An Evaluation of Automated Credit Scoring System for Financial Services in Developing Countries

UIU Institutional Repository

    • Login
    View Item 
    •   UIU DSpace Home
    • School of Science and Engineering (SoSE)
    • Department of Computer Science and Engineering (CSE)
    • M.Sc Thesis/Project
    • View Item
    •   UIU DSpace Home
    • School of Science and Engineering (SoSE)
    • Department of Computer Science and Engineering (CSE)
    • M.Sc Thesis/Project
    • View Item
    JavaScript is disabled for your browser. Some features of this site may not work without it.

    An Evaluation of Automated Credit Scoring System for Financial Services in Developing Countries

    Thumbnail
    View/Open
    rebekasultana_012142005.pdf (481.6Kb)
    Date
    2018-02-26
    Metadata
    Show full item record
    Abstract
    As the world is dependent on monetary stuff, credit has become consequential in our way of life. Therefore, credit scoring has become a comprehensively practiced strategy that helps bank and other financial organizations to evaluate creditworthiness of a client who applied for loans. The core purpose of this research is to carry out a comprehensible assessment of automated credit scoring framework for monetary service applications. The study tries to recognize the major deciding factors for developing an automated system for credit scoring purposes. It suggested a set of features which will be better to use in constructing scoring model for our country. We gave priority on employment, applicant’s salary, previous loan history, purpose of loan, requested loan amount in the optimal feature set. It presents a comparative assessment identified with Statistical and Artificial Intelligence (AI) methods that are utilized for automated credit scoring system. Moreover, it helps us to be aware of most accepted and effective methods practiced in credit scoring system. After comparing different methods, we found Neural Networks and Genetic Programming has higher predictive ability. This analysis notified that there is no supreme statistical approach employed to construct credit scoring framework which works on all circumstances. This study revealed that enhancements are necessary (in the current credit scoring framework) to successfully address every single financial environment. Despite the fact that credit scoring is greatly in practice in developed countries, nevertheless in developing countries it is not executed in numerous financial administrations. By using credit scoring system in our country we can facilitate loans specially micro credits to people who are applied for loan. In this paper, few recommendations are provided for microfinance and micro-lender of developing countries. To actualize better credit scoring framework, few conceivable methodologies were suggested as well. Although, it has great prospect of determining reliability, however credit scoring management is due for a noteworthy overhaul.
    URI
    http://dspace.uiu.ac.bd/handle/52243/156
    Collections
    • M.Sc Thesis/Project [151]

    Copyright 2003-2017 United International University
    Contact Us | Send Feedback
    Developed by UIU CITS
     

     

    Browse

    All of DSpaceCommunities & CollectionsBy Issue DateAuthorsTitlesSubjectsThis CollectionBy Issue DateAuthorsTitlesSubjects

    My Account

    LoginRegister

    Copyright 2003-2017 United International University
    Contact Us | Send Feedback
    Developed by UIU CITS