房市商品長年以來一直為國人喜好的投資標的之一，近年來對於房市趨勢的預測及看法意見不斷提出，但多仰賴財經資訊及名嘴建議，無法得到更具客觀及依據性的房價趨勢預測方法。本研究蒐集國內外房價預測相關文獻，彙整出房價趨勢預測的影響因素，並利用統計分析工具(SPSS)篩選出顯著影響房價趨勢預測的影響因子，接著針對時序性因子，應用時序性因子及非時序因子綜合性預測模式(Neural Network + Long-Short Term Memory , NNLSTM)建立台灣與六都(台北市、新北市、桃園市、新竹市、台中市、高雄市)之新屋與中古屋房價指數趨勢預測模式，藉由模式訓練與測試，找出輸入(影響因子)與輸出(房價指數趨勢)的映射關係，做出精準度較高的房價指數趨勢預測。本研究透過文獻彙整與統計分析工具篩選出10個影響因子，接著每個模式根據此10個因子蒐集自2001年Q1至2016年Q4，共64筆歷史資料並建立案例庫，本模式將案例依時間序列進行驗證共12次訓練和測試。台灣及六都之預測結果顯示絕對百分比誤差(Mean Absolute Percent Error, MAPE)值皆小於3%，屬於高精度的預測，有效取代人為主觀經驗之房市判斷，且說明經濟指標與房價指數趨勢是具有相關聯性的。最後將NNLSTM與其他預測模式相比較，其結果亦優於支持向量機(SVM)、最小平方差支持向量機(LS-SVM)、演化式支持向量機推論模式(ESIM)、演化式最小平差支持向量機(ELSIM)生物與共生演算法最小平方差支持向量機(SOS-LSSVM)，表示本研究應用NNLSTM此模式對於存在時序性因子更適合且能有效且準確地做出預測。

Housing products has been one of popular investment decisions for people in Taiwan many years, many prediction and proposal were continued to put forward but most of it were based on financial information and panelists’ opinion, we could not depend on more objective method predicting residential building price trend. This research collected several related literatures of housing price prediction, furthermore, using statistical analysis tools (SPSS) to figure out 10 influence factor of residential building price index trend. Against to the dependent factors, NNLSTM (Neural Network + Long – Short Term Memory) was applied to build Taiwan Residential Building Price Index Trend Prediction Model, including Taiwan, Taipei, New Taipei, Taoyuan, Hsinchu, Taichung, Kaohsiung.
By model training and testing, we can discover the relationship between the input and the output variables to make reasonable house price index trend prediction. According to these variables, each model collected 64 historical data from 2001 Q1 to 2016 Q4 and did it 12 times in training and testing sequentially.
The results showed that every model in this research are high precision forecast, prediction errors were all less than 3% in MAPE. These models effectively replace the human subjective experience of the housing market judgments and showed that economic indicators and housing prices trend are associated.
Compared with other modules, the result were also better than Support Vector Machine (SVM), Least Squares Support Vector Machines (LS-SVM), Evolutionary Support Vector Machine Inference Model (ESIM), Evolutionary Least Squares Support Vector Machine (ELSIM), Symbiotic Organisms Search- Hybrid Least Squares SVM(SOS-LSSVM). The model of this research can predict more effective and precise.

參考文獻
[1] 于宗先，王金利, 台灣土地問題. 聯經出版事業公司, 2001.
[2] I. A. o. A. Officers, Standard on Automated Valuation Models. Chicago: IAAO, 2003.
[3] W. J. McCluskey and A. Adair, Computer assisted mass appraisal: An international review. Ashgate Publishing Limited, 1997.
[4] 賴碧瑩, "應用類神經網路於電腦輔助大量估價之研究," (in 繁體中文), 住宅學報, vol. 16, no. 2, pp. 43-65, 2007.
[5] F. Kong, H. Yin, and N. Nakagoshi, "Using GIS and landscape metrics in the hedonic price modeling of the amenity value of urban green space: A case study in Jinan City, China," Landscape and urban planning, vol. 79, no. 3, pp. 240-252, 2007.
[6] 黃于祐, "台北市房價影響因素之空間分析-地理加權迴歸方法之應用," 都市計劃研究所, 臺北大學, 2007年, 2007.
[7] 古兆民，黃玉霖, "台灣房地產波動性分析-不對稱 T-GARCH 模型的實證," 2012.
[8] 張金鶚，楊宗憲，洪御仁, "中古屋及預售屋房價指數之建立, 評估與整合─ 台北市之實證分析," JOURNAL OF HOUSING, vol. 17, no. 2, 2008.
[9] 林英彥, 不動產估價. 文笙書局股份有限公司, 2006.
[10] 魏如龍, "類神經網路於不動產價格預估效果之研究," 碩士, 地政研究所, 國立政治大學, 台北市, 2003.
[11] 楊謙柔, "都市住環境設施評價模式之研究," 博士, 建築及都市計畫研究所, 中國文化大學, 台北市, 2009.
