購屋者常因不會估價而買到不合理的價格，雖然過去有許多學者提出不同房價預測的方法，但是預測的房價與實際價格仍有許多誤差，因此，如何減少預測房價的誤差是一個重要的議題。

本研究提出二階段的研究程序，第一階段為建構房屋估價模式，首先透過回顧過去不動產估價作業程序文獻後，建構房屋估價模式雛型，接著，本研究以機器學習理論為基礎，提出PSO-SVRXGBoost模型，以建構房價預測模型，最後將房屋估價模式雛型與房價預測模型結合，建構出嶄新的房屋估價模式。第二階段，為了讓購屋者快速獲得估價的結果，本研究透過雛型開發法，開發房屋估價系統，以輔助購屋者做使用。

本研究以台北市實價登錄的資料檢驗本研究提出的PSO-SVRXGBoost的績效，結果顯示房價預測值誤差低於SVR和XGBoost。此外，經過滿意度分析，94%的購屋者對於本研究開發的房屋估價系統相當滿意。

最後，本研究提出的二階段的研究程序，可提供後續研究人員加以沿用與擴充。本研究所使用的五步驟開發程序及滿意度評估亦可作為日後建構房屋估價系統之參考，降低開發風險與提升系統品質。對於購屋者而言，本研究開發之系統可以自動估價，解決以往不知如何委託或是尋找專業估價師的問題，並可快速瞭解房屋的價值。對於不動產業者而言，本研究之結果可以減少房價預測的誤差值，以更準確地估價。

House buyers often buy unreasonable prices due to their inability to evaluate. Although many scholars have put forward different methods for predicting house prices in the past, there are still many errors between the predicted house prices and the actual prices. Therefore, how to reduce the error of predicting house prices is an important issue.

The first stage is to construct the housing valuation model. First, the prototype of the housing valuation model is constructed after reviewing the literature of the past real estate valuation operation procedures. Then, based on the machine learning theory, the PSO-SVRXGBoost model is proposed to construct the housing price prediction model. Finally, combining the housing valuation model with the housing price forecast model, a new housing valuation model is constructed. In the second stage, in order to enable buyers to quickly obtain the appraisal results, this study developed a housing appraisal system through the prototype development method to assist buyers to use.

In this study, the performance of PSO-SVRXGBoost proposed in this study was tested with the real price registration data of Taipei City, and the results show that the error of housing price prediction value is lower than SVR and XGBoost. In addition, after satisfaction analysis, 94% of buyers are quite satisfied with the house appraisal system developed in this study.

Finally, This study proposes a two-stage research procedure that can be followed and expanded by subsequent researchers. The five-step development procedure and satisfaction evaluation used in this study can also be used as a reference for the future construction of housing appraisal system, reducing development risk and improving system quality. For home buyers, the system developed in this study can automatically evaluate, solve the problem of how to entrust or find a professional appraiser in the past, and can quickly understand the value of the house. For realtors, the results of this study can reduce the error value of housing price prediction, so as to achieve more accurate valuation.

摘　要 i
ABSTRACT iii
誌謝 v
目錄 vi
表目錄 viii
圖目錄 ix
一、 緒論 1
1.1 研究背景 1
1.2 研究動機 2
1.3 研究目的 11
1.4 論文架構 12
二、 文獻回顧 14
2.1 房屋估價方法 14
2.2 影響房價的因素 16
2.3 粒子群演算法 19
2.4 支持向量機 22
2.5 極限梯度提升 26
2.6 資訊系統成功模式 29
三、 研究方法 30
3.1 第一階段：建構房屋估價模式 31
3.1.1 建構房屋估價模式雛型 31
3.1.2 建構房價預測模型 31
3.1.3 評估模型 37
3.1.4 建構嶄新的房屋估價模式 38
3.2 第二階段：開發房屋估價系統 39
3.2.1 雛型開發法 39
3.2.2 (一)：需求分析 39
3.2.3 (二)：系統分析 41
3.2.4 (三)：系統設計 42
3.2.5 (四)：系統開發 42
3.2.6 (五)：房屋估價系統滿意度調查 42
四、 研究結果 43
4.1 第一階段：建構房屋估價模式之結果 43
4.1.1 建構房屋估價模式雛型 43
4.1.2 建構房價預測模型結果 44
4.1.3 評估模型結果 52
4.1.4 建構嶄新的房屋估價模式結果 55
4.2. 第二階段：開發房屋估價系統之結果 56
4.2.1 (一)：需求分析結果 56
4.2.2 (二)：系統分析結果 57
4.2.3 (三)：系統設計結果 57
4.2.4 (四)：系統開發結果 58
4.2.5 (五)：房屋估價系統滿意度調查結果 59
4.2.6 個案示例 61
五、 結論與建議 63
5.1 結論 63
5.2 研究貢獻 64
5.2.1 學術貢獻 64
5.2.2 實務貢獻 64
5.3 管理意涵 64
5.4 研究限制 65
5.5 未來研究建議 65
參考文獻 67
附錄一、房屋估價系統滿意度調查問卷 72

