隨著人工智慧之發展，機器學習已逐漸成為房價研究之重要工具。過去相關應用常被視為「黑箱模型」，難以清楚解釋其價格形成機制。近年可解釋人工智慧（XAI）技術興起，使機器學習模型解釋性顯著提升，亦為房價研究提供新的分析方法。然而，國內多數研究著重於模型之預測準確性，較少深入探討房價形成機制。因此，本研究以臺灣六都為研究對象，結合機器學習與XAI方法，分析各項變數在重要性、影響方向與非線性型態之差異，並進一步探討變數間之交互作用模式。
實證結果顯示，隨機森林於模型解釋力與預測準確度皆優於傳統OLS模型。進一步透過XAI分析發現，六都房價形成機制兼具共通性與區域異質性，其中屋齡與軌道運輸站距離為主要負向影響因素，而高階醫療資源可及性具明顯正向溢價效果。區域差異方面，臺北市房價較受區位及醫療機能主導，中南部則相對受停車位等私人運具因素影響較大。此外，多數變數與房價之間存在非線性關係與門檻效果，且變數間具有明顯交互作用。例如，雙北地區之低總樓層住宅於高屋齡階段會出現價格回升現象、桃園市之低屋齡住宅對於軌道運輸站距離變化較敏感等。
整體而言，本研究建構一套兼具預測力與解釋力之房價分析架構，有助於釐清房價複雜的形成機制並作為未來市場分析與住宅政策制定之參考。

With the development of artificial intelligence, machine learning has gradually become an important tool in housing price research. Previous applications have often been regarded as black-box models, making it difficult to clearly explain the mechanisms underlying housing price formation. In recent years, the emergence of explainable artificial intelligence (XAI) has substantially improved the interpretability of machine learning models and provided new analytical approaches for housing price research. However, most domestic studies have focused on predictive accuracy, with relatively limited attention given to the mechanisms underlying housing price formation. Therefore, this study takes Taiwan’s six special municipalities as the research area and combines machine learning with XAI methods to examine differences in the importance, direction of influence, and nonlinear patterns of various variables, and further investigates the patterns of interaction among variables.
Empirical results demonstrate that the Random Forest algorithm outperforms traditional Ordinary Least Squares (OLS) models in both explanatory power and predictive accuracy. Further XAI analysis reveals that housing price formation mechanisms across the six municipalities exhibit both commonalities and regional heterogeneity. Property age and distance to rail transit stations serve as the primary negative influencing factors, whereas the accessibility of advanced medical resources yields a significant positive premium effect. Regarding regional differences, housing prices in Taipei City are predominantly driven by location and healthcare amenities, whereas markets in central and southern Taiwan are relatively more influenced by private transportation factors, such as parking space availability. Furthermore, non-linear relationships and threshold effects exist between most variables and housing prices, alongside significant interaction effects among the variables. For instance, low-rise residential buildings in the Greater Taipei area exhibit a price rebound at advanced property ages, while newer properties in Taoyuan City are more sensitive to changes in distance from rail transit stations.
Overall, this study establishes a housing price analysis framework that possesses both predictive and explanatory power. This framework helps elucidate the complex mechanisms of housing price formation and serves as a valuable reference for future market analysis and housing policy formulation.