[12] 劉玉婷, "應用迴歸分析及類神經網路建構不動產估價模式-以台中市住宅為例," 碩士, 營建工程系碩士班, 國立雲林科技大學, 雲林縣, 2009.
[13] 蔡爾逸, "應用支撐向量機(SVM)於都市不動產價格預測之研究," 碩士, 營建管理研究所, 國立中央大學, 桃園縣, 2012.
[14] 張和崇, "應用人工智慧與果蠅演算法對房價預測之比較分析－以臺北市中古屋為例," 碩士, 經濟學系, 東吳大學, 台北市, 2013.
[15] 鄭啓亨, "演化式模糊多元適應性雲形迴歸應用在不動產價格估算之研究," 碩士, 營建工程系營建管理碩士班, 國立台灣科技大學, 台北市, 2015.
[16] B. Park and J. K. Bae, "Using machine learning algorithms for housing price prediction: The case of Fairfax County, Virginia housing data," Expert Systems with Applications, vol. 42, no. 6, pp. 2928-2934, 2015/04/15/ 2015.
[17] V. Plakandaras, R. Gupta, P. Gogas, and T. Papadimitriou, "Forecasting the U.S. real house price index," Economic Modelling, vol. 45, pp. 259-267, 2015/02/01/ 2015.
[18] 張金鶚, 房地產投資與市場分析：理論與實務. 華泰經銷, 2003.
[19] R. A. Dubin, "Predicting House Prices Using Multiple Listings Data," The Journal of Real Estate Finance and Economics, journal article vol. 17, no. 1, pp. 35-59, July 01 1998.
[20] 李艷秋，高海龍, "經濟指標與全國房價的關係分析," 吉林建築工程學院學報, vol. 30, no. 1, pp. 71-73, 2013.
[21] 鄭維瑩, "不動產稅制對不動產價格影響分析－論不動產稅制改革," 碩士, 不動產與城鄉環境學系, 國立臺北大學, 新北市, 2013.
[22] 紀美鳳, "房地合一課徵所得稅研議修法前後對六都房市之影響," 財金論文叢刊, no. 24, pp. 106-123, 2016.
[23] 余佳凱, "以灰色理論應用於房產成屋銷售價格預測之研究-以高雄市為例," 碩士, 經營管理研究所, 樹德科技大學, 高雄市, 2014.
[24] 林秋瑾，黃佩玲, "住宅價格與總體經濟變數關係之研究-以向量自我迴歸模式 (VAR) 進行實證," 政大學報, vol. 71, pp. 143-160, 1995.
[25] 汪新，谢昌浩, "我国房价的宏观经济影响因素分析-基于 PLS 方法的实证研究(in 簡體中文)," 華東經濟管理, vol. 24, no. 3, pp. 53-57, 2010.
[26] A. Beltratti and C. Morana, "International house prices and macroeconomic fluctuations," Journal of Banking & Finance, vol. 34, no. 3, pp. 533-545, 2010.
[27] 葉怡成, 類神經網路模式應用與實作. 儒林出版社, 2009.
[28] 賀志強，馮寅, "長的短時記憶(LSTM)在五聲調適合聲的應用," 福建電腦, no. 4, pp. 101-102, 2007.
[29] S. Hochreiter and J. Schmidhuber, "Bridging long time lags by weight guessing and “Long Short-Term Memory”," Spatiotemporal models in biological and artificial systems, vol. 37, pp. 65-72, 1996.
[30] F. A. Gers and J. Schmidhuber, "Recurrent nets that time and count," in Neural Networks, 2000. IJCNN 2000, Proceedings of the IEEE-INNS-ENNS International Joint Conference on, 2000, vol. 3, pp. 189-194: IEEE.
[31] W. Zaremba, I. Sutskever, and O. Vinyals, "Recurrent neural network regularization," arXiv preprint arXiv:1409.2329, 2014.
[32] M.-Y. Cheng and C. Ko, "Computer-aided decision support system for disaster prevention of hillside residents," in Proceedings of the 17th IAARC/CIB/IEEE/IFAC/IFR International Symposium on Automation and Robotics in Construction, Taipei, Taiwan, 2000, pp. 587-592.
[33] K. Fukahori and Y. Kubota, "Consistency evaluation of landscape design by a decision support system," Computer‐Aided Civil and Infrastructure Engineering, vol. 15, no. 5, pp. 342-354, 2000.
[34] S. Sundin and C. Braban‐Ledoux, "Artificial intelligence–based decision support technologies in pavement management," Computer‐Aided Civil and Infrastructure Engineering, vol. 16, no. 2, pp. 143-157, 2001.
[35] M.-Y. Cheng and Y.-W. Wu, "Evolutionary support vector machine inference system for construction management," Automation in Construction, vol. 18, no. 5, pp. 597-604, 2009.
[36] M.-Y. Cheng, P. M. Firdausi, and D. Prayogo, "High-performance concrete compressive strength prediction using Genetic Weighted Pyramid Operation Tree (GWPOT)," Engineering Applications of Artificial Intelligence, vol. 29, pp. 104-113, 2014.
