Classification for accuracy and insight: A weighted sum approach

This research presents a classifier that aims to provide insight into a dataset in addition to achieving classification accuracies comparable to other algorithms. The classifier called, Automated Weighted Sum (AWSum) uses a weighted sum approach where feature values are assigned weights that are summed and compared to a threshold in order to classify an example. Though naive, this approach is scalable, achieves accurate classifications on standard datasets and also provides a degree of insight. By insight we mean that the technique provides an appreciation of the influence a feature value has on class values, relative to each other. AWSum provides a focus on the feature value space that allows the technique to identify feature values and combinations of feature values that are sensitive and important for a classification. This is particularly useful in fields such as medicine where this sort of micro-focus and understanding is critical in classification.

• Type: Conference
• Year: 2007
• Where: AUSDM
• Authors: Anthony Quinn, Andrew Stranieri, John Yearwood
• Keywords: AUSDM 2007, Data Mining, Feature Values, Weighted Sum, Weighted Sum Approach