Abstract

Using artificial neural networks (ANN) and ordinal regression (OR) as alternative methods to predict Commercial Mortgage‐backed Securities (CMBS) credit ratings, we examine the role that various financial and industry‐based variables have on CMBS credit ratings issued by Standard and Poor's from 1999–2005. Our OR results show that rating agencies use only a subset of variables they describe or indicate as important to CMBS credit rating as some of the variables they use were statistically insignificant. Overall, ANN show superior results to OR in predicting CMBS credit ratings. Santrauka Sisteminant komercine hipoteka užtikrintų vertybinių popierių prekybos sandorius, svarbiausias tikslas – gauti aukštą kredito reitingą, nes tai daro poveikį pelningumui ir emitento sėkmei. Kredito reitingų agentūros teigia, kad jų vertinimai išreiškia kiekvienos agentūros nuomonę apie potencialią emitento nemokumo riziką ir daugiausia remiasi emitento gebėjimo bei noro grąžinti savo skolą analize, kurią atlieka komitetas, taigi tyrinėtojams jų reitingų kiekybiškai replikuoti nepavyktų. Tačiau tyrinėtojai replikavo obligacijų reitingus, remdamiesi prielaida, kad finansiniai koefi cientai turi daug informacijos apie įmonės kredito riziką. Prognozuodami komercine hipoteka užtikrintų vertybinių popierių reitingus, kaip alternatyvius metodus naudojame dirbtinius neuroninius tinklus ir ranginę regresiją. Ranginės regresijos rezultatai rodo, kad reitingų agentūros naudoja tik tą kintamųjų poaibį, kuriuos jos apibūdina arba nurodo kaip svarbius komercine hipoteka užtikrintų vertybinių popierių reitingui, nes kai kurie iš naudojamų kintamųjų statistiškai nereikšmingi. Apskritai dirbtinių neuroninių tinklų rezultatai, prognozuojant komercine hipoteka užtikrintų vertybinių popierių reitingus, geresni nei ranginės regresijos.

Highlights

  • Commercial mortgage-backed securities (CMBSs) have expanded the investment realm of both investors and issuers

  • Between 2001 and 2004, Listed Property Trusts (LPTs) issued CMBSs worth over $3.7B via 27 issues and bonds worth over $4.8B via 40 issues (Newell, 2005). This increased participation can partly be attributed to the high demand by institutional investors, mainly superannuation funds, for shares and bonds issued by LPTs in comparison to investing in direct property

  • Our motivation for the specified hypothesis stems from Fabozzi and Jacob (1997) and Geltner and Miller (2001), among others, who state that loanto-value ratio (LTV) and debt service coverage ratio (DSCR) are the two mostly widely used commercial mortgage underwriting criteria

Read more

Summary

INTRODUCTION

Commercial mortgage-backed securities (CMBSs) have expanded the investment realm of both investors and issuers. They are seen as an alternative to direct investment in property offering advantages of liquidity, diversification, and being an alternative investment to other financial investments. Corporate bond ratings inform the public of the likelihood of an investor receiving the promised principal and interest payments associated with the bond issue (Shin and Han, 2001). This study investigates several aspects of the use of ANN as a tool for predicting credit ratings of Australian CMBSs. Tests are undertaken to compare the predictive power of ANN models and ordinal regression models.

AN OVERVIEW OF THE AUSTRALIAN COMMERCIAL MORTGAGE-BACKED SECURITIES MARKET
PRIOR RESEARCH IN ARTIFICIAL NEURAL NETWORK SYSTEMS
Artificial neural network systems in real estate research
Artificial neural network systems in corporate bond rating research
Hypotheses
Description of OR model
Description of ANN model
Selection of variables
EMPIRICAL RESULTS AND ANALYSIS
Prediction accuracy analysis
Variable contribution analysis
Full Text
Published version (Free)

Talk to us

Join us for a 30 min session where you can share your feedback and ask us any queries you have

Schedule a call