[37] M.-Y. Cheng and M.-T. Cao, "Evolutionary multivariate adaptive regression splines for estimating shear strength in reinforced-concrete deep beams," Engineering Applications of Artificial Intelligence, vol. 28, pp. 86-96, 2014.
[38] M.-Y. Cheng, D. K. Wibowo, D. Prayogo, and A. F. Roy, "Predicting productivity loss caused by change orders using the evolutionary fuzzy support vector machine inference model," Journal of Civil Engineering and Management, vol. 21, no. 7, pp. 881-892, 2015.
[39] M.-Y. Cheng, N.-D. Hoang, and Y.-W. Wu, "Hybrid intelligence approach based on LS-SVM and Differential Evolution for construction cost index estimation: A Taiwan case study," Automation in Construction, vol. 35, pp. 306-313, 2013.
[40] M.-Y. Cheng and A. F. Roy, "Evolutionary fuzzy decision model for cash flow prediction using time-dependent support vector machines," International Journal of Project Management, vol. 29, no. 1, pp. 56-65, 2011.
[41] D. Prayogo, "A Novel Genetic Algorithm-Based Evolutionary Support Vector Machine for Optimizing High-Performance Concrete," Department of Construction Engineering, National Taiwan University of Science and Technology, Taiwan, 2012.
[42] M.-Y. Cheng, D. Prayogo, and Y.-W. Wu, "Novel genetic algorithm-based evolutionary support vector machine for optimizing high-performance concrete mixture," Journal of Computing in Civil Engineering, vol. 28, no. 4, p. 06014003, 2013.
[43] 楊智民、劉廣利, 不確定性支持向量機原理及應用. 中國: 科學出版社, 2006.
[44] M.-Y. Cheng and N.-D. Hoang, "Evolutionary Least Squares Support Vector Machine–Userguide," Technical Report, CIC Lab, National Taiwan Univ. of Sci. and Tech2012.
[45] 吳育偉，鄭明淵, "支持向量機最佳化模式-應用於營建管理決策," 第 11 屆營建工程與管理學術研討會, 2007.
[46] K. Price, R. M. Storn, and J. A. Lampinen, Differential evolution: a practical approach to global optimization. Springer Science & Business Media, 2006.
[47] N.-D. Hoang, "Decision Support System for Construction Management Based on Evolutionary Least Squares Support Vector Machine," PhD Dissertation, CIC Lab, National Taiwan Univ. of Sci. and Tech, 2013.
[48] M.-Y. Cheng and D. Prayogo, "Symbiotic organisms search: a new metaheuristic optimization algorithm," Computers & Structures, vol. 139, pp. 98-112, 2014.
[49] D. Prayogo, "An Innovative Parameter-Free Symbiotic Organisms Search (SOS) for Solving Construction-Engineering Problems," PhD thesis, Department of Construction Engineering, National Taiwan University of Science and Technology, 2015.
[50] M.-Y. Cheng, D. Prayogo, and D.-H. Tran, "Optimizing multiple-resources leveling in multiple projects using discrete symbiotic organisms search," Journal of Computing in Civil Engineering, vol. 30, no. 3, p. 04015036, 2015.
[51] D.-H. Tran, M.-Y. Cheng, and D. Prayogo, "A novel Multiple Objective Symbiotic Organisms Search (MOSOS) for time–cost–labor utilization tradeoff problem," Knowledge-Based Systems, vol. 94, pp. 132-145, 2016.
[52] M.-Y. Cheng et al., "SOS optimization model for bridge life cycle risk evaluation and maintenance strategies," Journal of the Chinese Institute of Civil and Hydraulic Engineering Volume 26, no. 4, 2014.
[53] M.-Y. Cheng, D. Prayogo, and Y.-W. Wu, "Predicting the Pavement Rutting Behavior of Asphalt Mixtures Using Symbiotic Organisms Search-Least Squares Support Vector Machine Inference Model," Construction and Building Materials.
[54] 黃佩玲, "住宅價格與總體經濟變數關係之研究—以向量自我迴歸模式 (VAR) 進行實證," 碩士論文, 國立政治大學地政研究所, 1994.
[55] 陳益財, "總體經濟、金融政策與房地產市場景氣對房價影響之研究," 碩士, 財務金融學系財務管理碩士班, 南華大學, 嘉義縣, 2014.
[56] 馮郁婷, "總體經濟對房地產價格之非線性影響---台北、香港之比較," 碩士, 財務金融學系碩士班, 淡江大學, 新北市, 2015.
[57] 呂珍珍, "房價與經濟指標之關聯性," 碩士, 金融研究所, 國立高雄第一科技大學, 高雄市, 2014.
[58] 張誌文, "影響房地產價格之總體經濟因素分析," 碩士, 經濟學研究所, 國立臺灣大學, 台北市, 2011.
[59] 孟庆斌，荣晨, "宏观经济因素对房地产价格的长短期影响(in 簡體中文)," 统计研究, no. 6, pp. 25-32, 2014.
[60] 游淑滿, "住宅成本與總體經濟因素對房價之實證分析, 國立屏東商業技術學院不動產經營系碩士論文," 2006.