{"title":"Integrating Artificial Neural Network and Taguchi Method on Constructing the Real Estate Appraisal Model","authors":"Mu-Yen Chen, Min-Hsuan Fan, Chia-Chen Chen, Siang-Yu Jhong","volume":93,"journal":"International Journal of Economics and Management Engineering","pagesStart":3010,"pagesEnd":3019,"ISSN":"1307-6892","URL":"https:\/\/publications.waset.org\/pdf\/9999425","abstract":"<p>In recent years, real estate prediction or valuation has<br \/>\r\nbeen a topic of discussion in many developed countries. Improper<br \/>\r\nhype created by investors leads to fluctuating prices of real estate,<br \/>\r\naffecting many consumers to purchase their own homes. Therefore,<br \/>\r\nscholars from various countries have conducted research in real estate<br \/>\r\nvaluation and prediction. With the back-propagation neural network<br \/>\r\nthat has been popular in recent years and the orthogonal array in the<br \/>\r\nTaguchi method, this study aimed to find the optimal parameter<br \/>\r\ncombination at different levels of orthogonal array after the system<br \/>\r\npresented different parameter combinations, so that the artificial<br \/>\r\nneural network obtained the most accurate results. The experimental<br \/>\r\nresults also demonstrated that the method presented in the study had a<br \/>\r\nbetter result than traditional machine learning. Finally, it also showed<br \/>\r\nthat the model proposed in this study had the optimal predictive effect,<br \/>\r\nand could significantly reduce the cost of time in simulation operation.<br \/>\r\nThe best predictive results could be found with a fewer number of<br \/>\r\nexperiments more efficiently. Thus users could predict a real estate<br \/>\r\ntransaction price that is not far from the current actual prices.<\/p>\r\n","references":"[1] J.F.C. Khaw, B.S. Lim, and L.E.N. Lim, \"Optimal design of neural\r\nnetworks using the Taguchi method,\u201d Neurocomputing, vol.7, no.3, pp.\r\n225-245, 1995.\r\n[2] A. Tortum, N. Yayla, C. \u00c7elik, and M. G\u00f6kda\u011f, \"The investigation of\r\nmodel selection criteria in artificial neural networks by the Taguchi\r\nmethod,\u201dPhysica A: Statistical Mechanics and its Applications, vol.386,\r\nno.1,pp. 446-468, 2007.\r\n[3] W.C. Chen, Y.Y. Hsu, L.F. Hsieh, and P.H. Tai, \"A systematic\r\noptimization approach for assembly sequence planning using Taguchi\r\nmethod, DOE, and BPNN,\u201d Expert Systems with Applications, vol.37,\r\nno.1, pp. 716-726, 2010.\r\n[4] K.Y. Chang, \"The optimal design for PEMFC modeling based on Taguchi\r\nmethod and genetic algorithm neural networks,\u201d International Journal of\r\nHydrogen Energy, vol.36, no.21, pp. 13683-13694, 2011.\r\n[5] J.R. Jung, and B.J. Yum, \"Artificial neural network based approach for\r\ndynamic parameter design,\u201d Expert Systems with Applications, vol.38,\r\nno.1,pp. 504-510, 2011.\r\n[6] T.B. Asafa, N. Tabet, and S.A.M. Said, \"Taguchi method\u2013ANN\r\nintegration for predictive model of intrinsic stress in hydrogenated\r\namorphous silicon film deposited by plasma enhanced chemical vapour\r\ndeposition,\u201d Neurocomputing, vol. 106, pp. 86-94, 2013.\r\n[7] C.O. Chang. Real estate in the world: trade, investment, agency, policy,\r\nYuan-Liou Publishing, 1990.