Information
- Author Services
Initiatives
You are accessing a machine-readable page. In order to be human-readable, please install an RSS reader.
All articles published by MDPI are made immediately available worldwide under an open access license. No special permission is required to reuse all or part of the article published by MDPI, including figures and tables. For articles published under an open access Creative Common CC BY license, any part of the article may be reused without permission provided that the original article is clearly cited. For more information, please refer to https://www.mdpi.com/openaccess .
Feature papers represent the most advanced research with significant potential for high impact in the field. A Feature Paper should be a substantial original Article that involves several techniques or approaches, provides an outlook for future research directions and describes possible research applications.
Feature papers are submitted upon individual invitation or recommendation by the scientific editors and must receive positive feedback from the reviewers.
Editor’s Choice articles are based on recommendations by the scientific editors of MDPI journals from around the world. Editors select a small number of articles recently published in the journal that they believe will be particularly interesting to readers, or important in the respective research area. The aim is to provide a snapshot of some of the most exciting work published in the various research areas of the journal.
Original Submission Date Received: .
- Active Journals
- Find a Journal
- Proceedings Series
- For Authors
- For Reviewers
- For Editors
- For Librarians
- For Publishers
- For Societies
- For Conference Organizers
- Open Access Policy
- Institutional Open Access Program
- Special Issues Guidelines
- Editorial Process
- Research and Publication Ethics
- Article Processing Charges
- Testimonials
- Preprints.org
- SciProfiles
- Encyclopedia
Article Menu
- Subscribe SciFeed
- Recommended Articles
- Google Scholar
- on Google Scholar
- Table of Contents
Find support for a specific problem in the support section of our website.
Please let us know what you think of our products and services.
Visit our dedicated information section to learn more about MDPI.
JSmol Viewer
Forecasting of the unemployment rate in turkey: comparison of the machine learning models.
1. Introduction
2. materials and methods, 2.1. artificial intelligence methods, 2.1.1. artificial neural networks (ann), 2.1.2. support vector machine (svm), 2.1.3. extreme gradient boosting (xgboost), 2.1.4. model performance metrics, 3.1. model-1, 3.2. model-2, 4. discussion, 5. conclusions, author contributions, data availability statement, conflicts of interest.
- ILO. Statistics of Labour Force, Employment, Unemployment and Underemployment ; ILO: Genova, Italy, 1982; Available online: https://www.ilo.org/public/libdoc/ilo/1982/82B09_438_engl.pdf (accessed on 28 February 2024).
- Friedman, M. Nobel Lecture: Inflation and Unemployment. J. Political Econ. 1977 , 85 , 451–472. [ Google Scholar ] [ CrossRef ]
- Haug, A.A.; King, I.P. Empirical Evidence on Inflation and Unemployment in the Long Run. Univ. Otago Econ. Discuss. Pap. Ser. 2011 , 1109 . [ Google Scholar ] [ CrossRef ]