中文
[1]內政部 (2013)。不動產估價技術規則。全國法規資料庫。https://law.moj.gov.tw/LawClass/LawAll.aspx?pcode=D0060077(擷取日期
2021/07/21)
[2]內政部 (2021)。內政部不動產交易實價查詢服務網。內政部。https://lvr.land.moi.gov.tw/(擷取日期2021/08/05)
[3]公職王資訊網(2021)。不動產估價師高考錄取率與錄取人數歷年統計。公職王資訊網。https://www.public.com.tw/exam-license/appraiser-quota(擷取日期2021/06/08)
[4]毛麗琴（2009）。房屋價格預測模型分析－以高雄市區爲例。商業現代化學刊，5(1)，31-42。
[5]江穎慧（2009）。不動產自動估價與估價師個別估價之比較－以比較法之案例選取、權重調整與估值三階段差異分析。住宅學報，18(1)，39-62。
[6]沈育生、林秋瑾（2012）。不同人工神經網路架構在不動產大量估價之應用與比較。臺灣土地研究，15(1)，1-29。
[7]林祖嘉、馬毓駿（2007）。特徵方程式大量估價法在台灣不動產市場之應用。住宅學報，16(2)，1-22。
[8]張怡文、江穎慧、張金鶚（2009）。分量迴歸在大量估價模型之應用－非典型住宅估價之改進。都市與計劃，36(3)，281-304。
[9]陳奉瑤（2008）。不動產估價師之教育、考試與執業分析。國家菁英季刊，4(4)，141-158。
[10]董呈煌、李春長、陳俊麟、吳韻玲（2016）。SVR與OLS在住宅價格預測正確率的比較。住宅學報，25(2)，31-51。
[11]蔡瑞煌、高明志、張金鶚（1999）。類神經網路應用於戶地產估價之研究。住宅學報，(8)，1-20。
[12]賴碧瑩（2007）。應用類神經網路於電腦輔助大量估價之研究。住宅學報，16(2)，43-65。
[13]賴碧瑩（2014）。現代不動產估價：理論與實務（第二版），智勝文化。
[14]龔永香、江穎慧、張金鶚（2007）。客觀標準化不動產估價之可行性分析－市場比較法應用於大量估價。住宅學報，16(2)，23-42。
 