一、 中文文獻
王文楷，2025，「利用機器學習和隨機過程預測房價：以臺灣房市為例」，『住宅學報』，34(1)：1-20。
王健安、鄧筱蓉，2026，「特殊樓層與交易價格的關係：來自實價登錄台北市數據之驗證」，『建築與規劃學報』，26(1/2)：18-46。
江穎慧、朱智揚、張金鶚，2019，「預售屋大量估價模型之建立」，『住宅學報』，28(2)：17-36。
余惠芳、梁榮輝，2015，「高負債比觀點分析家族業外部監控與營運策略之實證研究」，『華人經濟研究』，13(2)：75-96。
李鴻英、賴宗裕，2017，「人口結構變遷對房地產市場之影響」，『土地問題研究季刊』，16(3)：69-82。
李春長、梁志民、林豐文，2017，「捷運系統對鄰近住宅價格之影響-以差異中之差異法估計」，『臺灣土地研究』，20(2)：31-58。
李春長、游淑滿、張維倫，2012，「公共設施、環境品質與不動產景氣對住宅價格影響之研究-兼論不動產景氣之調節效果」，『住宅學報』，21(1)：67-87。
杜宇璇、宋豐荃、曾禹瑄、葛仲寧、陳奉瑤，2013，「臺灣特徵價格模型之回顧分析」，『土地問題研究季刊』，12(2)：44-57。
林左裕、程于芳，2014，「影響不動產市場之從眾行為與總體經濟因素之研究」，『應用經濟論叢』，95：61-99。
林秋瑾、楊宗憲、張金鶚，1996，「住宅價格指數之研究-以臺北市為例」，『住宅學報』，4：1-30。
林祖嘉、林素菁，1993，「臺灣地區環境品質與公共設施對房價與房租影響之分析」，『住宅學報』，1：21-45。
林祖嘉、馬毓駿，2007，「特徵方程式大量估價法在臺灣不動產市場之應用」，『住宅學報』，16(2)：1-22。
林楨家、黃至豪，2003，「台北捷運營運前後沿線房地屬性特徵價格之變化」，『運輸計劃季刊』，32(4)：777-800。
花敬群、張金鶚，1999，「住宅空間次市場間價格與市場規模之關係」，『都市與計劃』，26(1)：79-94。
邵勸如、陳奉瑤，2022，「臺中捷運綠線對周邊住宅價格影響之研究」，『土地經濟年刊』，33：1-22。
洪得洋、林祖嘉，1999，「臺北市捷運系統與道路寬度對房屋價格影響之研究」，『住宅學報』，8(3)：47-67。
梁仁旭，2012，「不動產價值逆折舊之探討」，『住宅學報』，21(2)：71-89。
陳亭霓、張智安，2025，「應用梯度提升樹於實價登錄之車位價格預測」，『國土測繪與空間資訊』，13(1)：71-90。
陳奕廷、陳永寬、鄭欽龍，1997，「整合地理資訊系統及計量經濟方法於坡地利用之研究-以阿里山鄉坡地開發為例」，『航測及遙測學刊』，2(4)：65-75。
陳彥仲、吳京玲，1998，「家戶住宅區位選擇與地方財政分配之實證研究」，『都市與計劃』，25(2)：223-238。
陳彥仲、梁詠涵、呂昭宏，2021，「檢視臺灣縣市房價之區域空間異質性與外溢效果」，『規劃學報』，39(2)：1-21。
陳晏筑、林雅亭、劉千菱、吳佳洟、張雅嵐、林左裕，2022，「鄰避設施對鄰近房價的影響－以臺北市為例」，『土地問題研究季刊』，21(4)：32-53。
陳樹衡、郭子文、棗厥庸，2007，「以決策樹之迴歸樹建構住宅價格模型-臺灣地區之實證分析」，『住宅學報』，16(1)：1-20。
彭建文、馮靖博、丁玟甄，2011，「待更新不動產之實質選擇權價值分析」，『住宅學報』，20(2)：1-26。
彭建文、楊宗憲、楊詩韻，2009，「捷運系統對不同區位房價影響分析-以營運階段為例」，『運輸計劃季刊』，38(3)：275-296。
彭蒂菁，2021，「醫療可及性是否左右房價？機器學習之迴歸樹及隨機森林模型的應用」，『應用經濟論叢』，109：115-167。
黃士峰、廖育苹，2022，「基於廣義加成模型之房屋價格預測方法」，『中國統計學報』，60：95-124。
黃允亭，2022，「應用實價登錄建立以聚類方法之堆疊泛化房價預測模型-以桃園市區分建物房價資料為例」，國立政治大學經濟學系研究所碩士論文。
楊宗憲、蘇倖慧，2011，「迎毗設施與鄰避設施對住宅價格影響之研究」，『住宅學報』，20(2)：62-81。
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。
詹為巽、鄭可風、林俊成，2021，「都市公園綠地對於房價之影響－以新北市八二三紀念公園為例」，『林業論壇』，28(2)：66-69。
劉富容、游璿達、黃孝雲、劉正夫，2019，「利用政府開放資料探討影響臺北市房價之主要房屋特性及周邊設施影響因子」，『數據分析』，14(5)：1-26。
蔡永順、宋宣瑩、臧仕維，2023，「房屋特徵對房價之影響-道路寬度之研究」，『藝見學刊』，26：91-115。
蔡孟珂、吳珮瑛、劉哲良，2019，「空間特徵分量Durbin模型之建構-桃園市都市計劃區多元開放空間組合價值之檢視」，『都市與計劃』，46(4)：297-341。
蔡繡容、夏政瑋，2023，「預測臺灣房地產市場趨勢之模型-應用深度學習技術」，『住宅學報』，32(2)：21-55。
蘇偉強、劉庭如、黃斐、陳奉瑤，2013，「特徵價格法應用的差異分析」，『土地問題研究季刊』，12(3)：55-68。
二、 英文文獻
Adadi, A., & Berrada, M., 2018, “Peeking inside the black-box: A survey on explainable artificial intelligence (XAI)”, IEEE Access, 6: 52138-52160.
