Effects of Capital Market Cycle on Behavior of Prediction Patterns of Financial Distress

Abstract

This study aimed to investigate the effectiveness of capital market cycle on behavior of financial distress predicting patterns. In this study, the information of 211 distressed firms, selected by certain distress criteria, along with 211 healthy firms listed in the Tehran Stock Exchange in the period 2006-2015 have been used. The model estimation by the use of 35 selected indices in the two periods of capital market recession and expansion was carried out. In this study, Hodrich-Prescott Filter for determining capital market cycle and Logistic Regression and Support Vector Machine models for predicting financial distress were used. The results showed that the behavior of financial distress predicting patterns are influenced by capital market cyclical variation in recession and expansion periods, but the influences are different in application of explaining variables and in predicting ability in the periods of recession and expansion. Also, the prediction ability in Support Vector Machine model is more than that in Logistic Regression model.

Keywords

• capital market cycle
• financial distress
• logistic regression
• support vector machine