The Problem of Variable Selection for Financial Distress: Applying Grasp Metaheuristics

We use GRASP strategies to solve the problem of selecting financial ratios to model and predict business failure. As a previous step, we use the GRASP procedure to select a subset of financial ratios that are then used to estimate a model of logistic regression to anticipate finanical distress on a sample of Spanish firms. The algorithm we suggest is designed “ad-hoc” for this type of variables. Reducing dimensionality has several advantages (Inza et al. 2000) such as reducing the cost of data acquisition, bette r understanding of the final classification model, and increasing the efficiency and the efficacy. The application of t he GRASP procedure t o preselect a reduced subset of financial ratios g enerated better results than those obtained directly by applying a model of logistic regression to the set of the 141 original financial ratios.