Mathematics and Computer Science

Permanent URI for this community

https://repository.elizadeuniversity.edu.ng/handle/20.500.12398/26

Browse

Browsing Mathematics and Computer Science by Author "Adebiyi, A A"

Now showing 1 - 2 of 2
  • Thumbnail Image
    Item
    Fraud prediction in loan default using support vector machine
    (IOP Conf. Series: Journal of Physics: Conf. Series, 2019) Eweoya, Ibukun; Adebiyi, A A; Azeta, A A; Amosu, Olufunmilola
    The concept of taking loan has been in existence since inception of the human race but it is now taking diverse dimensions. This spans through personal exchange of loans for repayment based on personal track records, enjoying loans as proceeds of daily contribution without collaterals, except for the banking sector that requests collaterals for official loans. The uniform occurrence of being unable to pay the debts and resulting in a default is evident to the level of bank closures and nations’ bankruptcy is experienced across board. With a large volume and variety of data, credit history judgment by man is inefficient; case-based, analogy-based reasoning and statistical approaches have been employed but the 21st century fraudulent attempts cannot be discovered by these approaches, hence; the machine learning approach using the support vector machine. This work employs a supervised learning approach based on machine learning to predict the possibility of a fraud in a loan application through hidden trends in data instead of giving loans which ordinarily should not be approved; past occurrences discovered through machine learning reveals risky loans and a possible fraud by humans in approvals that can result in a default. Machine learning approaches are able to detect fraudulent financial statements to avert business comatose
  • Thumbnail Image
    Item
    A Naive Bayes approach to fraud prediction in loan default
    (IOP Conf. Series: Journal of Physics: Conf. Series, 2019) Eweoya, Ibukun; Adebiyi, A A; Azeta, A A; Chidozie, F; Agono, F O; Guembe, B
    The essence of granting loans to individuals and corporate beneficiaries is to boost the economy while the lenders make profit from the interest that accrues to the lending. However, due to non-compliance to basic rules, fraud is prevalent in credit administration and traditional methods of detecting fraud have failed. Furthermore, they are time-consuming and less accurate. This work uses a supervised machine learning approach, specifically the Naïve Bayes to predict fraudulent practices in loan administration based on training and testing of labeled dataset. Previous works either predict credit worthiness or detect loan fraud but not predicting fraud in credit default. The approach employed in this work yielded 78 % accuracy.