SavedAdd your journal

Journals / Journal of Mehmet Akif Ersoy University Economics and Administrative Sciences Faculty / 2026 / Volume: 13 Issue: 1

XAI-Supported Multi-Algorithm Budget Forecasting Model: Analysis of Türkiye’s Fiscal Sustainability and Parameter Importances for the Period 1999–2024

Ebru Yılmaz İnce(ISPARTA UNIVERSITY OF APPLIED SCIENCES, TECHNICAL SCIENCES VOCATIONAL SCHOOL, DEPARTMENT OF COMPUTER TECHNOLOGIES)0000-0001-9462-0363
Oğuz Kuyumcu(ISPARTA UYGULAMALI BİLİMLER ÜNİVERSİTESİ)0000-0003-4153-7210
Murat İnce(ISPARTA UNIVERSITY OF APPLIED SCIENCES, TECHNICAL SCIENCES VOCATIONAL SCHOOL, DEPARTMENT OF COMPUTER TECHNOLOGIES, COMPUTER PROGRAMMING PR.)0000-0001-5566-5008
Pages
—
Publication Date
2026-03-30
🏛️Bibliographic metadata and full text access for this article are provided via DergiPark.
DergiPark Record ↗
✨

AI Summary & Key Takeaways

AI Insight
⚡ TL;DR(Too Long; Didn't Read)

The findings indicate that the RF model is more effective at predicting borrowing needs, even while the XGB model offers the most accurate forecasts for overall revenues and expenses.

📌 3 Key Takeaways

🎯
Objective & Hypothesis:Using financial and sociological data from Türkiye between 1999 and 2024, this work aims to develop an artificial intelligence (AI) augmented budget forecasting model.
📊
Key Findings & Data:The findings indicate that the RF model is more effective at predicting borrowing needs, even while the XGB model offers the most accurate forecasts for overall revenues and expenses.
💡
Conclusion & Impact:The findings emphasize how crucial it is to combine explainable budget forecasts in Türkiye with AI techniques.
🔬Design:Modeling & Simulation
📍Scope:2024 Verileri
⚙️Variables:Budget Forecasting · Explainable Artificial Intelligence (XAI) · SHAP Value

Abstract

Using financial and sociological data from Türkiye between 1999 and 2024, this work aims to develop an artificial intelligence (AI) augmented budget forecasting model. It also seeks to evaluate sustainability using the output of this model. This study assessed the efficacy of a number of methods, including Artificial Neural Networks (ANN), Random Forest (RF), XGBoost (XGB), and Deep Learning (DL). The study employed SHapley Additive Explanations (SHAP), a method associated with explainable artificial intelligence (XAI), to explain the model's output. The findings indicate that the RF model is more effective at predicting borrowing needs, even while the XGB model offers the most accurate forecasts for overall revenues and expenses. The SHAP analysis emphasizes how important variables like loan amounts, debt levels, and demographic size are. The findings emphasize how crucial it is to combine explainable budget forecasts in Türkiye with AI techniques.

🔖

Cite This Article

İnce, E. Y., Kuyumcu, O., İnce, M. (2026). XAI-Supported Multi-Algorithm Budget Forecasting Model: Analysis of Türkiye’s Fiscal Sustainability and Parameter Importances for the Period 1999–2024. Journal of Mehmet Akif Ersoy University Economics and Administrative Sciences Faculty, Volume: 13 Issue: 1. https://doi.org/10.30798/makuiibf.1764796

📄 Full Text PDF Viewer

📄

PDF görüntüleyici hazırlanıyor...

References (54)

