About | Contact Us | Register | Login
ProceedingsSeriesJournalsSearchEAI
Innovations and Interdisciplinary Solutions for Underserved Areas. 6th EAI International Conference, InterSol 2023, Flic en Flac, Mauritius, September 16-17, 2023, Proceedings

Research Article

Comparative Performance Evaluation of Random Forest, Extreme Gradient Boosting and Linear Regression Algorithms Using Nigeria’s Gross Domestic Products

Cite
BibTeX Plain Text
  • @INPROCEEDINGS{10.1007/978-3-031-51849-2_9,
        author={M. D. Adewale and D. U. Ebem and O. Awodele and A. Azeta and E. M. Aggrey and E. A. Okechalu and K. A. Olayanju and A. F. Owolabi and J. Oju and O. C. Ubadike and G. A. Otu and U. I. Muhammed and O. P. Oluyide},
        title={Comparative Performance Evaluation of Random Forest, Extreme Gradient Boosting and Linear Regression Algorithms Using Nigeria’s Gross Domestic Products},
        proceedings={Innovations and Interdisciplinary Solutions for Underserved Areas. 6th EAI International Conference, InterSol 2023, Flic en Flac, Mauritius, September 16-17, 2023, Proceedings},
        proceedings_a={INTERSOL},
        year={2024},
        month={2},
        keywords={Machine learning Random Forest Regressor XGboost Regressor Linear Regression Gross Domestic Product 5-fold cross-validation},
        doi={10.1007/978-3-031-51849-2_9}
    }
    
  • M. D. Adewale
    D. U. Ebem
    O. Awodele
    A. Azeta
    E. M. Aggrey
    E. A. Okechalu
    K. A. Olayanju
    A. F. Owolabi
    J. Oju
    O. C. Ubadike
    G. A. Otu
    U. I. Muhammed
    O. P. Oluyide
    Year: 2024
    Comparative Performance Evaluation of Random Forest, Extreme Gradient Boosting and Linear Regression Algorithms Using Nigeria’s Gross Domestic Products
    INTERSOL
    Springer
    DOI: 10.1007/978-3-031-51849-2_9
M. D. Adewale1,*, D. U. Ebem2, O. Awodele3, A. Azeta4, E. M. Aggrey1, E. A. Okechalu1, K. A. Olayanju1, A. F. Owolabi1, J. Oju1, O. C. Ubadike1, G. A. Otu1, U. I. Muhammed1, O. P. Oluyide1
  • 1: African Centre of Excellence on Technology Enhanced Learning
  • 2: Department of Computer Science
  • 3: Department of Computer Science, Babcock University
  • 4: Department of Software Engineering
*Contact email: ace22140007@noun.edu.ng

Abstract

Statistical methods like linear regression analysis are frequently used to create predictive analytic models. However, these methods have limitations that may affect the accuracy of the models. Using a typical dataset, this study seeks to accomplish two main goals. First, we fitted three predictive models, including linear regression analysis and two ensemble machine learning algorithms: Random Forest Regressor and Extreme Gradient Boosting Regressor. Secondly, we compared the performance of the models using a 5-fold cross-validation technique. The Random Forest Regressor outperformed the other models, with a Mean Absolute Error (MAE) of 10.138, Mean Square Error (MSE) of 139.729, Mean Absolute Percentage Error (MAPE) of 0.071, Root Mean Square Error (RMSE) of 11.821, and Normalised Mean Square Error (NMSE) of 13.782. These results suggest that the Random Forest Regressor is optimal for developing predictive models with similar datasets.

Keywords
Machine learning Random Forest Regressor XGboost Regressor Linear Regression Gross Domestic Product 5-fold cross-validation
Published
2024-02-02
Appears in
SpringerLink
http://dx.doi.org/10.1007/978-3-031-51849-2_9
Copyright © 2023–2025 ICST
EBSCOProQuestDBLPDOAJPortico
EAI Logo

About EAI

  • Who We Are
  • Leadership
  • Research Areas
  • Partners
  • Media Center

Community

  • Membership
  • Conference
  • Recognition
  • Sponsor Us

Publish with EAI

  • Publishing
  • Journals
  • Proceedings
  • Books
  • EUDL