Research Article
An Investigation of Ensemble and Explainable Machine Learning Models for Consumer Price Index Prediction in Ethiopia: Evidence from 1990-2023
Issue:
Volume 12, Issue 3, September 2026
Pages:
53-63
Received:
9 July 2026
Accepted:
23 July 2026
Published:
17 August 2026
DOI:
10.11648/j.ijdst.20261203.11
Downloads:
Views:
Abstract: A plenty of research investigations have demonstrated the pivotal role that the consumer price index (CPI) plays in the comprehensive assessment and understanding of inflationary trends within an economy. For prediction of consumer price index, researchers have used a variety of empirical methodologies and sophisticated statistical techniques, each of which come up with inherent challenges regarding their generalizability. To solve issues with generalizability, researchers developed artificial intelligence and machine learning. In this work, the sophisticated machine learning models such as decision tree (DT), random forest (RF), and gradient boosting (GB)s have integrated together to develop super learner machine learning to enhance the predictive capabilities concerning the consumer price index robustly. To ensure the optimization of these models, rigorous methodologies such as K-fold cross-validation and an extensive grid search for hyperparameter tuning are meticulously applied to refine the model's performance. The efficiency and predictive performance of the proposed super learner model are then critically compared with those of other base models, thereby establishing a benchmark for assessing improvements in predictive accuracy. Remarkably, the suggested super learner model demonstrated superior prediction capabilities, achieving highest coefficient of determination (R2) of 98.3%, with the lowest mean absolute error of 2.89%, a mean absolute percentage error of 2.60%, and a root mean square error of 3.46%. Moreover, the interpretability of the model's predictions is significantly explained through the application of Shapley additive explanations. This method explains the essential factors that influence the consumer price index in the context of Ethiopia. The super learner model that has been developed possesses the versatility and accuracy necessary for application across various economic sectors, enabling researchers and practitioners to predict dependent variables with both precision and efficiency, thus facilitating informed decision-making in financial planning.
Abstract: A plenty of research investigations have demonstrated the pivotal role that the consumer price index (CPI) plays in the comprehensive assessment and understanding of inflationary trends within an economy. For prediction of consumer price index, researchers have used a variety of empirical methodologies and sophisticated statistical techniques, each...
Show More
Research Article
Machine Learning Approach to Assessment of Nutritional Status of Children with Cardiac Disease in Ethiopia
Tayu Nigusie Abebe*
,
Abdisa Jura Hunduma
Issue:
Volume 12, Issue 3, September 2026
Pages:
64-74
Received:
1 August 2026
Accepted:
4 September 2026
Published:
22 September 2026
DOI:
10.11648/j.ijdst.20261203.12
Downloads:
Views:
Abstract: Nutritional status is an important determinant of health outcomes among children with cardiac disease, yet identifying children at risk of poor nutritional status remains challenging. Machine learning methods may provide useful tools for identifying important predictors and improving the classification of nutritional status in pediatric cardiac patients. The main objective of the study is to predict the nutritional status of children with cardiac disease using various machine learning methods, such as decision tree, logistic regression, random forest, support vector machine, and eXtreme Gradient Boosting. The predictive performance of each machine learning method was evaluated based on precision, accuracy, recall, f1 score, and the Kappa statistics value. The results indicate that the eXtreme Gradient Boosting method is recommended for predicting children nutritional status with precision, accuracy, recall, f1 score, and kappa statistics values: 0.7812, 0.7995, 0.7799, 0.7884, and 0.6299, respectively. The features that determine the nutritional status of children with cardiac disease are ROSS/NYHA, types of cardiac disease, pulmonary hypertension, anemia, pneumonia, and residence. This research will assist policy makers and healthcare providers to develop a framework for implementing necessary interventions and care practices to prevent complications associated with nutritional status in cardiac patients.
Abstract: Nutritional status is an important determinant of health outcomes among children with cardiac disease, yet identifying children at risk of poor nutritional status remains challenging. Machine learning methods may provide useful tools for identifying important predictors and improving the classification of nutritional status in pediatric cardiac pat...
Show More