  1. Adu, W.K., Appiahene, P. & Afrifa, S. (2023) VAR, ARIMAX and ARIMA models for nowcasting unemployment rate in Ghana using Google trends. Journal of Electrical Systems and Inf Technol, 10(12), 1-16. https://doi.org/10.1186/s43067-023-00078-1
  2. Akıncı, A. (2025). Sürdürülebilir ekonomik büyümenin sağlanmasında vergi harcamalarının rolü: Teknokentlerin vergilendirilmesi. Uluslararası Afro-Avrasya Araştırmaları Dergisi, 10(19), 108-119.
  3. Akıncı, A., & Erasa Akça, İ. (2024). Türkiye’de bütçe açıkları ile ekonomik büyüme arasındaki ilişki: Nedensellik analizi. Akademik Araştırmalar ve Çalışmalar Dergisi (AKAD), 16(30), 62-71. https://doi.org/10.20990/kilisiibfakademik.1429454
  4. Aliyev, P. (2025). LSTM ve GRU Modellerinde açıklanabilir yapay zekâ yaklaşımı: İktisadi veriler üzerine bir uygulama. Journal of the Institute of Science and Technology, 15(2), 396-411.
  5. Alkan, A., & Sevli, O. (2023). Türkiye’de yapay zekâ alanında yazılmış yüksek lisans tezlerinin incelenmesi. Osmaniye Korkut Ata Üniversitesi Fen Bilimleri Enstitüsü Dergisi, 6(1), 931-947. https://doi.org/10.47495/okufbed.1062622
  6. Amoako, G. K., Adam, A. M., Arthur, C. L., & Tackie, G. (2021). Institutional isomorphism, environmental management accounting and environmental accountability: A review. Environment, Development and Sustainability, 23(8), 11201-11216. https://doi.org/10.1007/s10668-020-01140-y
  7. Antwi, G. B. (2025). The role of artificial intelligence in enhancing budget forecasting for SMEs amid economic uncertainty. International Journal of Novel Research and Development, 8(12), 549-560. https://doi.org/10.56975/ijnrd.v8i12.305865
  8. Armağan, R., & Büyükçulcu, U. (2024). Türkiye’de Covid-19 pandemisinin kalkınma ajanslarının ekonomik yapısı ve faaliyetleri üzerine etkileri. Süleyman Demirel Üniversitesi İktisadi ve İdari Bilimler Fakültesi Dergisi, 29(3), 133-148.
  9. Arrieta, A. B., Díaz-Rodríguez, N., Del Ser, J., Bennetot, A., Tabik, S., Barbado, A., Garcia, S., Gil-Lopez, S., Molina, D., Benjamins, R., Chatila, R., & Herrera, F. (2020). Explainable artificial intelligence (XAI): concepts, taxonomies, opportunities and challenges toward responsible AI. Information Fusion, 58, 82-115. https://doi.org/10.1016/j.inffus.2019.12.012
  10. Aydemi̇r, E., & Yalçınkaya, C. A. M. A. (2024). Yapay zekâ ile konut fiyatlarının tahmin edilmesi. Turkish Studies- Information Technologies and Applied Sciences, 15(2), 183-194. https://doi.org/10.29228/TurkishStudies.43161
  11. Aydın, M. A. (2025). Telekomünikasyon sektöründe müşteri kaybı tahmini için açıklanabilir makine öğrenmesi. EMO Bilimsel Dergi, 15(2), 71-79. https://izlik.org/JA75WY57HS
  12. Balkan, B. (2021). Impacts of digitalization on banks and banking. In S. Bozkuş Kahyaoğlu (Eds.) The impact of artificial intelligence on governance, economics and finance, Volume I. Accounting, finance, sustainability, governance & fraud: Theory and application. (pp. 33-50) Springer. https://doi.org/10.1007/978-981-33-6811- 8_3
  13. Barthélémy, S., Binet, M.-E., & Pentecôte, J.-S. (2020). Worldwide economic recoveries from financial crises through the decades. Journal of International Money and Finance, 105, 102204. https://doi.org/10.1016/j.jimonfin.2020.102204
  14. Bekiaris, M., & Markogiannopoulou, A. (2022). Enterprise resource planning system reforms of European Union member states in association with central government accrual accounting and IPSAS adoption. Journal of Public Budgeting, Accounting & Financial Management, 35(1), 115-140. https://doi.org/10.1108/JPBAFM- 06-2021-0104
  15. Bisen, Ö. (2012). Üstyapı projelerinin maliyet tahmin çalışmalarında belirsizliklerin yapay zekâ teknikleriyle analizi. Engineering Sciences, 7(2), 394-403. https://doi.org/10.12739/nwsaes.v7i2.5000066847
  16. Bouchetara, M., Zerouti, Messaoud, & and Zouambi, A. R. (2024). Leveraging artificial intelligence (AI) in public sector financial risk management: Innovations, challenges, and future directions. EDPACS, 69(9), 124-144. https://doi.org/10.1080/07366981.2024.2377351
  17. Breiman, L. (2001). Random forests. Machine Learning, 45(1), 5-32. https://doi.org/10.1023/A:1010933404324
  18. Capone, C., Talgat, S., Hazir, O., Abdrasheva, K., & Kozhakhmetova, A. (2024). Artificial intelligence models for predicting budget expenditures. Eurasian Journal of Economic and Business Studies, 68(1), 32-43. https://doi.org/10.47703/ejebs.v68i1.331