Agarwal, N., & Das, S., 2020, “Interpretable machine learning tools: A survey”. pp. 1528-1534 in 2020 IEEE symposium series on computational intelligence, New York: IEEE.
Anas, A., Arnott, R., & Small, K. A., 1998, “Urban spatial structure”, Journal of Economic Literature, 36(3): 1426-1464.
Alonso, W., 1964, Location and land use, Cambridge: Harvard University Press.
Basuchoudhary, A., Bang, J. T., & Sen, T., 2017, Machine-learning techniques in Economics: New tools for Predicting Economic Growth, Cham: Springer.
Breiman, L., 1996, “Bagging Predictors”, Machine Learning, 24: 123-140.
Breiman, L., 2001, “Random forests”, Machine Learning, 45(1): 5-32.
Breiman, L., Friedman, J., Olshen, R. A., & Stone, C. J., 1984, Classification and Regression Trees, Boca Raton: Chapman & Hall/CRC.
Bates, L. K., 2006, “Does neighborhood really matter?:Comparing historically defined neighborhood boundaries with housing submarkets”, Journal of Planning Education and Research, 26(1): 5-17.
Bourassa, S. C., Hamelink, F., Hoesli, M., & MacGregor, B. D., 1999, “Defining Housing Submarkets”, Journal of Housing Economics, 8: 160-183.
Bae, C. H. C., Jun, M. J., & Park, H., 2003, “The Impact of Seoul’s Subway Line 5 on Residential Property Values”, Transport Policy, 10(2): 85-94.
Chow, G. C., & Lin, A., 1971, “Best Linear Unbiased Interpolation, Distribution, and Extrapolation of Time Series by Related Series”, The Review of Economics and Statistics, 53(4): 372-375.
Chin, T. L. & Chau, K. W., 2003, “A critical review of literature on the hedonic price model”, International Journal for Housing and Its Applications, 27(2): 145-165.
Court, A. T., 1939, “Hedonic price indexes with automotive examples”. pp. 98-119 in The Dynamics of Automotive Demand, edited by General Motors, New York: General Motors.
Chen, K., Lin, H., Cao, F., Han, Y., You, S., Shyr, O., Lu, Y., & Huang, X., 2022, “Do hospital and rail accessibility have a consistent influence on housing prices? Empirical evidence from China”, Frontiers in Environmental Science, 10: 1044600.
Clapp, J. M. & Salavei, K., 2010, “Hedonic Pricing with Redevelopment Options: A New Approach to Estimating Depreciation Effects”, Journal of Urban Economics, 67(3): 362-377.
Chernobai, E., Carney, M., & Reibel, M., 2011, “Nonlinear spatial and temporal effects of highway construction on house prices”, Journal of Real Estate Finance and Economics, 42: 348-370.
Dell’Anna, F., 2025, “Machine learning framework for evaluating energy performance certificate (EPC) effectiveness in real estate: A case study of Turin’s private residential market”, Energy Policy, 198: 114407.
Dai, S., Li, W., Huang, Y., Xu, Q., & Jia, S., 2026, “Effects of network dynamics of urban rail transit and built environment on housing values using explainable XGBoost model”, Cities, 174: 107103.
Firano, Z., & Filali Adib, F., 2021, “Towards the hedonic modelling and determinants of real estates price in Morocco”, Social Sciences & Humanities Open, 4(1): 100176.
Frasca, M., La Torre, D., Pravettoni, G., & Cutica, I., 2024, “Explainable and interpretable artificial intelligence in medicine: a systematic bibliometric review”, Discover Artificial Intelligence, 4: 15.
Gunning, D., & Aha, D., 2019, “DARPA’s explainable artificial intelligence (XAI) program”, AI Magazine, 40(2): 44-58.
Ghoddusi, H., Creamer, G. G., & Rafizadeh, N., 2019, “Machine learning in energy economics and finance: A review”, Energy Economics, 81: 709-727.