- Berentsen, A.; Menzio, G.; Wright, R. Inflation and Unemployment in the Long Run. Am. Econ. Rev. 2011 , 101 , 371–398. [ Google Scholar ] [ CrossRef ]
- Ormerod, P.; Rosewell, B.; Phelps, P. Inflation/unemployment regimes and the instability of the Phillips curve. Appl. Econ. 2013 , 45 , 1519–1531. [ Google Scholar ] [ CrossRef ]
- Alisa, M. The Relationship between Inflation and Unemployment: A Theoretical Discussion about the Philips Curve. J. Int. Bus. Econ. 2015 , 3 , 89–97. [ Google Scholar ] [ CrossRef ]
- Karacan, R. Phillips Eğrisi Yaklaşımı İle Türkiye’de Enflasyon ve İşsizlik ArasındakiNedensellik İlişkisi. Socıal Ment. Res. Thınkers J. 2018 , 4 , 242–249. [ Google Scholar ]
- Uysal, D.; Erdoğan, S. Enflasyon ile İşsizlik Oranı Arasındaki İlişki Ve Türkiye Örneği (1980–2002). Sos. Ekon. Araştırmalar Derg. 2003 , 3 , 35–47. [ Google Scholar ]
- Ayvaz Güven, E.T.; Ayvaz, Y.Y. Türkiye’de Enflasyon Ve İşsizlik Arasındaki İlişki: Zaman Serileri Analizi. KSÜ Sos. Bilim. Derg. 2016 , 13 , 241–262. [ Google Scholar ]
- Akiş, E. Türkiye’de Enflasyon ile İşsizlik Arasındaki İlişki (2005–2020). Yüzüncü Yıl Üniv. Sos. Bilim. Enstitüsü Dergisi 2020 , 49 , 403–420. [ Google Scholar ]
- Gordon, R.J. Inflatıon, Flexıble Exchange Rates, and the Natural Rate of Unemployment ; Nber Working Paper Series: Cambridge, MA, USA, 1981. [ Google Scholar ] [ CrossRef ]
- Bilgin, M.H. Döviz Kuru İşsizlik İlişkisi: Türkiye Üzerine Bir İnceleme. Döviz Kuru İşsizlik İlişkisi Türkiye Üzerine Bir İnceleme 2004 , 8 , 80–94. [ Google Scholar ]
- Frenkel, R.; Ros, J. Unemployment and the Real Exchange Rate in Latin America. World Dev. 2006 , 34 , 631–646. [ Google Scholar ] [ CrossRef ]
- Bakhshi, Z.; Ebrahimi, M. The effect of real exchange rate on unemployment. Mark. Brand. Res. 2016 , 3 , 4–13. [ Google Scholar ] [ CrossRef ]
- Choi, Y.; Choi, K.E. Unemployment and optimal exchange rate in an open economy. Econ. Model. 2017 , 69 , 82–90. [ Google Scholar ] [ CrossRef ]
- Ani, E.C.; Joel, E.; Baajon, M.A. Exchange Rate and Unemployment in Nigeria: An Analysis. Int. J. Fam. Bus. Manag. 2019 , 3 , 1–7. [ Google Scholar ]
- Selim, S.; Ayvaz Güven, E.T. Türkiye’de Enflasyon, Döviz Kuru ve İşsizlik Arasındaki İlişkinin Ekonometrik Analizi. Ekon. Ve Sos. Araştırmalar Derg. 2014 , 10 , 127–145. [ Google Scholar ]
- Kakinaka, M.; Miyamoto, H. Unemployment and labour force participation in Japan. Appl. Econ. Lett. 2012 , 19 , 1039–1043. [ Google Scholar ] [ CrossRef ]
- Özerkek, Y. Unemployment and Labor Force Partıcıpatıon: A Panel Coıntegratıon Analysıs For European Countrıes. Appl. Econom. Int. Dev. 2013 , 13 , 67–76. [ Google Scholar ]
- Yenilmez, F.; Kılıç, E. Türkiye’de İşgücüne Katılma Oranı-İşsizlik Oranı İlişkisi: Cinsiyet ve Eğitim Düzeyine Dayalı Bir Analiz. Eskişehir Osman. Üniv. İİbf Derg. 2018 , 13 , 55–76. [ Google Scholar ]
- Phillips, A.W. The Relation Between Unemployment and the Rate of Change of Money Wage Rates in the United Kingdom, 1861–1957. Lond. Sch. Econ. Political Sci. 1958 , 25 , 283–299. [ Google Scholar ] [ CrossRef ]
- Moshiri, S.; Brown, L. Unemployment Variation Over the Business Cycles: A Comparison of Forecasting Models. J. Forecast. 2004 , 23 , 463–539. [ Google Scholar ] [ CrossRef ]
- Purpa, N.Z.; Anjar, W.; Okta, I.O. Implementation of Ann for Prediction of Unemployment Rate Based on Urban Village in 3 Sub-Districts of Pematangsiantar. Int. J. Inf. Syst. Technol. 2019 , 3 , 107–116. [ Google Scholar ]
