Presenter: Jun-Yi Wu Authors: Philippe du Jardin, Eric Séverin

Predicting corporate bankruptcy using a self-organizing map: An empirical study to improve the forecasting horizon of a financial failure model Presenter: Jun-Yi Wu Authors: Philippe du Jardin, Eric Séverin 國立雲林科技大學 National Yunlin University of Science and Technology 2011 DSS

Outline • Motivation • Objective • Methodology • Experiments • Conclusion • Comments

Motivation • Most prediction models fail to forecast accurately the occurrence of failure beyond 1 year, and their accuracy tends to fall as the prediction horizon recedes. • Prediction rates are rather good one year before failure, but less so as the horizon recedes to two and three years.

Objective • To use what some researchers have called the “trajectory of corporate collapse” to examine another way of estimating the changes in firms' financial health. • To propose a new way of using a Kohonen map to improve model reliability.

Methodology

Experiments

Conclusion • To propose a new way of assessing a company’s financial health. • To use what we called “trajectories”, and a Kohonen map to quantize such trajectories, to measure it over time, rather than at a given moment in time. • To compared the predictive ability of these trajectories to that of modeling methods traditionally used to design financial failure models. 12

Comments • Advantage • Many experiments • Application • Forecasting horizon • Financial failure prediction 13

Presenter: Jun-Yi Wu Authors: Philippe du Jardin, Eric Séverin