Forecasting Cell Phone Ownership among Children with TurkStat Micro Data: Comparative Performance of Machine Learning Models

Kamil Abdullah EŞİDİR

Fiscaoeconomia, 2025, issue 3

Abstract: In this study, we estimate children's mobile phone ownership and analyze the factors affecting mobile phone ownership among children using the micro data set of the Turkey Child Survey for 2022. RandomForest, XGBoost, Gradient Boosting, and Support Vector Machines (SVM) machine models are used in forecasting. The performance of the models was evaluated with Precision, Recall, F1 Score and ROC AUC metrics. The findings show that children's age and access to the internet have a significant impact on cell phone ownership. Machine learning models provided high accuracy values in terms of statistical metrics. The study found that machine learning models improve decision-making processes and provide effective tools for policymakers. Simultaneously, it has been demonstrated that they can be effectively utilized in the field of social sciences. The high accuracy rates achieved by the models demonstrate that data-driven policy development processes can be enhanced to become more effective and efficient.

Keywords: Machine Learning; Management Information Systems; Data Analysis; RandomForest; XGBoost (search for similar items in EconPapers)
JEL-codes: C45 C83 M10 (search for similar items in EconPapers)
Date: 2025
References: Add references at CitEc
Citations:

Downloads: (external link)
https://dergipark.org.tr/en/download/article-file/4406083

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:fis:journl:250314

DOI: 10.25295/fsecon.1594029

Access Statistics for this article

More articles in Fiscaoeconomia from Tubitak Ulakbim JournalPark (Dergipark)
Bibliographic data for series maintained by Emre Atsan ().