- Mutascu, M.; Hegerty, S.W. Predicting the Contribution of Artifcial Intelligence to Unemployment Rates: An Artifcial Neural Network Approach. J. Econ. Financ. 2023 , 47 , 400–416. [ Google Scholar ] [ CrossRef ]
- Tufaner, M.B.; Sözen, İ. Forecasting Unemployment Rate in the Aftermath of the COVID-19 Pandemic: The Turkish Case. İzmir İktisat Derg. 2021 , 36 , 685–693. [ Google Scholar ] [ CrossRef ]
- Stasinakis, C.; Sermpinis, G.; Theofilatos, K.; Karathanasopuolos, A. Forecasting US Unemployment with Radial Basis Neural Networks, Kalman Filters and Support Vector Regressions. Comput. Econ. 2016 , 47 , 569–587. [ Google Scholar ] [ CrossRef ]
- Ansari, A. Application of Neural Network-Support Vector Technique to Forecast U.S. Unemployment Rate. Master’s Thesis, Vest Virginia University, Morgantown, WV, USA, 2014. [ Google Scholar ]
- Sermpinis, G.; Charalampos, S.; Konstantinos, T.; Andreas, K. Inflation and Unemployment Forecasting with Genetic Support Vector Regression. J. Forecast. 2014 , 33 , 471–487. [ Google Scholar ] [ CrossRef ]
- Priliani, E.M.; Putra, A.T.; Muslim, M.A. Forecasting Inflation Rate Using Support Vector Regression (SVR) Based Weight Attribute Particle Swarm Optimization (WAPSO). Sci. J. Inform. 2018 , 5 , 118–127. [ Google Scholar ] [ CrossRef ]
- Adenomon, M.O. Modelling and Forecasting Unemployment Rates in Nigeria Using Arima Model. FUW Trends Sci. Technol. J. 2017 , 2 , 525–531. [ Google Scholar ]
- Kütük, Y.; Güloğlu, B. Prediction of Transition Probabilities from Unemployment to Employment for Turkey Via Machine Learning and Econometrics: A Comparative Study. İktisat Araştırmaları Derg. 2019 , 3 , 58–75. [ Google Scholar ]
- Fausett, L.V. Fundamentals of Neural Networks: Architectures, Algorithms and Applications ; Pearson Education: Noida, India, 2006. [ Google Scholar ]
- Xie, X.; Pu, Y.F.; Wang, J. A fractional gradient descent algorithm robust to the initial weights of multilayer perceptron. Neural Netw. 2023 , 158 , 154–170. [ Google Scholar ] [ CrossRef ]
- Maehashi, K.; Shintani, M. Macroeconomic forecasting using factor models and machine learning: An application to Japan. J. Jpn. Int. Econ. 2020 , 58 , 101104. [ Google Scholar ] [ CrossRef ]
- Atallah, R.; Al-Mousa, A. Heart Disease Detection Using Machine Learning Majority Voting Ensemble Method. In Proceedings of the 2nd International Conference on New Trends in Computing Sciences (ICTCS), Amman, Jordan, 9–11 October 2019. [ Google Scholar ]
- Shevade, S.K.; Keerthi, S.S.; Bhattacharyya, C.; Murthy, K.R.K. Improvements to the SMO algorithm for SVM regression. IEEE Trans. Neural Netw. 2000 , 11 , 1188–1193. [ Google Scholar ] [ CrossRef ] [ PubMed ]
- Chen, T.; Guestrin, C. Xgboost: A Scalable Tree Boosting System. In Proceedings of the 22nd acm Sigkdd International Conference on Knowledge Discovery and Data Mining, San Francisco, CA, USA, 13–17 August 2016. [ Google Scholar ]
- Lewis, C.D. Industrial and Business Forecasting Methods ; Butterworths Publishing: London, UK, 1982; ISBN 978-0408005593. [ Google Scholar ]
- Total Unemployment Rate & TURKSTAT. 2024. Available online: https://data.tuik.gov.tr/Kategori/GetKategori?p=istihdam-issizlik-ve-ucret-108&dil=1 (accessed on 25 May 2024).
