EVALUATING CLASSIFICATION ALGORITHMS FOR PREDICTING SOCIAL PROJECT APPROVAL IN POST-CONFLICT REGIONS

Yasemin Şirin Eryoldaş; Jamil Hallak

TR EN

ÇATIŞMA SONRASI BÖLGELERDE SOSYAL PROJE ONAYINI TAHMİN ETMEK İÇİN SINIFLANDIRMA ALGORİTMALARININ DEĞERLENDİRİLMESİ

Abstract

İhtiyaç sahibi bireylere destek olmak ve krizden etkilenen bölgelerde yoksulluğu azaltmak için Sosyal Projelerin (SP’ler) kullanılması giderek artan bir zorunluluk hâline gelmiştir. Bu çalışma, çatışma sonrası bölgelerde sosyal projelerin seçilme sonuçlarını tahmin etmek amacıyla makine öğrenmesi sınıflandırma algoritmalarının uygulanmasını incelemektedir. Suriye’nin kuzeyinde yürütülen ve 274 aday projeyi içeren bir karar verme çalışmasından elde edilen veri seti temel alınmış; finansal, teknik, mekânsal ve sosyal ölçütleri kapsayan dokuz proje özelliği tahmin değişkeni olarak kullanılmıştır. Altı sınıflandırma algoritması değerlendirilmiştir: Lojistik Regresyon, Simple Logistic, Naive Bayes, IBk (en yakın komşular – KNN), J48 karar ağacı ve Çok Katmanlı Algılayıcı (Multilayer Perceptron). Model performansını ölçmek için doğruluk oranı, Kappa istatistiği, ortalama mutlak hata (MAE) ve kök ortalama kare hata (RMSE) kullanılmıştır. Sonuçlar, Simple Logistic ve Naive Bayes algoritmalarının en yüksek doğruluk ( %98,18 ) ve Kappa (0,963) değerlerine ulaştığını, Lojistik Regresyonun ise en düşük MAE değerine sahip olduğunu göstermektedir. Bu çalışma, Kuzey Suriye’den elde edilen gerçek bir STK arşiv veri setini kullanarak geleneksel ÇKKV değerlendirmesini tamamlayıcı nitelikte, proje düzeyinde sosyal proje seçimine yönelik makine öğrenmesi tabanlı bir karar destek aracı geliştirmesiyle literatüre katkı sunmaktadır.

Keywords

EVALUATING CLASSIFICATION ALGORITHMS FOR PREDICTING SOCIAL PROJECT APPROVAL IN POST-CONFLICT REGIONS

Abstract

Implementing Social Projects (SPs) has become crucial in crisis-affected areas for supporting disadvantaged groups and decreasing poverty. The use of classification algorithms to forecast social project selection outcomes in post-conflict areas is examined in this study. Nine project variables, including financial, technical, spatial, and social aspects, were employed as predictive features based on a dataset that included 274 possible projects in Northern Syria. Logistic Regression, Simple Logistic, Naive Bayes, IBk (k-Nearest Neighbors), J48 decision tree, and Multilayer Perceptron were the six classification techniques that were assessed. Model performance was evaluated using accuracy, the Kappa statistic, mean absolute error (MAE), and root mean square error (RMSE). The results show that Simple Logistic and Naive Bayes obtained the best accuracy (98.18%) and Kappa (0.963), and Logistic Regression had the lowest MAE. The novelty of this study lies in using a real archival non-governmental organization (NGO) dataset from northern Syria to develop a machine learning-based decision-support framework for project-level social project selection, thereby providing a practical complement to traditional multi-criteria decision-making MCDM methods.

