Machine Learning Ensemble Modelling for Predicting Unemployment Duration
Source abstract
Abstract
Predictions of the unemployment duration of the economically active population play a crucial assisting role for policymakers and employment agencies in the well-organised allocation of resources (tied to solving problems of the unemployed, whether on the labour supply or demand side) and providing targeted support to jobseekers in their job search. This study aimed to develop an ensemble model that can serve as a reliable tool for predicting unemployment duration among jobseekers in Slovakia. The ensemble model was developed using real data from the database of jobseekers (those registered as unemployed and actively searching for a job through the Local Labour Office, Social Affairs, and Family) using the stacking method, incorporating predictions from three individual models: CART, CHAID, and discriminant analysis. The final meta-model was created using logistic regression and indicates an overall accuracy of the prediction of unemployment duration of almost 78%. This model demonstrated high accuracy and precision in identifying jobseekers at risk of long-term unemployment exceeding 12 months. The presented model, working with real data of a robust nature, represents an operational tool that can be used to check the functionality of the current labour market policy and to solve the problem of long-term unemployed individuals in Slovakia, as well as in the creation of future government measures aimed at solving the problem of unemployment. The measures from the state are financed from budget funds, and by applying the appropriate model, it is possible to arrive at the rationalization of the financing of these measures, or to specifically determine the means intended to solve the problem of long-term unemployment in Slovakia (this, together with the regional disproportion of unemployment, is considered one of the most prominent problems in the labour market in Slovakia). The model also has the potential to be adapted in other economies, taking into account country-specific conditions and variables, which is possible due to the data-mining approach used.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Fault Detection and Control Systems · Scheduling and Optimization Algorithms · AI and HR Technologies
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
Department of Economics, Faculty of Operation and Economics of Transport and Communications, University of Zilina, 010 26 Zilina, Slovakia
Funding
Operational Program Integrated Infrastructure for the project
References (64)
Show source-provided references
1. Achdut, N., and Refaeli, T. (2020). Unemployment and Psychological Distress among Young People during the COVID-19 Pandemic: Psychological Resources and Risk Factors. Int. J. Environ. Res. Public Health, 17.10.3390/ijerph17197163 ↗
2. Job Displacement, Unemployment, and Crime: Evidence from Danish Microdata and Reforms10.1093/jeea/jvz054 ↗
3. Labour Market Policy and Unemployment10.1016/0014-2921(94)00065-8 ↗
4. Baliak, M., and Belin, M. (2020). The Current State of Unemployment and Its Short-Term Forecast [Aktualny Stav Nezamestnanosti a Jej Kratkodoba Prognoza], Institute of Social Policy.
5. Youth Unemployment in Slovakia and in Slovenia
6. Youth Unemployment and Active Labor Market Policies in Europe10.1186/s40173-016-0057-x ↗
7. Active Labour Market Policies of Selected European Countries and Their Competitiveness
8. What Works? A Meta Analysis of Recent Active Labor Market Program Evaluations10.1093/jeea/jvx028 ↗
9. Prediction of Unemployment Rates with Time Series and Machine Learning Techniques10.1007/s10614-019-09908-9 ↗
10. Viljanen, M., and Pahikkala, T. (2020). Research Challenges in Information Science, Springer International Publishing.
11. What Gets Them Going? The Effects of Activation Policies on Personal Change Processes of Unemployed Youth10.1080/13639080.2021.1953694 ↗
12. Prasasti, N., and Ohwada, H. (2014, January 27–29). Applicability of Machine-Learning Techniques in Predicting Customer Defection. Proceedings of the 2014 International Symposium on Technology Management and Emerging Technologies, Bandung, Indonesia.10.1109/ISTMET.2014.6936498 ↗
13. Shinde, P.P., and Shah, S. (2018, January 16–18). A Review of Machine Learning and Deep Learning Applications. Proceedings of the 2018 Fourth International Conference on Computing Communication Control and Automation (ICCUBEA), Pune, India.10.1109/ICCUBEA.2018.8697857 ↗
14. Can Machine Learning on Economic Data Better Forecast the Unemployment Rate?10.1080/13504851.2019.1688237 ↗
15. Werken, L., and Smit, V. (2023, May 01). Exploring the Use of Recurrent Neural Networks for Predicting Inflation and Unemployment. Available online: https://www.researchgate.net/profile/Victoria-Smit/publication/337171301_Exploring_the_Use_of_Recurrent_Neural_Networks_for_predicting_Inflation_and_Unemployment/links/5dc9bdfa299bf1a47b2ff69c/Exploring-the-Use-of-Recurrent-Neural-Networks-for-predicting-Inflation-and-Unemployment.pdf.
16. Prediction of Labor Unemployment Based on Time Series Model and Neural Network Model
17. Determinants of Unemployment Duration in Ukraine10.1016/j.jce.2006.02.006 ↗
18. Arslan, H., and Senturk, I. (2023, May 01). Individual Determinants of Unemployment Duration in Turkey. Available online: https://hdl.handle.net/20.500.12881/3649.
