Modeling the Open Unemployment Rate on Java Island Using Based on Influencing Factors
Keywords:
Open Unemployment Rate, Semiparametric Regression, Truncated Spline, Cross-Validation, Optimal Knot, Java IslandAbstract
The open unemployment rate is a key indicator reflecting the labor market conditions of a region. Java Island, as the economic hub of Indonesia with a large population, is at risk of facing unemployment issues. This study aims to model the open unemployment rate in Java Island using truncated spline semiparametric regression with optimal knot selection based on the minimum Cross Validation (CV) value. The data used are secondary data from the Central Statistics Agency (BPS) for the year 2024. The data cover 119 regencies/cities on Java and are divided into 80% training data and 20% testing data. The variables used in this study include the minimum wage, the percentage of the poor population, Gross Regional Domestic Product (GRDP), population growth rate, and Labor Force Participation Rate (LFPR). The results show that the best model was obtained using a first-order spline with two knot points, yielding a minimum CV value of 0.994062. Model evaluation shows that the training data achieved a Mean Absolute Error (MAE) of 0.84332 and 0.964139 on the testing data, as well as a Mean Absolute Percentage Error (MAPE) of 19.63% on the training data and 21.29% on the testing data. The coefficient of determination ( ) was 63.66% for the training data and 48.88% for the testing data. The difference in values between the training and testing data indicates that the model is capable of modeling the open unemployment rate with a reasonably good level of prediction accuracy.
References
[1] M. A. A. Pratiwi, R. S. Wijaya, and P. Perdana, “Analysis of Factors Affecting the Open Unemployment Rate,” Formosa Journal of Multidisciplinary Research (FJMR), vol. 4, no. 7, pp. 3069–3082, July 2025, doi: 10.55927/fjmr.v4i7.309.
[2] B. R. Satrio, and Y. P. Utomo, “Analysis of the Influence of Education, Economic Growth, Technological Development, and Wages on Unemployment on Java Island,” in Proc. Int. Conf. Sustainable Innovation, Aug. 2023, pp. 67–72, doi: 10.18196/icosi.v3i1.116.
[3] A. E. Pravitasari, et al., “Spatiotemporal Distribution Patterns and Local Driving Factors of Regional Development in Java,” ISPRS Int. J. Geo-Inf, vol. 10, no. 12, pp. 1–13, Nov. 2021, doi: 10.3390/ijgi10120812.
[4] A. Putri, N. Murialti, and M. Hidayat, “Analysis of the Factors Driving Economic Growth in Central Java,” ” Journal of Islamic Accounting, Management, and Economics (JAM-EKIS), vol. 8, no. 2, pp. 746–755, May 2025, doi: 10.36085/jamekis.v8i2.7789.
[5] P. S. Kinasih, and D. M. Nihayah, “Determinants of Unemployment Among University Graduates on Java Island,” Indonesian Journal of Development Economics, vol. 5, no. 1, pp. 1505–1519, Jan.2022 , doi:10.15294/efficient.v5i1.49150.
[6] S. Akbar, A. S. Herisma, and T. Suharto, “Analysis of Factors Influencing Employment Opportunities in West Java Province in 2015–2020,” Journal of Economic Development and Village Building, vol. 1, no. 1, pp. 53–65, Mar. 2023, doi: 10.59261/jedvb.v1i1.4.
[7] S. Purwandari, and N. Hanifa, “The Effect of Labor Force, Education, and Minimum Wage on Open Unemployment in East Java Province: A Spatial Disparity Approach2020-2024,”, vol. 6, no. 1, pp. 44–57, Dec. 2025, doi: 10.38142/jtep.v6i1.1779.
[8] M. E. Rayhan, and P. M. A. Saputra, “An Analysis of the Determinants of the Unemployment Rate in West Java,” Journal of Development Economics and Social Studies, vol. 4, no. 1, pp. 77–90, Jan. 2025, doi: 10.21776/jdess.2025.04.1.07.
[9] P. C. Amarta, and R. I. S. Setiawati, “Analysis of the Effect of Population, Education Level, and Minimum Wage on the Open Unemployment Rate in West Java Province,” International Journal of Business and Applied Economics (IJBAE), vol. 4, no. 5, pp. 2567–2576, Sep. 2025, doi: 10.55927/ijbae.v4i5.214.
[10] V. M. Santi, N. R. Ningsih, and F. Ladayya, “Analyzing the in Java Using Penalized Spline Nonparametric Regression,” International Journal of Applied Science and Sustainable Development (IJASSD), vol. 4, no. 2, pp. 70–83, Sep. 2022.
[11] S. S. Handajani, H. Pratiwi, Respatiwulan, Y. Susanti, M. B. Nirwana, and L. P. Nareswari, “Truncated Spline Semiparametric Regression to Handle Mixed-Pattern Data in Modeling Rice Production in East Java Province,” BAREKENG: Journal of Mathematics and Its Application, vol. 19, no. 4, pp. 2597–2608, Dec. 2025, doi: 10.30598/barekengvol19iss4pp2597-2608.
