An ants algorithm for bankruptcy prediction

Abstract

We propose a new ants algorithm (AA) for predicting bankruptcy of firms. Inspired by an AA for solving the travelling salesman problem, we present the choices made in order to transform it into the AA for bankruptcy prediction. We sketch the experimental set-up of our simulations and the origin of the data sets used. Next we show the most important results obtained. It turns out that in some cases our AA outperforms the classical multiple discriminant analysis method as introduced by Altman in his seminal paper (Altmann, 1968). We finalize by offering a discussion and a few conclusions