In many classification tasks training data have missing feature values that can be acquired at a cost. For building accurate predictive models, acquiring all missing values is often prohibitively expensive or unnecessary, while acquiring a random subset of feature values may not be most effective. The goal of active feature-value acquisition is to incrementally select feature values that are most cost effective for improving the model’s accuracy. We present an
approach that acquires feature values for inducing a classification model based on an estimation of the expected improvement in model accuracy per unit cost. Experimental results demonstrate that our approach consistently reduces the cost of producing a model of a desired accuracy compared to random feature acquisitions.




An Expected Utility Approach to Active Feature-Value Acquisition
- Prem Melville
- Raymond Mooney
- Foster Provost
- Maytal Saar-Tsechansky
- Venue: Fifth IEEE International Conference on Data Mining (ICDM-2005)
- 2005
- Type: Selected Conference Paper