Fezeh Zahedi Fard - Department of Accounting and Management, Neyshabur Branch, Islamic Azad University
Mahdi Salehi - Assistant Professor, Department of Accounting Ferdowsi University of Mashhad, Mashhad

Going concern is a fundamental concept for the preparation of financial statements by management. This paper has employed a data mining approach for going concern prediction (GCP) and has applied Adaptive Network Based Fuzzy Inference Systems (ANFIS) based on feature selection method for GCP in Iranian firms, listed in Tehran Stock Exchange (TSE). For this purpose, at the first step, using the stepwise discriminant analysis (SDA) has opted the final variables from among of 42 variables and in the next stage, has applied 10-fold cross-validation to figure out the optimal model for one year ahead. The empirical test signifies that the ANFIS model reached 99.92 and 95.19 percent accuracy rates so as to train and hold-out data

ANFIS; data mining; feature selection; financial ratios; going concern prediction