英文
[1]Abarna P, A. R. K. M. (2021). A hybrid network model for effective house price prediction -a combination of ML algorithms. International Journal of Advanced Engineering Science and Information Technology, 4(4), 58-62.
[2]Abraham, A. (2005). Artificial Neural Networks. In Handbook of Measuring System Design. John Wiley & Sons.
[3]Ahtesham, M., Bawany, N. Z., & Fatima, K. (2020, November, 28-30). House Price Prediction using Machine Learning Algorithm - The Case of Karachi City, Pakistan [Paper presentation]. 2020 21st International Arab Conference on Information Technology (ACIT), Giza, Egypt.
[4]Bally, L., Brittan, J., & Wagner, K. H. (1977). A prototype approach to information system design and development. Information & Management, 1(1), 21-26.
[5]Carbone, R., & Longini, R. L. (1977). A feedback model for automated real estate assessment. Management Science, 24(3), 241-248.
[6]Chen, T., & Guestrin, C. (2016, August, 13-17). Xgboost: a scalable tree boosting system [Paper presentation]. Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, San Francisco, California, USA.
[7]Chin, W. M., Kit, N. L. W., & Fei, J. L. W. (2019, July, 8). Valuation of real estate: a multiple regression approach [Paper presentation]. Proceedings of the 2019 2nd International Conference on Mathematics and Statistics, Prague, Czech Republic.
[8]Cortes, C., & Vapnik, V. (1995). Support-Vector Networks. Machine Learning, 20(3), 273-297.
[9]Cui, S., Yin, Y., Wang, D., Li, Z., & Wang, Y. (2021). A stacking-based ensemble learning method for earthquake casualty prediction. Applied Soft Computing, 101, 107038.
[10]Cupal, M. (2014). The comparative approach theory for real estate valuation. Procedia - Social and Behavioral Sciences, 109, 19-23.
[11]Dawidowicz, A., Radzewicz, A., & Renigier-Biłozor, M. (2014). Algorithm for purposes of determining real estate markets efficiency with help of land administration system. Survey Review, 46(336), 189-204.
[12]DeLone, W. H., & McLean, E. R. (1992). Information systems success: the quest for the dependent variable. Information systems research, 3(1), 60-95.
[13]Do, Q., & Grudnitski, G. (1993). A neural network analysis of the effect of age on housing values. Journal of Real Estate Research, 8(2), 253-264.
[14]Eberhart, & Yuhui, S. (2001, May, 27-30). Particle swarm optimization: developments, applications and resources [Paper presentation]. Proceedings of the 2001 Congress on Evolutionary Computation (IEEE Cat. No.01TH8546), Seoul, Korea (South).
[15]Frew, J., & Jud, G. (2003). Estimating the value of apartment buildings. Journal of Real Estate Research, 25(1), 77-86.
[16]Gu, J., Zhu, M., & Jiang, L. (2011). Housing price forecasting based on genetic algorithm and support vector machine. Expert Systems with Applications, 38(4), 3383-3386.
[17]Gu, Y., Zhang, D., & Bao, Z. (2021). A new data-driven predictor, PSO-XGBoost, used for permeability of tight sandstone reservoirs: A case study of member of chang 4+5, western Jiyuan Oilfield, Ordos Basin. Journal of Petroleum Science and Engineering, 199, 108350.
[18]He, Y., Ma, W. J., & Zhang, J. P. (2016). The parameters selection of PSO algorithm influencing on performance of fault diagnosis. MATEC Web of Conferences, 63, 02019.
[19]Hsu, C.-W., & Lin, C.-J. (2002). A comparison of methods for multiclass support vector machines. IEEE Transactions on Neural Networks, 13(2), 415-425.
[20]Ibrahem Ahmed Osman, A., Najah Ahmed, A., Chow, M. F., Feng Huang, Y., & El-Shafie, A. (2021). Extreme gradient boosting (Xgboost) model to predict the groundwater levels in selangor malaysia. Ain Shams Engineering Journal, 12(2), 1545-1556.
[21]J.Avanijaa, Sunithab, G., Madhavic, K. R., Korad, P., & Vittale, R. H. S. (2021). Prediction of house price using xgboost regression algorithm. Turkish Journal of Computer and Mathematics Education, 12(2), 2115-2155.
[22]Jiang, H., He, Z., Ye, G., & Zhang, H. (2020). Network intrusion detection based on PSO-Xgboost model. IEEE Access, 8, 58392-58401.
[23]Kennedy, J., & Eberhart, R. (1995, November, 27-December,1). Particle swarm optimization [Paper presentation]. Proceedings of ICNN'95 - International Conference on Neural Networks, Perth, WA, Australia.