19. Determinants of Increasing Duration of First Unemployment among First Degree Holders in Rwanda: A Logistic Regression Analysis10.1080/13639080.2016.1165343 ↗
20. Predicting Low Employability Graduates: The Case of Universiti Utara Malaysia10.1142/S0217590810003870 ↗
21. The Determinants of Youth Unemployment: A Panel Data Analysis of OECD Countries
22. Determinants of Unemployment in the European Union
23. The Impact of Macroeconomic and Structural Factors on the Unemployment of Young Women and Men10.1007/s10644-021-09341-9 ↗
24. Forecasting Unemployment in the Euro Area with Machine Learning10.1002/for.2824 ↗
25. Gong, J., and Lee, C.-T. (2022, January 15–17). Research on Unemployment Rate Based on Machine Learning Method: A Case Study of United States from 1976 to 1986. Proceedings of the International Conference on Cyber Security, Artificial Intelligence, and Digital Economy (CSAIDE 2022), Huzhou, China.10.1117/12.2647799 ↗
26. Kaya, C., Bishop, M., and Torres, A. (2023). The Impact of Work Incentives Benefits Counseling on Employment Outcomes: A National Vocational Rehabilitation Study. J. Occup. Rehabil.10.1007/s10926-022-10092-1 ↗
27. Drivers of Hiring Discrimination for Individuals with Disabilities10.1007/s10926-008-9136-1 ↗
28. Ho, T.-W. (2023, July 01). Forecasting Unemployment via Machine Learning: The Use of Average Windows Forecasts. Available online: https://ssrn.com/abstract=3496138.
29. Determinants of Youth Unemployment Rate: Case of Slovakia10.24136/eq.2022.013 ↗
30. Structural and Cyclical Drivers of Unemployment Rate
31. Estimating ARIMA–ARCH Model Rate of Unemployment in Slovakia
32. Short-Term Forecasting of the US Unemployment Rate10.1002/for.2630 ↗
33. Forecasting Unemployment with Internet Search Data: Does It Help to Improve Predictions When Job Destruction Is Skyrocketing?10.1016/j.techfore.2014.12.005 ↗
34. Forecasting Unemployment Using Internet Search Data via PRISM10.1080/01621459.2021.1883436 ↗
35. Ensemble Deep Learning: A Review10.1016/j.engappai.2022.105151 ↗
36. Ensemble Modeling, Uncertainty and Robust Predictions10.1002/wcc.220 ↗
37. Combining Bagging and Boosting
38. Supervised Machine Learning: A Review of Classification Techniques
39. Adamko, P., and Siekelova, A. (2017, January 4–5). An Ensemble Model for Prediction of Crisis in Slovak Companies. Proceedings of the 17th International Scientific Conference Globalization and Its Socio-Economic Consequences: Proceedings, Rajecke Teplice, Slovakia. Part I.
40. Ensemble with Neural Networks for Bankruptcy Prediction10.1016/j.eswa.2009.10.012 ↗
41. Pavlicko, M., Durica, M., and Mazanec, J. (2021). Ensemble Model of the Financial Distress Prediction in Visegrad Group Countries. Mathematics, 9.10.3390/math9161886 ↗
42. Bhagia, D. (2023). Duration Dependence and Heterogeneity: Learning from Early Notice of Layoff. arXiv.
43. The Nature of Long-Term Unemployment: Predictability, Heterogeneity and Selection
44. Decision Tree Methods: Applications for Classification and Prediction
45. Breiman, L., Friedman, J.H., Olshen, R.A., and Stone, C.J. (1984). Classification and Regression Trees, Wadsworth & Brooks/Cole Advanced Books & Software.
46. The CART Decision Tree for Mining Data Streams10.1016/j.ins.2013.12.060 ↗
47. Comparative Analysis of Decision Tree Classification Algorithms
48. A Classification and Regression Tree Algorithm for Heart Disease Modeling and Prediction10.1016/j.health.2022.100130 ↗
49. An Exploratory Technique for Investigating Large Quantities of Categorical Data
50. CHAID Decision Tree: Methodological Frame and Application10.1515/ethemes-2016-0029 ↗
51. McArdle, J.J., and Ritschard, G. (2013). Contemporary Issues in Exploratory Data Mining in Behavioral Sciences, Routeledge.10.4324/9780203403020 ↗
52. McLachlan, G.J. (2004). Discriminant Analysis and Statistical Pattern Recognition, John Wiley & Sons.
53. The Use of Multiple Measurements in Taxonomic Problems10.1111/j.1469-1809.1936.tb02137.x ↗
54. Some Theory for Fisher’s Linear Discriminant Function, “Naive Bayes”, and Some Alternatives When There Are Many More Variables than Observations10.3150/bj/1106314847 ↗
55. Tabachnick, B.G., Fidell, L.S., and Ullman, J.B. (2019). Using Multivariate Statistic, Pearson. [7th ed.].
56. Gajdosikova, D., Lăzăroiu, G., and Valaskova, K. (2023). How Particular Firm-Specific Features Influence Corporate Debt Level: A Case Study of Slovak Enterprises. Axioms, 12.10.3390/axioms12020183 ↗
57. Hosmer, D.W., Lemeshow, S., and Sturdivant, R.X. (2013). Applied Logistic Regression, Wiley. [3rd ed.].10.1002/9781118548387 ↗
58. Agresti, A. (2015). Foundations of Linear and Generalized Linear Models, Wiley. [2nd ed.].
59. (2004). Act No. 5/2004 Coll. on Employment Services and on Amending Certain Laws, Ministry of Labour, Social Affairs and Family, Slovakia.
60. Brownlee, J. (2014). Classification Accuracy Is Not Enough: More Performance Measures You Can Use, Machine Learning Mastery.
61. Duration Dependence and Labor Market Conditions: Evidence from a Field Experiment10.1093/qje/qjt015 ↗
62. Effect of Labour Code Reform on Unemployment Duration in the Course of Crisis: Evidence from Slovakia
63. Jallouli, R., Zaiane, O.R., Bach Tobji, M.A., Srarfi Tabbane, R., and Nijholt, A. (2017, January 4–6). Intermediation and Decision Support System for the Management of Unemployment: The Simulator of Duration. Proceedings of the Digital Economy. Emerging Technologies and Business Innovation, Sidi Bou Said, Tunisia.10.1007/978-3-319-62737-3 ↗
64. Long-Term Unemployment in Economic Boom and Bust: The Case of Estonia10.3176/tr.2011.3.01 ↗