- Inflation, Exchange Rate and Labor Force Rates & TURKSTAT. 2024. Available online: https://data.tuik.gov.tr/Kategori/GetKategori?p=enflasyon-ve-fiyat-106&dil=1 (accessed on 25 May 2024).
- Yamacli, D.S.; Yamacli, S. Estimation of the unemployment rate in Turkey: A comparison of the ARIMA and machine learning models including COVID-19 pandemic periods. Heliyon 2023 , 9 , e12796. [ Google Scholar ] [ CrossRef ] [ PubMed ]
- Wei, Y.; Rao, X.; Fu, Y.; Song, L.; Chen, H.; Li, J. Machine learning prediction model based on enhanced bat algorithm and support vector machine for slow employment prediction. PLoS ONE 2023 , 18 , e0294114. [ Google Scholar ] [ CrossRef ] [ PubMed ]
- Katris, C. Prediction of unemployment rates with time series and machine learning techniques. Comput. Econ. 2020 , 55 , 673–706. [ Google Scholar ] [ CrossRef ]
Click here to enlarge figure
Lag1 | Lag2 | Lag3 | Lag4 | Lag5 | Lag6 | Lag7 | Lag8 | Lag9 | Lag10 | Lag11 | Lag12 | Unemployment |
---|---|---|---|---|---|---|---|---|---|---|---|---|
11.76 | 11.93 | 11.23 | 10.36 | 9.61 | 9.62 | 9.63 | 9.93 | 10.13 | 10.44 | 10.9 | 11.53 | 12.07 |
11.93 | 11.23 | 10.36 | 9.61 | 9.62 | 9.63 | 9.93 | 10.13 | 10.44 | 10.9 | 11.53 | 12.07 | 12.23 |
11.23 | 10.36 | 9.61 | 9.62 | 9.63 | 9.93 | 10.13 | 10.44 | 10.9 | 11.53 | 12.07 | 12.23 | 11.25 |
10.36 | 9.61 | 9.62 | 9.63 | 9.93 | 10.13 | 10.44 | 10.9 | 11.53 | 12.07 | 12.23 | 11.25 | 10.25 |
9.61 | 9.62 | 9.63 | 9.93 | 10.13 | 10.44 | 10.9 | 11.53 | 12.07 | 12.23 | 11.25 | 10.25 | 9.16 |
. | . | . | . | . | . | . | . | . | . | . | . | . |
. | . | . | . | . | . | . | . | . | . | . | . | . |
. | . | . | . | . | . | . | . | . | . | . | . | . |
10.2 | 10.3 | 9.7 | 10.7 | 10.2 | 10.2 | 9.5 | 9.6 | 9.7 | 9.2 | 9.1 | 8.5 | 9 |
10.3 | 9.7 | 10.7 | 10.2 | 10.2 | 9.5 | 9.6 | 9.7 | 9.2 | 9.1 | 8.5 | 9 | 8.8 |
Month/Year | Annual Inflation Compared with Same Month of Previous Year | Monthly Inflation Compared with Previous Month | Dollar Sale TRY | Labor Force | Lag1 | Lag2 | Lag3 | Lag4 | Lag5 | Lag6 | Lag7 | Lag8 | Lag9 | Lag10 | Lag11 | Lag12 | Unemployment |
---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
January 2006 | 7.72 | 0.42 | 1.35 | 22.14 | 11.76 | 11.9 | 11.2 | 10.3 | 9.61 | 9.62 | 9.63 | 9.93 | 10.1 | 10.4 | 10.9 | 11.5 | 12.07 |
February 2006 | 7.93 | 0.75 | 1.33 | 21.82 | 11.93 | 11.2 | 10.3 | 9.61 | 9.62 | 9.63 | 9.93 | 10.1 | 10.4 | 10.9 | 11.5 | 12.0 | 12.23 |
March 2006 | 8.15 | 0.22 | 1.33 | 21.58 | 11.23 | 10.3 | 9.61 | 9.62 | 9.63 | 9.93 | 10.1 | 10.4 | 10.9 | 11.5 | 12.0 | 12.2 | 11.25 |
April 2006 | 8.16 | 0.27 | 1.34 | 22.00 | 10.36 | 9.61 | 9.62 | 9.63 | 9.93 | 10.1 | 10.4 | 10.9 | 11.5 | 12.0 | 12.2 | 11.2 | 10.25 |
