AN EARLY-WARNING SYSTEM FOR FINANCIAL PERFORMANCE PREDICTIONS

Abstract

The Self-Organizing Map (SOM) algorithm is used to assess comparatively the performance of non-banking financial institutions (NFIs) in Romania. The benchmarking model is represented by a-two-dimensional map (a SOM) that can be used to assess visually the performance of NFIs based on different performance dimensions. The SOM is further applied as an early-warning system (EWS) that would accurately forecast the NFIs’ future performance. The model is able to correctly predict NFIs’ performance movements. Finally, the SOM-based model is compared with a multivariate logit-based model proposed in previous research.