Cost-Sensitive Classification: Empirical Evaluation of a Hybrid Genetic Decision Tree Induction Algorithm

TLDR

The study introduces ICET, a cost‑sensitive classification algorithm. ICET evolves decision‑tree biases with a genetic algorithm whose fitness is the average classification cost, accounting for test and error costs. ICET outperforms EG2, CS‑ID3, IDX, and cost‑agnostic C4.5 on five medical datasets, remains robust under varied conditions, and its bias‑space search can be further improved.

Abstract

This paper introduces ICET, a new algorithm for cost-sensitive classification. ICET uses a genetic algorithm to evolve a population of biases for a decision tree induction algorithm. The fitness function of the genetic algorithm is the average cost of classification when using the decision tree, including both the costs of tests (features, measurements) and the costs of classification errors. ICET is compared here with three other algorithms for cost-sensitive classification - EG2, CS-ID3, and IDX - and also with C4.5, which classifies without regard to cost. The five algorithms are evaluated empirically on five real-world medical datasets. Three sets of experiments are performed. The first set examines the baseline performance of the five algorithms on the five datasets and establishes that ICET performs significantly better than its competitors. The second set tests the robustness of ICET under a variety of conditions and shows that ICET maintains its advantage. The third set looks at ICET's search in bias space and discovers a way to improve the search.