May 2006 | 8.83 | 1.34 | 1.34 | 22.57 | 9.61 | 9.62 | 9.63 | 9.93 | 10.1 | 10.4 | 10.9 | 11.5 | 12.0 | 12.2 | 11.2 | 10.2 | 9.16 |
. | . | . | . | . | . | . | . | . | . | . | . | . | . | . | . | . | . |
. | . | . | . | . | . | . | . | . | . | . | . | . | . | . | . | . | . |
. | . | . | . | . | . | . | . | . | . | . | . | . | . | . | . | . | . |
November 2023 | 61.36 | 3.43 | 27.85 | 34.79 | 10.2 | 10.3 | 9.7 | 10.7 | 10.2 | 10.2 | 9.5 | 9.6 | 9.7 | 9.2 | 9.1 | 8.5 | 9 |
December 2023 | 61.98 | 3.28 | 28.64 | 34.72 | 10.3 | 9.7 | 10.7 | 10.2 | 10.2 | 9.5 | 9.6 | 9.7 | 9.2 | 9.1 | 8.5 | 9 | 8.8 |
Model-2 | Model-1 | ||||
---|---|---|---|---|---|
Performance Metrics | ANN | SVM | XGBoost | ANN | SVM |
R | 0.462 | 0.577 | 0.448 | 0.697 | 0.149 |
r | 0.68 | 0.76 | 0.67 | 0.835 | 0.387 |
MAE | 0.397 | 0.395 | 0.368 | 0.954 | 0.555 |
RMSE | 0.493 | 0.466 | 0.518 | 1.07 | 0.7 |
MAPE | 0.41 | 0.41 | 0.37 | 0.104 | 0.606 |
Total Number of Instances | 228 | 228 | 228 | 228 | 228 |
The statements, opinions and data contained in all publications are solely those of the individual author(s) and contributor(s) and not of MDPI and/or the editor(s). MDPI and/or the editor(s) disclaim responsibility for any injury to people or property resulting from any ideas, methods, instructions or products referred to in the content. |
Share and Cite
Güler, M.; Kabakçı, A.; Koç, Ö.; Eraslan, E.; Derin, K.H.; Güler, M.; Ünlü, R.; Türkan, Y.S.; Namlı, E. Forecasting of the Unemployment Rate in Turkey: Comparison of the Machine Learning Models. Sustainability 2024 , 16 , 6509. https://doi.org/10.3390/su16156509
Güler M, Kabakçı A, Koç Ö, Eraslan E, Derin KH, Güler M, Ünlü R, Türkan YS, Namlı E. Forecasting of the Unemployment Rate in Turkey: Comparison of the Machine Learning Models. Sustainability . 2024; 16(15):6509. https://doi.org/10.3390/su16156509
Güler, Mehmet, Ayşıl Kabakçı, Ömer Koç, Ersin Eraslan, K. Hakan Derin, Mustafa Güler, Ramazan Ünlü, Yusuf Sait Türkan, and Ersin Namlı. 2024. "Forecasting of the Unemployment Rate in Turkey: Comparison of the Machine Learning Models" Sustainability 16, no. 15: 6509. https://doi.org/10.3390/su16156509
Article Metrics
Further information, mdpi initiatives, follow mdpi.
Subscribe to receive issue release notifications and newsletters from MDPI journals
IMAGES
VIDEO
COMMENTS
Unemployment rates are typically higher for young women than for men, while youth in rural areas face different challenges from their urban peers.
PDF | The aim of this paper is to explain the importance, causes and consequences of youth unemployment and policies to fight it. Global economic crisis... | Find, read and cite all the research ...
As youth unemployment remains elevated following the Great Recession, youth employment programs have received increased scrutiny from policy-makers.