Gu, Z., Tang, M., Luo, X., & Feng, J., 2024, “Examination of the impacts of hospital accessibility on housing prices: heterogeneity across attributes, space and price quantiles”, Journal of Housing and the Built Environment, 39: 179-200.
Grass, R. G., 1992, “The Estimation of Residential Property Values Around Transit Station Sites in Washington, D.C.”, Journal of Economics and Finance, 16(2): 139-146.
Garreau, J., 1991, Edge City: Life on the New Frontier, New York: Doubleday.
Han, F., Lu, M., Qin, D., Zheng, G., Zeng, G., Tan, Y., Wu, Z., Lu, H., Wang, J., Deng, Y., & He, H., 2025, “Exploring housing price dynamics in sustainable cities through a cooperated big data driven machine learning method: case study on a typical city in China”, City and Environment Interactions, 28: 100223.
Hastie, T., Tibshirani, R., & Friedman, J., 2009, The Elements of Statistical Learning: Data mining, inference, and prediction, New York: Springer.
Hu, S., Xiong, C., Chen, P., & Schonfeld, P., 2023, “Examining nonlinearity in population inflow estimation using big data: An empirical comparison of explainable machine learning models”, Transportation Research Part A, 174: 103743.
Herath, S., & Maier, G., 2010, “The Hedonic Price Method in Real Estate and Housing Market Research: A Review of the Literature”, SRE Discussion Papers, No.2010/03, Vienna: WU Vienna University of Economics and Business.
Jafary, P., Shojaei, D., Rajabifard, A., & Ngo, T., 2024, “Automated land valuation models: A comparative study of four machine learning and deep learning methods based on a comprehensive range of influential factors”, Cities, 151: 105115.
Janiesch, C., Zschech, P., & Heinrich, K., 2021, “Machine learning and deep learning”, Electronic Markets, 31(3): 685-695.
James, G., Witten, D., Hastie, T., & Tibshirani, R., 2013, An Introduction to Statistical Learning, New York: Springer.
Jin, S., Zheng, H., Marantz, N., & Roy, A., 2024, “Understanding the effects of socioeconomic factors on housing price appreciation using explainable AI”, Applied Geography, 169: 103339.
Jakubik, J., Vössing, M., Kühl, N., Walk, J., & Satzger, G., 2024, “Data-Centric Artificial Intelligence”, Business & Information Systems Engineering, 66(4): 507-515.
Li, Z., 2022, “Extracting spatial effects from machine learning model using local interpretation method: An example of SHAP and XGBoost”, Computers, Environment and Urban Systems, 96: 101845.
Li, F., 2010, “The Information Content of Forward-Looking Statements in Corporate Filings - A Naïve Bayesian Machine Learning Approach”, Journal of Accounting Research, 48: 1049-1102.
Lee, B. S., Chung, E. C., & Kim, Y. H., 2005, “Dwelling Age, Redevelopment, and Housing Prices: The Case of Apartment Complexes in Seoul,” Journal of Real Estate Finance and Economics, 30(1): 55-80.
Liaw, A. & Wiener, M., 2002, “Classification and Regression by Random Forest”, R News, 2(3): 18-22.
Linardatos, P., Papastefanopoulos, V., & Kotsiantis, S., 2021, “Explainable AI: A review of machine learning interpretability methods”, Entropy, 23(1): 18.
Lenaers, I., & De Moor, L., 2023, “Exploring XAI techniques for enhancing model transparency and interpretability in real estate rent prediction: A comparative study”, Finance Research Letters, 58: 104306.
Lundberg, S. M., Erion, G., Chen, H., DeGrave, A., Prutkin, J. M., Nair, B., Katz, R., Himmelfarb, J., Bansal, N., & Lee, S. I., 2020, “From local explanations to global understanding with explainable AI for trees”, Nature Machine Intelligence, 2(1): 56-67.
Lancaster, K. J., 1966, “A New Approach to Consumer Theory”, Journal of Political Economy, 74(2): 132-157.
Molnar, C., 2020, Interpretable Machine Learning, Lulu.com.
McMillen, D. P., & McDonald, J., 2004, “Reaction of Prices to a New Rapid Transit Line：Chicago’s Midway Line, 1983-1999”, Real Estate Economics, 32(3): 463-486.
Nepal, M., Rai, R. K., Khadayat, M. S., & Somanathan, E., 2020, “Value of cleaner neighborhoods: Application of hedonic price model in low income context”, World Development, 131: 104965.