  19. Chai, T., & Draxler, R. R. (2014). Root mean square error (RMSE) or mean absolute error (MAE)? – Arguments against avoiding RMSE in the literature. Geoscientific Model Development, 7(3), 1247-1250. https://doi.org/10.5194/gmd-7-1247-2014
  20. Chang, X. (2025). Optimisation of big data and artificial intelligence driven digital intelligence in manufacturing budget management. In H. Sun, H. Luo, V. Gaikar, & N. Cudečka-Puriņa (Eds.), Proceedings of the 2025 10th international conference on social sciences and economic development (ICSSED 2025) (pp. 517–530). Atlantis Press. https://doi.org/10.2991/978-94-6463-734-2_59
  21. Chollet, F. (2021). Deep learning with Python (2nd ed.). Simon & Schuster.
  22. Das, A., & Rad, P. (2020). Opportunities and challenges in explainable artificial intelligence (XAI): A survey (arXiv:2006.11371). arXiv. 1-24. https://doi.org/10.48550/arXiv.2006.11371
  23. Demir, S., & Sahin, E. K. (2023). An investigation of feature selection methods for soil liquefaction prediction based on tree-based ensemble algorithms using AdaBoost, gradient boosting, and XGBoost. Neural Computing and Applications, 35(4), 3173-3190. https://doi.org/10.1007/s00521-022-07856-4
  24. Dere, İ., & Çinikaya, C. (2023). Tiflis bildirgesi ve BM 2030 sürdürülebilir kalkınma amaçlarının çevre eğitimi ve iklim değişikliği dersi öğretim programına yansımaları. Ordu Üniversitesi Sosyal Bilimler Enstitüsü Sosyal Bilimler Araştırmaları Dergisi, 13(1), 1343-1366. https://doi.org/10.48146/odusobiad.1218188
  25. Emirkadı, Ö. (2024). Kırılgan beşlilerde mali sürdürülebilirlik: Panel regresyon analizi. Fırat Üniversitesi Uluslararası İktisadi ve İdari Bilimler Dergisi, 8(1), 23-50.
  26. Ghimire, P., Pokharel, S., Kim, K., & Barutha, P. (2023, June). Machine learning-based prediction models for budget forecast in capital construction. In proceedings of the 2nd international conference on construction, energy, environment & sustainability, (pp. 1-6), Funchal, Portugal.
  27. Gür, Y., & Yıldız, A. (2024). Türkiye’de bütçe gelirlerinin tahmini için yenilikçi bir model önerisi: XGBoost-LSTM- GRU hibrit yaklaşımı, Maliye Dergisi, 186, 57-86.
  28. İnce, M. (2022). Automatic and intelligent content visualization system based on deep learning and genetic algorithm. Neural Computing and Applications, 34(3), 2473-2493. https://doi.org/10.1007/s00521-022-06887-1
  29. Jang, H. (2019). A decision support framework for robust R&D budget allocation using machine learning and optimization. Decision Support Systems, 121, 1-12. https://doi.org/10.1016/j.dss.2019.03.010
  30. Karaş, E. (2024). Türkiye’de mali sürdürülebilirliğin analizi: NARDL yöntemi. Maliye Çalışmaları Dergisi, 72, 64- 78. https://doi.org/10.26650/mcd2024-1559287
  31. Kaya, E. (2024). Kamu yönetiminde dijital dönüşüm ve yapay zekâ uygulamaları. Hitit Ekonomi ve Politika Dergisi, 4(2), 126-141. https://doi.org//hepdergi.1588634
  32. Kesriklioglu, E., & Oktay, E. (2023). Makine Öğrenmesi yöntemleri kullanılarak hanehalkı toplam enerji harcamaları tahmini. Türk Akademik Sosyal Bilimler Araştırma Dergisi, 5(2), 110-118.
  33. Konu, A., & Ata, A. Y. (2022). Kamu yönetimi açısından yapay zekanın Türkiye’deki bütçe açıklarının tahmini üzerine etkisi. Fiscaoeconomia, 6(2), 636-655.
  34. Kryvovyazyuk, I., Britchenko, I., Lipych, L., Kravchuk, P., Galaziuk, N., & Burban, O. (2025). Impact of global risks on economic downturn in countries worldwide: Analysis of the causes of the situation and opportunities for growth recovery. Economic Studies Journal (Ikonomicheski Izsledvania), 34(6), 66-86. http://dx.doi.org/10.2139/ssrn.5314126
  35. Kunnathuvalappil Hariharan, N. (2017). Predictive model building for driver-based budgeting using machine learning. MPRA Paper. https://mpra.ub.uni-muenchen.de/109516/
  36. Kusonkhum, W., Srinavin, K., Leungbootnak, N., Aksorn, P., & Chaitongrat, T. (2022). Government construction project budget prediction using machine learning. Journal of Advances in Information Technology, 13(1), 29- 35. https://doi.org/10.12720/jait.13.1.29-35
  37. Kuyumcu, O. (2024). Kamu ve özel sektör muhasebesi kavramsal çerçevelerinin karşılaştırmalı analizi. Maliye Dergisi, 187, 221-246.