Elasticity of youth unemployment rates with respect to the adult unemployment rate and the youth/adult population ratio and youth/adult relative wage rates (with country and time fixed effects, t-ratios in parentheses).
This policy brief provides a framework for applying behavioral insights to youth unemployment problems, building on rigorous evidence from across the world. Many drivers of youth. Young people are over three inactivity are structural and times more likely to be require traditional interventions. But unemployment and inactivity.
Youth underemployment: A review of research on young people and the problems of less (er) employment in an era of mass education
In this Policy Paper, which is an update of the 2008 Policy Paper on Youth Employment, the Youth Forum identifies the main causes of youth unemployment, including: inequalities on the labour market, a lack of provision of services to young people, and the privatisation of education. It also addresses the need to eradicate discrimination against ...
This edition of the Global Employment Trends for Youth focuses on the impact of tech- nological advances on youth labour markets. It analyses both opportunities and risks for youth in terms of job destruction and creation, the use of digital technology to improve labour market programmes, and sharing productivity gains. Policy responses to address
Wangmo, Deki. From the beginning of the 20th century, unemployment was articulated as an alarming issue in the world. In particular, youth unemployment has gained its concern by wake of the 21st century. There are varying ideas and thoughts about the effects and causes of unemployment in the world. The consequences of unemployment are not short ...
This paper looks at recent trends in youth unemployment and joblessness and seeks to clarify some issues related to the nature of the youth labour market 'problem'.
In 2010, the global youth unemployment rate was 12.6 per cent, dramatically overshadowing the global adult unemployment rate of 4.8 per cent. Even after finding work, young workers continue to ...
The continued high rates of youth unemployment in South Africa present a serious risk to the promotion of an inclusive economy and society. We have assessed existing national evidence about a) the drivers1 of youth unemployment; b) the policies and interventions that have sought to address it; and c) what interventions exist and work to tackle the challenge. Based on an assessment of 1 294 ...
This article pays attention to youth unemployment as one of the most serious socio-economic challenges in South Africa. The nature of unemployment in South Africa is followed by a discussion on the interconnectedness between unemployment and poverty. The psychological and theological meaning of work is discussed in short, followed by the psychological effect of unemployment. In order to ...
In this broader context, this paper presents a profile of youth employment and unemployment in India, which has the world's largest youth population. Young Indians face major barriers because of poverty and low levels of human capital.
85 million young people are unemployed worldwide. Global youth unemployment amounted to 13.5% compared to 6.5% for the overall global unemployment rate and 4.5% for the adult unemployment rate. The ratio of the youth-to-adult unemployment rate is 3. Unemployed youth make up 43.7% of the world's total unemployed.
Toward Solutions for Youth Employment A 2015 Baseline Report 9396_S4YE_Flagship_Report_FRCVR_1604162.indd 1 10/5/15 10:37 AM
The link between youth employment and vulnerability is explored, with an explanation of how sustained periods of unemployment can lead to marginalization or social exclusion.
Persistent youth unemployment and underemployment carry very high social and economic costs and threaten the fabric of our societies. Failure to generate sufficient decent jobs can result in long-lasting "scarring" effects on young people.
Unemployment is the most important problem that countries need to solve in their economic development plans. The uncontrolled growth and unpredictability of unemployment are some of the biggest obstacles to economic development. Considering the benefits of technology to human life, the use of artificial intelligence is extremely important for a stable economic policy.
2.3.3 Youth unemployment 44 2.3.4 Youth inactivity and discouragement 48 2.4 School-to-work transition 49 2.5 Wages and other conditions of work 50 2.6 Conclusions and key challenges 52 Annex 2 - Examples of data analysis Annex 2.1 Main youth labour market indicators 56
The world is currently facing the challenge of giving more and better jobs to young people. Addressing this issue is particularly pressing at a moment of high average of youth unemployment and inactivity across the countries.
The ILC's conclusions highlight the importance of an "enabling environment" for sustainable enterprises.1 This term as presented in this essay contains four elements such as i) the norms and values in a country with regards to entrepreneurship, ii) the policy, legal and regulatory framework in which youth led enterprises operate, iii) the ...