[12] H. Nurcahayani, I. N. Budiantara, and I. Zain, “Nonparametric Truncated Spline Regression for Modeling,” IP Conf. Proc.: The2ndInternational Conference on Science, Mathematics, Environment, and Education, , Oct020073-1–020073-8, doi: 10.1063/1.5139805.
[13] D. Fitriana, I. N. Budiantara, and V. Ratnasari, “Semiparametric Truncated Spline Regression for Modeling AHH in Indonesia,” in Proc.3rdInt. Seminar Sci. Technol., Surabaya, Indonesia, vol. 4, no. 1, pp. 26, Aug. 2018, doi: 10.12962/j23546026.y2018i1.3502.
[14] R. D. Fadlirhohim, Sifriyani, and A. T. R. Dani, “Modeling Stunting Prevalence in Indonesia Using Spline Truncated Semiparametric Regression,” , vol. 18, no. 3, pp. 2015–2028, Sep. 2026, doi: 10.30598/barekengvol18iss3pp2015-2026.
[15] Y. V. T. Saputra, Moh. Hafiyusholeh, H. Khaulasari, Y. Farida, and P. K. Intan, “Modeling the Number of Crimes in East Java Using a Truncated Spline Semiparametric Regression Approach,” BAREKENG: Journal of Mathematics and Its Application, vol. 20, no. 2, pp. 1627–1642, Sep. 2025, doi: 10.30598/barekengvol20iss2pp1627-1642.
[16] A. Achmad, R. Fernandes, and B. Hutahayan, “Comparison of Curve Estimation of the Smoothing Spline Nonparametric Function Path Based on PLS and PWLS atLevels of Heteroscedasticity,” IOP Conf. Series: Materials Science and Engineering 546, June 2019, pp. 1–8, doi: 10.1088/1757-899X/546/5/052024.
[17] F. Fadri, K. A. Santoso, and S. N. I. Karsan, “A Semiparametric Regression for Modeling Life Expectancy: Spline Truncated and Fourier Series Estimators," in Proc. 9th Int. Conf. on Research, Implementation, and Education in Mathematical Sciences (ICRIEMS), Advances in Social Science, Education and Humanities Research, vol. 957, Nov. 2025, doi: 10.2991/978-2-38476-481-5_18.
[18] W. Marbun, Suparti, and D. A. I. Maruddani, “Modeling of the Composite Stock Price Index (CSPI) Using Semiparametric Regression with Truncated Splines Based on R GUI,” J. Phys. Conference Series., vol. 1524, no. 1, June 2020, doi: 10.1088/1742-6596/1524/1/012096.
[19] M. Setyawati, N. Chamidah, A. Kurniawan, and D. Aydin, “Confidence Interval for Semiparametric Regression Model Parameters Based on Truncated Spline with Application to COVID-19 Dataset in Indonesia,” Data and Metadata, vol. 3, pp. 1–13, Dec. 2024, doi: 10.56294/dm2024.609.
[20] A. P. Anisar, Sifriyani, and A. T. R. Dani, “Estimation of a Bivariate Truncated Spline Nonparametric Regression Model on Life Expectancy and Prevalence of Underweight Children in Indonesia,” , vol. 17, no. 4, pp. 2011–2022, Dec. 2023, doi: 10.30598/barekengvol17iss4pp2011-2022.
[21] F. Ubaidillah, A. A. R. Fernandes, A. Iriany, N. W. S. Wardhani, and S. Solimun “Truncated Spline Path Analysis Modeling in Company X with the Government’s Role as a Mediating Variable,” Journal of Statistics Application & Probability, vol. 794, no. 3, pp. 781–794, Sep. 2022, doi:10.18576/jsap/110303.
[22] R. L. Eubank, ““Smoothing” in *, 2ed. Boca Raton, FL, USA: CRC Press, 1999.
[23] A. A. D. Lestari, A. T. Damaliana, and D. A. Prasetya, “Implementing GCV and mGCV to Determine Optimal Knot in Spline Regression for East Java Life Expectancy,” International Journal of Advances in Data and Information Systems, vol. 6, no. 2, pp. 242–258, Aug. 2025, doi: 10.59395/ijadis.v6i2.1379.
[24] A. Jierula, S. Wang, T. Oh, and P. Wang, “Applied Sciences Study on Accuracy Metrics for Evaluating the Predictions of Damage Locations in Deep Piles Using Artificial Neural Networks with Acoustic Emission Data,” Appl. Sci, vol. 11, no. 5, Mar. 2021, doi: 10.3390/app11052314.
[25] A. Fayyazbakhsh, T. Kienberger, and J. Vopara-Wrienz, “Comparative Analysis of Load Profile Forecasting: LSTM, SVR, and Ensemble Approaches for Singular and Cumulative Load Categories,” Smart Cities, vol. 8, no. 2, Apr. 2025, doi: 10.3390/smartcities8020065.