Keywords

References

Abdulla, A., & Baryannis, G. (2024). A hybrid multi-criteria decision-making and machine learning approach for explainable supplier selection. Supply Chain Analytics, 7, 100074. https://doi.org/10.1016/j.sca.2024.100074
Abidi, H., de Leeuw, S., & Klumpp, M. (2014). Humanitarian supply chain performance management: A systematic literature review. Supply Chain Management: An International Journal, 19(5–6), 592–608.
Altıntaş, F. F. (2025). A current approach to objective criteria weighting: The Hellinger distance method (HDM). Kahramanmaraş Sütçü İmam Üniversitesi Mühendislik Bilimleri Dergisi, 28, 1861–1885. https://doi.org/10.17780/ksujes.1729297
Alturki, I., & Lee, S. (2024). A systematic survey of multicriteria models in humanitarian logistics. International Journal of Disaster Risk Reduction, 102, 104209. https://doi.org/10.1016/j.ijdrr.2023.104209
Banerjee, A., & Duflo, E. (2013). Poor economics: A radical rethinking of the way to fight global poverty. Society and Economy, 35(4), 573–587.
Bishop, C. M. (2006). Pattern recognition and machine learning. Springer.
Brück, T. (2020). The economics of fragility and conflict. Oxford University Press.
Brück, T., d’Errico, M., & Pietrelli, R. (2019). The effects of violent conflict on household resilience and food security: Evidence from the 2014 Gaza conflict. World Development, 119, 203–223.

Cover, T., & Hart, P. (1967). Nearest neighbor pattern classification. IEEE Transactions on Information Theory, 13(1), 21–27.
Dang, Q., Pham, T., & Nguyen, H. (2021). Root mean square error in regression analysis. International Journal of Advanced Computer Science and Applications, 12(5), 85–92.
de Souza, D. G. B., dos Santos, E. A., Soma, N. Y., & da Silva, C. E. S. (2021). MCDM-based R&D project selection: A systematic literature review. Sustainability, 13(21), 11626. https://doi.org/10.3390/su132111626
Derse, O. (2022). DEMATEL tabanlı TOPSIS yöntemi ve küme kapsama modeli ile afet lojistiği için depo yeri seçimi: Ege Bölgesi örneği. Kahramanmaraş Sütçü İmam Üniversitesi Mühendislik Bilimleri Dergisi, 25(4), 702–713. https://doi.org/10.17780/ksujes.1159925
Dou, J., Zhang, L., & Wang, Y. (2023). Performance metrics in machine learning: An overview. Journal of Physics: Conference Series, 2420, 012051.
Hallak, J., Özkurt, P., & Ağduk, S. (2022). Social entrepreneurial projects evaluation in crisis areas through multi-criteria decision making. Avrupa Bilim ve Teknoloji Dergisi, (41), 457–470.
Haykin, S. (2009). Neural networks and learning machines (3rd ed.). Pearson.
Jordan, M. I., & Mitchell, T. M. (2015). Machine learning: Trends, perspectives, and prospects. Science, 349(6245), 255–260.
Kocaman, H., & Asan, U. (2026). Integration modes between MCDM methods and machine learning algorithms: A structured approach for framework development. Mathematics, 14(1), 33. https://doi.org/10.3390/math14010033
Mediouni, A., & Cheikhrouhou, N. (2019). Expert selection for humanitarian projects development: A group decision making approach with incomplete information relations. IFAC-PapersOnLine, 52(13), 1943–1948. https://doi.org/10.1016/j.ifacol.2019.11.487
Menard, S. (2002). Applied logistic regression analysis (2nd ed.). SAGE Publications.
Mohd Radzi, N. H., Ismail, W., & Osman, M. H. (2022). A review on classification algorithms for imbalanced datasets. Journal of Physics: Conference Series, 2324, 012003.
OCHA. (2023). Syrian Arab Republic: Humanitarian needs overview 2023. United Nations Office for the Coordination of Humanitarian Affairs.
Popescu, M. C., Balas, V. E., Perescu-Popescu, L., & Mastorakis, N. (2009). Multilayer perceptron and neural networks. WSEAS Transactions on Circuits and Systems, 8(7), 579–588.
Ratra, R., Gulia, P., & Gill, N. S. (2021). Performance analysis of classification techniques in data mining using WEKA. Proceedings of the International Conference on Innovative Computing.
Rish, I. (2001). An empirical study of the naive Bayes classifier. IJCAI Workshop on Empirical Methods in AI, 41–46.
Tekdamar, D. A., & Tekdamar, K. (2024). Coğrafi bilgi sistemleri tabanlı analitik hiyerarşi yöntemi kullanılarak güneş enerjisi santrali yer seçimi: Mardin ili örneği. Kahramanmaraş Sütçü İmam Üniversitesi Mühendislik Bilimleri Dergisi, 27(1), 199–212. https://doi.org/10.17780/ksujes.1371448
UNHCR. (2023). Global trends: Forced displacement in 2022. United Nations High Commissioner for Refugees. Witten, I. H., Frank, E., Hall, M. A., & Pal, C. J. (2016). Data mining: Practical machine learning tools and techniques (4th ed.). Morgan Kaufmann.