[24]Kontrimas, V., & Verikas, A. (2011). The mass appraisal of the real estate by computational intelligence. Applied Soft Computing, 11(1), 443-448.
[25]Lai, V., Ahmed, A. N., Malek, M. A., Abdulmohsin Afan, H., Ibrahim, R. K., El-Shafie, A., & El-Shafie, A. (2019). Modeling the nonlinearity of sea level oscillations in the malaysian coastal areas using machine learning algorithms. Sustainability, 11(17), 4643.
[26]Le, L. T., Nguyen, H., Zhou, J., Dou, J., & Moayedi, H. (2019). Estimating the heating load of buildings for smart city planning using a novel artificial intelligence technique PSO-XGBoost. Applied Sciences, 9(13), 2714.
[27]Mu, J., Wu, F., & Zhang, A. (2014). Housing value forecasting based on machine learning methods. Abstract and Applied Analysis, 2014(4), 1-7.
[28]Nur, A., Ema, R., Taufiq, H., & Firdaus, W. (2017). Modeling house price prediction using regression analysis and particle swarm optimization case study : malang, east java, indonesia. International Journal of Advanced Computer Science and Applications, 8(10), 323-326.
[29]Ojo, A. I. (2017). Validation of the delone and mclean information systems success model. hir, 23(1), 60-66.
[30]Peng, Z., Huang, Q., & Han, Y. (2019, October, 18-20). Model research on forecast of second-hand house price in chengdu based on xgboost algorithm [Paper presentation]. 2019 IEEE 11th International Conference on Advanced Infocomm Technology (ICAIT), Jinan, China.
[31]Petter, S., DeLone, W., & McLean, E., 2008, Measuring information systems success: models, dimensions, measures, and interrelationships. European journal of information systems, 17(3), 236-263.
[32]Rana, V. S., Mondal, J., Sharma, A., & Kashyap, I. (2020, December, 18-19). House price prediction using optimal regression techniques [Paper presentation]. 2020 2nd International Conference on Advances in Computing, Communication Control and Networking (ICACCCN), Greater Noida, India.
[33]Shi, Y., & Eberhart, R. (1998, May, 4-9 ). A modified particle swarm optimizer [Paper presentation]. 1998 IEEE International Conference on Evolutionary Computation Proceedings. IEEE World Congress on Computational Intelligence (Cat. No.98TH8360), Anchorage, AK, USA.
[34]Tay, D. P. H., & Ho, D. K. H. (1992). Artificial intelligence and the mass appraisal of residential apartments. Journal of Property Valuation and Investment, 10(2), 525-540.
[35]Wang, C. (2013). Family house-purchase decision model based on analytic hierarchy process. Applied Mechanics and Materials, 423-426(6), 2973-2976.
[36]Wang, X., Wen, J., Zhang, Y., & Wang, Y. (2014). Real estate price forecasting based on SVM optimized by PSO. Optik, 125(3), 1439-1443.
[37]Wang, Y., Wang, D., Geng, N., Wang, Y., Yin, Y., & Jin, Y. (2019). Stacking-based ensemble learning of decision trees for interpretable prostate cancer detection. Applied Soft Computing, 77, 188-204.
[38]Wu, J., Liu, H., Wei, G., Song, T., Zhang, C., & Zhou, H. (2019). Flash flood forecasting using support vector regression model in a small mountainous Catchment. Water, 11(7), 1327.
[39]Xiao-zhu, D., & Ling-wei, K. (2013, July, 17-19). The land prices and housing prices — empirical research based on panel data of 11 provinces and municipalities in eastern china [Paper presentation]. 2013 International Conference on Management Science and Engineering 20th Annual Conference Proceedings, Harbin, China.
[40]Yahya, N., Megat Mohd Zainuddin, N., Amir Sjarif, N. N., & Fisdaus Mohd Azmi, N. (2021). Predictive visual analytics for machine learning model in house price prediction: a case study. Open International Journal of Informatics, 9(1), 1-29.
[41]Yilmazer, S., & Kocaman, S. (2020). A mass appraisal assessment study using machine learning based on multiple regression and random forest. Land Use Policy, 99, 104889.
[42]Yin, Y., Sun, Y., Zhao, F., & Chen, J. (2020). Improved XGBoost model based on genetic algorithm. International Journal of Computer Applications in Technology, 62(3), 240-245.
[43]Zulkifley, N. H., Rahman, S. A., Ubaidullah, N. H., Ibrahim, I. J. I. J. o. M. E., & Science, C. (2020). House price prediction using a machine learning model: a survey of literature. International Journal of Modern Education and Computer Science, 12(6), 46-54.