Research Article
A Hybrid Extreme Gradient Boosting Model for Credit Risk Modelling in the Presence of Inflation
Kenneth Kiprotich Langat*,
Anthony Gichuhi Waititu,
Philip Odhiambo Ngare
Issue:
Volume 10, Issue 3, June 2024
Pages:
41-48
Received:
12 July 2024
Accepted:
31 July 2024
Published:
22 August 2024
Abstract: The recent developments in the credit and banking industry brought by technology has led to increased competition and the rise of risks and challenges. Credit scoring is one of the core items that keeps this industry competitive and profitable. The creation of credit score models to assess the ability of the loan applicant to repay his or her loan remains an active field of research. Practically, the existing models ignore the factor of inflation in determining the credit score of a loan applicant. Inflation affect the performance of the financing institution negatively because it makes some of the borrowers struggle to repay the loan and so leading to some bad debts that might end up being written off. By integrating the inflation factor to the Extreme gradient boosting algorithm led to improved accuracy of the model. In this paper, a new model that uses the inflation rate of a specific region or country in the regularization term of the extreme gradient boosting model has been developed. The evaluation of the model is by comparison with the other common models using ROC, Accuracy, precision and recall. The developed model emerge the second best in terms of performance but better than the standard extreme gradient boosting model.
Abstract: The recent developments in the credit and banking industry brought by technology has led to increased competition and the rise of risks and challenges. Credit scoring is one of the core items that keeps this industry competitive and profitable. The creation of credit score models to assess the ability of the loan applicant to repay his or her loan ...
Show More
Research Article
Spatial Patterns and Risk Factors of Stunting Among Under-five Children in Kenya: A Multilevel and Spatial Analysis
Jackline Masit*,
Bonface Miya Malenje
,
Herbert Imboga
Issue:
Volume 10, Issue 3, June 2024
Pages:
49-60
Received:
16 May 2024
Accepted:
3 June 2024
Published:
26 August 2024
DOI:
10.11648/j.ijdsa.20241003.12
Downloads:
Views:
Abstract: Stunting remains a significant public health burden in sub-Saharan Africa and has far reaching consequences. Identifying the drivers of stunting and high burden regions is key to developing effective and targeted intervention strategies. The objective of the study was to identify the risk factors and explore spatial patterns of stunting across counties in Kenya. Secondary data from 2022 Kenya Demographic Health Survey (KDHS) was utilized. A total of 13,016 children aged between 0 - 59 months were included in the analysis. A multilevel logistic regression was applied to identify individual, household and community level determinants of stunting, spatial regression models to analyze spatial dependency and geographically weighted regression to explore spatial heterogeneity in the association between childhood stunting and county level determinants. In the multilevel logistic regression, Children from urban residence exhibited a significantly increased odds of stunting compared to those in rural areas (aOR = 1.25, 95% CI: 1.03 - 1.51, p = 0.02). Children from households categorized as poorer, middle, richer, and richest all exhibited significantly reduced odds of stunting compared to those from the poorest households. Children whose mothers had attained secondary education exhibit higher odds of stunting compared to those with no education (aOR = 1.32, 95% CI: 1.01 - 1.72, p = 0.04). Male children show significantly higher odds of stunting compared to females (aOR = 1.50, 95% CI: 1.33 - 1.70, p < 0.001). Children aged 12-23 months exhibit the highest odds of stunting (aOR = 2.65, 95% CI: 2.23 - 3.14, p < 0.001) compared to those aged < 6 months). Spatial analysis indicated that stunting prevalence varies geographically, with some areas exhibiting higher clustering. The geographically weighted regression further revealed that the influence of socioeconomic and climatic factors on stunting prevalence differed across locations highlighting the need for geographically targeted interventions.
Abstract: Stunting remains a significant public health burden in sub-Saharan Africa and has far reaching consequences. Identifying the drivers of stunting and high burden regions is key to developing effective and targeted intervention strategies. The objective of the study was to identify the risk factors and explore spatial patterns of stunting across coun...
Show More