Details

Primary Language

English

Subjects

Multiple Criteria Decision Making, Industrial Engineering

Journal Section

Research Article

Authors

Yasemin Şirin Eryoldaş
0000-0002-7212-9108
Türkiye

Jamil Hallak ^*
0000-0001-5975-4075
Türkiye

Publication Date

June 3, 2026

Submission Date

November 23, 2025

Acceptance Date

March 31, 2026

Published in Issue

Year 2026 Volume: 29 Number: 2

IZ

https://izlik.org/JA72XL24MZ

Cite

RIS / Bibtex

APA

Şirin Eryoldaş, Y., & Hallak, J. (2026). EVALUATING CLASSIFICATION ALGORITHMS FOR PREDICTING SOCIAL PROJECT APPROVAL IN POST-CONFLICT REGIONS. Kahramanmaraş Sütçü İmam Üniversitesi Mühendislik Bilimleri Dergisi, 29(2), 919-930. https://izlik.org/JA72XL24MZ

AMA

1.Şirin Eryoldaş Y, Hallak J. EVALUATING CLASSIFICATION ALGORITHMS FOR PREDICTING SOCIAL PROJECT APPROVAL IN POST-CONFLICT REGIONS. KSU J. Eng. Sci. 2026;29(2):919-930. https://izlik.org/JA72XL24MZ

Chicago

Şirin Eryoldaş, Yasemin, and Jamil Hallak. 2026. “EVALUATING CLASSIFICATION ALGORITHMS FOR PREDICTING SOCIAL PROJECT APPROVAL IN POST-CONFLICT REGIONS”. Kahramanmaraş Sütçü İmam Üniversitesi Mühendislik Bilimleri Dergisi 29 (2): 919-30. https://izlik.org/JA72XL24MZ.

EndNote

Şirin Eryoldaş Y, Hallak J (June 1, 2026) EVALUATING CLASSIFICATION ALGORITHMS FOR PREDICTING SOCIAL PROJECT APPROVAL IN POST-CONFLICT REGIONS. Kahramanmaraş Sütçü İmam Üniversitesi Mühendislik Bilimleri Dergisi 29 2 919–930.

IEEE

[1]Y. Şirin Eryoldaş and J. Hallak, “EVALUATING CLASSIFICATION ALGORITHMS FOR PREDICTING SOCIAL PROJECT APPROVAL IN POST-CONFLICT REGIONS”, KSU J. Eng. Sci., vol. 29, no. 2, pp. 919–930, June 2026, [Online]. Available: https://izlik.org/JA72XL24MZ

ISNAD

Şirin Eryoldaş, Yasemin - Hallak, Jamil. “EVALUATING CLASSIFICATION ALGORITHMS FOR PREDICTING SOCIAL PROJECT APPROVAL IN POST-CONFLICT REGIONS”. Kahramanmaraş Sütçü İmam Üniversitesi Mühendislik Bilimleri Dergisi 29/2 (June 1, 2026): 919-930. https://izlik.org/JA72XL24MZ.

JAMA

1.Şirin Eryoldaş Y, Hallak J. EVALUATING CLASSIFICATION ALGORITHMS FOR PREDICTING SOCIAL PROJECT APPROVAL IN POST-CONFLICT REGIONS. KSU J. Eng. Sci. 2026;29:919–930.

MLA

Şirin Eryoldaş, Yasemin, and Jamil Hallak. “EVALUATING CLASSIFICATION ALGORITHMS FOR PREDICTING SOCIAL PROJECT APPROVAL IN POST-CONFLICT REGIONS”. Kahramanmaraş Sütçü İmam Üniversitesi Mühendislik Bilimleri Dergisi, vol. 29, no. 2, June 2026, pp. 919-30, https://izlik.org/JA72XL24MZ.

Vancouver

1.Yasemin Şirin Eryoldaş, Jamil Hallak. EVALUATING CLASSIFICATION ALGORITHMS FOR PREDICTING SOCIAL PROJECT APPROVAL IN POST-CONFLICT REGIONS. KSU J. Eng. Sci. [Internet]. 2026 Jun. 1;29(2):919-30. Available from: https://izlik.org/JA72XL24MZ