\r\n[8] W.J. McCluskey, and A.S. Adair, Computer Assisted Mass Appraisal.\r\n1997.\r\n[9] F. Rosenblatt, \"The perceptron - a perceiving and recognizing automaton,\u201d\r\nCornell Aeronautical Laboratory report, pp.85-460-1, 1957.\r\n[10] W.S. McCulloch, and W. Pitts, \"A logical calculus of the ideas immanent\r\nin nervous activity,\u201d The bulletin of mathematical biophysics, vol.5, no.4,\r\npp. 115-133, 1943.\r\n[11] D.O. Hebb, The organization of behavior: a neuropsychological theory.\r\nJohn Wiley and Sons, 1949.\r\n[12] M. Minsky, and S.Papert, Perceptrons. MIT Press. Cambridge, Ma, 1969.\r\n[13] S. Grossberg, \"Adaptive pattern classification and universal recoding: I.\r\nParallel development and coding of neural feature detectors,\u201d Biological\r\nCybernetics, vol.23, no.3,pp. 121-134, 1976.\r\n[14] T. Kohonen, \"Self-organized formation of topologically correct feature\r\nmaps,\u201d Biological Cybernetics, vol.43, no.1,pp. 59-69, 1982.\r\n[15] J.J. Hopfield, \"Neurons with graded response have collective\r\ncomputational properties like those of two-state neurons,\u201d Proceedings of\r\nthe National Academy of Sciences, vol.81, no.10, pp. 3088-3092, 1984.\r\n[16] D.E. Rumelhart, G.E. Hinton, and R.J. Williams, \"Learning\r\nrepresentations by back-propagating errors,\u201d in Neurocomputing:\r\nfoundations of research, A.A. James and R. Edward, Editors. MIT Press.\r\npp. 696-699, 1986.\r\n[17] H.H. Lee, Taguchi Methods: Principles and Practices of Quality Design.\r\nGauLih Book Publishing (4nd), 2013.\r\n[18] Ministry of the Interior of R.O.C., Monthly Bulletin of Interior Statistics,\r\n2014. Available at: http:\/\/sowf.moi.gov.tw\/stat\/month\/list.htm.\r\n[19] J.R. Quinlan, \"Discovering rules by induction from large collections of\r\nexamples,\u201d Expert Systems in the Microelectronic Age, pp. 168-201,\r\n1979.\r\n[20] J.R. Quinlan, \"Induction of decision trees,\u201d Machine Learning, vol. 1,\r\nno.1, pp. 81-106, 1986.\r\n[21] I.C. Yeh, Neural Network Model: Application and Implementation (9rd),\r\nScholars Book Publishing, 2009.\r\n[22] C. Cortes, and V. Vapnik, \"Support-Vector Networks,\u201d Machine\r\nLearning, vol.20, no.3, pp. 273-297, 1995.\r\n[23] S.S. Keerthi, and C.-J. Lin, \"Asymptotic Behaviors of Support Vector\r\nMachines with Gaussian Kernel,\u201d Neural Computation, vol.15, no.7, pp.\r\n1667-1689, 2003.\r\n[24] C.W. Hsu, C.C. Chang, and C.J. Lin, A practical guide to support vector\r\nclassification. 2003.\r\n[25] R.S. Pindyck, and D.L. Rubinfeld, Econometric models and economic\r\nforecasts. Boston, Mass.: Irwin\/McGraw-Hill, 1998.\r\n[26] J. Mingers, \"An empirical comparison of selection measures for\r\ndecision-tree induction,\u201d Machine Learning, 1vol.3, no.4, pp. 319-342,\r\n1989.\r\n[27] U.M. Fayyad, and K.B. Irani, \"On the handling of continuous-valued\r\nattributes in decision tree generation,\u201d Machine Learning, vol.8, no.1, pp.\r\n87-102, 1992.\r\n[28] T.G. Dietterich, \"Ensemble Methods in Machine Learning, in Multiple\r\nClassifier Systems,\u201d Lecture Notes in Computer Science, vol. 1857, pp.\r\n1-15, 2000.","publisher":"World Academy of Science, Engineering and Technology","index":"Open Science Index 93, 2014"}