Credit Rating Agencies: Evolution or Extinction?

Abstract

Credit Rating Agencies (CRAs) have been around for more than 150 years. Their role evolved from mere information collectors and providers to quasi-official arbitrators of credit risk throughout the global financial system. They compiled information that -at the time- was too difficult and costly for their clients to gather on their own. After the 1929 big market crash, they started to play a more formal role. Since then, we see a growing reliance of investors on the CRAs ratings. After the global financial crisis of 2007, the CRAs became the focal point of criticism by economists, politicians, the media, market participants and official regulatory agencies. The reason was obvious: the CRAs failed to perform the job they were supposed to do financial markets, i.e. efficient, effective and prompt measuring and signaling of financial (default) risk. The main criticism was focusing on the “issuer-pays system”, the relatively loose regulatory oversight from the relevant government agencies, the fact that often ratings change ex-post and the limited liability of CRAs. Many changes were implemented to the operational framework of the CRAs, including public disclosure of CRA information. This is designed to facilitate unsolicited ratings of structured securities by rating agencies that are not paid by the issuers. This combined with the abundance of data and the availability of powerful new methodologies and inexpensive computing power can bring us to the new era of independent ratings: The not-for-profit Independent Credit Rating Agencies (ICRAs). These can either compete or be used as an auxiliary risk gauging mechanism free from the problems inherent in the traditional CRAs. This role can be assumed by either public or governmental authorities, national or international specialized entities or universities, research institutions, etc. Several factors facilitate today the transition to the ICRAs: the abundance data, cheaper and faster computer processing the progress in traditional forecasting techniques and the wide use of new forecasting techniques i.e. Machine Learning methodologies and Artificial Intelligence systems.