may be advantageous, in practice the data may be too big. The dimensions can exceed the capacity of the prediction programs, or it may simply take too long to produce a solution. In this tutorial, after giving a short introduction to the field, we shall survey methods for reducing data to within acceptable bounds. Our emphasis shall be on practical methods that can be usefully applied in a wide range of situations independent of the prediction methods.