  38. Montgomery, D. C., Peck, E. A., & Vining, G. G. (2021). Introduction to linear regression analysis (6th ed.). John Wiley & Sons.
  39. Mosca, E., Szigeti, F., Tragianni, S., Gallagher, D., & Groh, G. (2022). SHAP-Based explanation methods: A review for NLP interpretability. In, N. Calzolari, C.-R. Huang, H. Kim, J. Pustejovsky, L. Wanner, K.-S. Choi, P.-M. Ryu, H.-H. Chen, L. Donatelli, H. Ji, S. Kurohashi, P. Paggio, N. Xue, S. Kim, Y. Hahm, Z. He, T. K. Lee, E. Santus, F. Bond, & S.-H. Na (Ed.), The 29th international conference on computational linguistics (ss. 4593-4603). International Committee on Computational Linguistics. https://aclanthology.org/2022.coling-1.406/
  40. Newbold, P. (1983). ARIMA model building and the time series analysis approach to forecasting. Journal of forecasting, 2(1), 23-35. https://doi.org/10.1002/for.3980020104
  41. Nguyen, S., Chan, R., Cadena, J., Soper, B., Kiszka, P., Womack, L., Work, M., Duggan, J. M., Haller, S. T., Hanrahan, J. A., Kennedy, D. J., Mukundan, D., & Ray, P. (2021). Budget constrained Machine Learning for Early Prediction of Adverse Outcomes for COVID-19 Patients. Scientific Reports, 11(1), 19543. 1-14. https://doi.org/10.1038/s41598- 021-98071-z
  42. Öztürk, K., & Şahin, M. E. (2018). Yapay sinir ağları ve Yapay Zekâ’ya genel bir bakış. Takvim-i Vekayi, 6(2), 25- 36.
  43. Pıçak, Ş. (2022). Türkiye’de bütçe gider ve gelir tahminlerinin objektif doğruluk açısından değerlendirilmesi. Ekonomi İşletme ve Maliye Araştırmaları Dergisi, 4(2), 146-158. https://doi.org/10.38009/ekimad.1139292
  44. Qin, J., & Qin, Q. (2021). Cloud platform for enterprise financial budget management based on artificial intelligence. Wireless Communications and Mobile Computing, 2021(1), 8038433. https://doi.org/10.1155/2021/8038433
  45. Sadick, A.-M., Gurmu, A., & Gunarathna, C. (2024). Artificial intelligence-based pre-conception stage construction budget decision-making model and tool for residential buildings. Engineering, Construction and Architectural Management, 32(7), 4552-4580. https://doi.org/10.1108/ECAM-11-2023-1108
  46. Sun, Y., Li, J., Lu, M., & Guo, Z. (2024). Study of the impact of the big data era on accounting and auditing. Frontiers in Business, Economics and Management, 13(3), 44-47. https://doi.org/10.48550/arXiv.2403.07180
  47. Tsikomia, A. A. M. (2021). Can a budget simulation model of decentralized territorial authorities be enhanced by an artificial intelligence method? In International conference “Risk in contemporary economy” (pp. 81– 128). “Dunarea de Jos” University of Galati, Romania – Faculty of Economics and Business Administration. https://doi.org/10.35219/rce20670532107
  48. Türküz, E., & Akay, E. Ç. (2020). Econometrics and machine learning: a review of choice models and classification algorithms. Social Sciences Research Journal, 9(04), 181-194.
  49. Valle-Cruz, D., Fernandez-Cortez, V., & Gil-Garcia, J. R. (2022). From e-budgeting to smart budgeting: exploring the potential of artificial intelligence in government decision-making for resource allocation. Government Information Quarterly, 39(2), 101644. https://doi.org/10.1016/j.giq.2021.101644
  50. Willmott, C. J., & Matsuura, K. (2005). Advantages of the mean absolute error (MAE) over the root mean square error (RMSE) in assessing average model performance. Climate Research, 30(1), 79-82.
  51. Yavuz, E., Kılıç, E., Kar, A., & Pazarcı, Ş. (2024). Mali sürdürülebilirliğe giden yolda asimetrik yapı ne kadar etkili? Türkiye üzerine yeniden düşünmek. Maliye Dergisi, 185, 97-124.
  52. Yıldız, B., & Gedik, H. (2004). Bulanık bütçeleme ve bulanık bütçe kontrolü. Eskişehir Osmangazi Üniversitesi Sosyal Bilimler Dergisi, 5(2), 141-166.
  53. Zhang, D., Lin, R., Wei, T., Ling, L., & Huang, J. (2023). A novel deep transfer learning framework with adversarial domain adaptation: Application to financial time-series forecasting. Neural Computing and Applications, 35(34), 24037-24054. https://doi.org/10.1007/s00521-023-09047-1
  54. Zhou, W., Yan, Z., & Zhang, L. (2024). A comparative study of 11 non-linear regression models highlighting autoencoder, DBN, and SVR, enhanced by SHAP importance analysis in soybean branching prediction. Scientific Reports, 14(1), 5905. https://doi.org/10.1038/s41598-024-55243-x