Minimum wage prediction based on K-Mean clustering using neural based optimized Minkowski Distance Weighting

  • Abstract
  • Keywords
  • References
  • PDF
  • Abstract

    Minimum Wage is a minimum standard used by employers to provide wages to workers in their business environment. The national minimum wage is the average of the provincial minimum wage. There are many factors need to be considered to set a minimum wage. The aim of this study is to predict the minimum wage based on K-Mean clustering concept. The Minkowski Distance Weighting (MDW) then used to estimate a value at the observation point in a cluster by using a linear combination of values of all cluster members around observation point mapped in 3-dimensional Cartesian coordinates. The prediction result by MDW then optimized by Artificial Neural Network Back Propagation (ANN-BP) to obtain a smaller Mean Absolute Percentage Error (MAPE). The net structure which already trained then used to predict the minimum wage for next year.



  • Keywords

    minimum wage; K-Mean clustering algorithm; MDW method; ANN-BP

  • References

      [1] J. M. Merigó and M. Casanovas, “A new minkowski distance based on induced aggregation operators,” Int. J. Comput. Intell. Syst., vol. 4, no. 2, pp. 123–133, 2011.

      [2] J. M. Merigó and A. M. Gil-lafuente, “Using the OWA Operator in the Minkowski Distance,” Int. J. Econ. Manag. Eng., vol. 2, no. 9, pp. 1032–1040, 2008.

      [3] BPS - Statistics Indonesia, Statistical Yearbook of Indonesia 2005/2006. Jakarta: BPS - Statistics Indonesia, 2006.

      [4] BPS - Statistics Indonesia, Statistical Yearbook of Indonesia 2008. Jakarta: BPS - Statistics Indonesia, 2008.

      [5] BPS - Statistics Indonesia, Statistical Yearbook of Indonesia 2011. BPS - Statistics Indonesia, 2011.

      [6] BPS - Statistics Indonesia, Statistical Yearbook of Indonesia 2014. Jakarta: BPS - Statistics Indonesia, 2014.

      [7] BPS - Statistics Indonesia, Statistical Yearbook of Indonesia 2017. Jakarta: BPS-Statistics Indonesia, 2017.

      [8] A. S. Ahmar, “Sutte Indicator : an Approach to Predicting the Direction of Stock Market Movement,” Songklanakarin J. Sci. Technol., 2017.

      [9] A. S. Ahmar, “International Journal of Economics and Financial Issues Sutte Indicator: A Technical Indicator in Stock Market,” Int. J. Econ. Financ. Issues, vol. 7, no. 2, pp. 1–4, 2017.

      [10] A. Rahman and A. S. Ahmar, “Forecasting of primary energy consumption data in the United States: A comparison between ARIMA and Holter-Winters models,” in AIP Conference Proceedings, 2017, vol. 1885.

      [11] A. S. Ahmar et al., “Modeling Data Containing Outliers using ARIMA Additive Outlier (ARIMA-AO),” J. Phys. Conf. Ser., vol. 954, 2018.

      [12] A. S. Ahmar, “A Comparison of α-Sutte Indicator and ARIMA Methods in Renewable Energy Forecasting in Indonesia,” Int. J. Eng. Technol., vol. 7, no. 1.6, pp. 9–11, 2018.

      [13] E. Rama Kalaivani, E. R. Marivendhan, and N. Suma, “Prediction of diabetes with hybrid prediction model using big data in health care,” Int. J. Eng. Technol., vol. 7, no. 13, pp. 21–23, 2018.

      [14] E. Oktavia, Widyawan, and I. W. Mustika, “Inverse distance weighting and kriging spatial interpolation for data center thermal monitoring,” Proc. - 2016 1st Int. Conf. Inf. Technol. Inf. Syst. Electr. Eng. ICITISEE 2016, pp. 69–74, 2016.

      [15] M. H. Beale, M. T. Hagan, and H. B. Demuth, Neural Network ToolboxTM MATLAB R2015a – User’s Guide. The MathWorks, Inc., 2015.




Article ID: 12741
DOI: 10.14419/ijet.v7i2.2.12741

Copyright © 2012-2015 Science Publishing Corporation Inc. All rights reserved.