University of Canterbury Home
    • Admin
    UC Research Repository
    UC Library
    JavaScript is disabled for your browser. Some features of this site may not work without it.
    View Item 
    1. UC Home
    2. Library
    3. UC Research Repository
    4. UC Business School | Te Kura Umanga
    5. Business: Theses and Dissertations
    6. View Item
    1. UC Home
    2.  > 
    3. Library
    4.  > 
    5. UC Research Repository
    6.  > 
    7. UC Business School | Te Kura Umanga
    8.  > 
    9. Business: Theses and Dissertations
    10.  > 
    11. View Item

    The need for disruption in the credit ratings landscape : a model for machine learning computed credit ratings. (2022)

    Thumbnail
    View/Open
    Vasin, Maxim_Final PhD Thesis.pdf (7.538Mb)
    Vasin, Maxim_Appendix 1_RightsLink Printable License - Fig9.pdf (79.59Kb)
    Vasin, Maxim_Appendix 2_Toptal Re Contact Form Maxim Vasin Press.pdf (126.5Kb)
    Vasin, Maxim_Co-Authorship Form.pdf (168.7Kb)
    Type of Content
    Theses / Dissertations
    UC Permalink
    https://hdl.handle.net/10092/104964
    
    Thesis Discipline
    Accountancy
    Degree Name
    Doctor of Philosophy
    Collections
    • Business: Theses and Dissertations [446]
    Authors
    Vasin, M. V.
    show all
    Abstract

    I present the results from the research on the topics of (1) credit ratings, which are usually provided by credit rating agencies, and (2) Artificial Intelligence and Machine Learning as a form of solving classification tasks, such as credit ratings, without the involvement of human experts. My research problem is stated as follows: to improve the solutions for the credit rating problem introduced by other credit rating agencies, I propose a rating system in the form of an expert system. Then I show that this system is more efficient than traditional rating systems on different hold-out samples of large-scale, multi-period data for public nonfinancial corporate entities worldwide, and with respect to different forecasting horizons. I show that my rating system, which is based on an ensemble machine learning method, specifically Gradient Boosted Decision Trees, when applied to the rating process, outperforms incumbent rating systems on the accuracy-stability scale measured by a compound metric Index of the Quality of Ratings, which I develop and introduce.

    In the course of the research in addition to the topic of rating performance evaluation, I have included the comparison of market-implied ratings with fundamental ratings, ratings forecasting and replication, mapping of ratings of different providers to the universal scale, financial effects of qualitative ratings for the investors, the stability of ratings, and the cyclical effects of ratings. The novelty is in the amount of data that I used, including the number and diversification of the rated entities, also in the number of other rating providers involved in performance comparison tests and the number of optional models built and tested. I have shown performance results for different forecasting horizons. The complexity of the proposed model, its iterative revisions throughout the estimation periods, as well as mapping of ratings directly through the default ratios, also mark out my research.

    The significance of the research is in showing a more reliable, hi-tech, cost- and timeeffective solution for the problem of credit risk assessment for financial markets participants, who now rely upon the opinion of credit rating agencies. The key output of the research is therefore to re-imagine the credit ratings according to modern advances in finance, datascience, information technology and software. The results of my analysis can be used as a starting point or proxy for choosing the optimal rating agency for investor’s needs, as a stepby- step manual to develop a rating system, as a benchmark for the regulation of rating agencies, or when discussing the quality of ratings in academic and financial papers.

    Rights
    All Rights Reserved
    https://canterbury.libguides.com/rights/theses

    Related items

    Showing items related by title, author, creator and subject.

    • A machine learning examination of hydroxyl radical differences among model simulations for CCMI-1 

      Nicely, J.M.; Duncan, B.N.; Hanisco, T.F.; Wolfe, G.M.; Salawitch, R.J.; Deushi, M.; Haslerud, A.S.; Jöckel, P.; Josse, B.; Kinnison, D.E.; Klekociuk, A.; Manyin, M.E.; Marécal, V.; Morgenstern, O.; Murray, L.T.; Myhre, G.; Oman, L.D.; Pitari, G.; Pozzer, A.; Quaglia, I.; Revell, Laura E.; Rozanov, E.; Stenke, A.; Stone, K.; Strahan, S.; Tilmes, S.; Tost, H.; Westervelt, D.M.; Zeng, G. (Copernicus GmbH, 2020)
      Abstract. The hydroxyl radical (OH) plays critical roles within the troposphere, such as determining the lifetime of methane (CH4), yet is challenging to model due to its fast cycling and dependence on a multitude of ...
    • A machine learning examination of hydroxyl radical differences among model simulations for CCMI-1 

      Nicely JM; Duncan BN; Hanisco TF; Wolfe GM; Salawitch RJ; Deushi M; Haslerud AS; Jöckel P; Josse B; Kinnison DE; Klekociuk A; Manyin ME; Marécal V; Morgenstern O; Murray LT; Myhre G; Oman LD; Pitari G; Pozzer A; Quaglia I; Rozanov E; Stenke A; Stone K; Strahan S; Tilmes S; Tost H; Westervelt DM; Zeng G; Revell, Laura (Copernicus GmbH, 2020)
      The hydroxyl radical (OH) plays critical roles within the troposphere, such as determining the lifetime of methane (CH ), yet is challenging to model due to its fast cycling and dependence on a multitude of sources and ...
    • A machine-readable online database for rate coefficients in radical polymerization 

      Van Herck J; Harrisson S; Hutchinson RA; Junkers T; Russell, Greg (Royal Society of Chemistry (RSC), 2021)
      An online database created and curated by an IUPAC subcommittee is introduced. It is designed to act as central access point for finding reliable kinetic data on radical polymerizations. The database can be accessed via a ...
    Advanced Search

    Browse

    All of the RepositoryCommunities & CollectionsBy Issue DateAuthorsTitlesSubjectsThesis DisciplineThis CollectionBy Issue DateAuthorsTitlesSubjectsThesis Discipline

    Statistics

    View Usage Statistics
    • SUBMISSIONS
    • Research Outputs
    • UC Theses
    • CONTACTS
    • Send Feedback
    • +64 3 369 3853
    • ucresearchrepository@canterbury.ac.nz
    • ABOUT
    • UC Research Repository Guide
    • Copyright and Disclaimer
    • SUBMISSIONS
    • Research Outputs
    • UC Theses
    • CONTACTS
    • Send Feedback
    • +64 3 369 3853
    • ucresearchrepository@canterbury.ac.nz
    • ABOUT
    • UC Research Repository Guide
    • Copyright and Disclaimer