Nerlove, M. L., & Sadka, E., 1991, “Von Thünen's model of the dual economy”, Journal of Economics, 54(2): 97-123.
Owusu-Ansah, A., 2013, “A review of hedonic pricing models in housing research”, Journal of International Real Estate and Construction Studies, 1(1): 20-33.
Pride, D., Little, J., & Mueller-Stoffels, M., 2018, “The value of residential energy efficiency in interior Alaska: A hedonic pricing analysis”, Energy Policy, 123: 450-460.
Peng, T. C., & Chiang, Y. H., 2015. “The non-linearity of hospitals' proximity on property prices: experiences from Taipei, Taiwan”, Journal of Property Research, 32(4): 341-361.
Rampini, L., & Re Cecconi, F., 2022, “Artificial intelligence algorithms to predict Italian real estate market prices”, Journal of Property Investment & Finance, 40(6): 588-611.
Rico-Juan, J. R., & Taltavull de La Paz, P., 2021, “Machine learning with explainability or spatial hedonics tools? An analysis of the asking prices in the housing market in Alicante, Spain”, Expert Systems with Applications, 171: 114590.
Rosen, S., 1974, “Hedonic prices and implicit markets: Product differentiation in pure competition”, Journal of Political Economy, 82(1): 34-55.
Rivas, R., Patil, D., Hristidis, V., Barr, J. R., & Srinivasan, N., 2019, “The impact of colleges and hospitals to local real estate markets”, Journal of Big Data, 6: 7.
Shakeel, H. M., Iram, S., Hill, R., Farid, H. M. A., Brown, P., & Rehman, H. U., 2025, “An XAI-driven diagnostic framework to investigate the predictive power of building features to enhance EPC ratings in detached houses”, Energy & Buildings, 344: 116022.
Shakeel, H. M., Iram, S., Hill, R., Athar Farid, H. M., Sheikh-Akbari, A., & Saleem, F., 2025, “A machine learning-based intelligent framework for predicting energy efficiency in next-generation residential buildings”, Buildings, 15(8): 1275.
Sharma, N., Sharma, R., & Jindal, N., 2021, “Machine learning and deep learning applications-A vision”, Global Transitions Proceedings, 2(2): 178-181.
Shi, H., Yang, N., Yang, X., & Tang, H., 2023, “Clarifying relationship between PM2. 5 concentrations and spatiotemporal predictors using multi-way partial dependence plots”, Remote Sensing, 15(2): 358.
Sirmans, G. S., Macpherson, D. A., & Zietz, E. N., 2005, “The composition of hedonic pricing models”, Journal of Real Estate Literature, 13(1): 3-43.
Soltani, A., & Lee, C. L., 2024, “The non-linear dynamics of South Australian regional housing markets: A machine learning approach”, Applied Geography, 166: 103248.
Soltani, A., Lee, C. L., Mirzaie, R., & Roohani Qadikolaei, M., 2026, “Environmental drivers of housing prices and thermal inequality using satellite imagery: A submarket approach”, Habitat International, 167: 103628.
Sopranzetti, B. J., 2015, “Hedonic regression models”. pp.115-120 in International Encyclopedia of the Social & Behavioral Sciences, 2nd ed., Vol. 10, edited by Springer, New York: Springer.
Tiebout, C. M., 1956, “A Pure Theory of Local Expenditures”, Journal of Political Economy, 64(5): 416-424.
Voith, R., 1991, “Transportation, Sorting and House Values”, Real Estate Economics, 19(2): 117-137.
Von Thünen, H., 1826, The isolated state in its relation to agriculture and national economy, Tellow in Mecklenburg.
Wan, H., Roy Chowdhury, P. K., Yoon, J., Bhaduri, P., Srikrishnan, V., Judi, D., & Daniel, B., 2025, “Explaining drivers of housing prices with nonlinear hedonic regressions”, Machine Learning with Applications, 21: 100707.
Wang, G., Ma, J., & Yang, S., 2014, “An improved boosting based on feature selection for corporate bankruptcy prediction”, Expert Systems with Applications, 41(6): 2353-2361.
Wu, Y., Wei, Y. D., & Li, H., 2020, “Analyzing Spatial Heterogeneity of Housing Prices Using Large Datasets”, Applied Spatial Analysis and Policy, 13: 223-256.
Wu, C., & Sharma, R., 2012, “Housing submarket classification: The role of spatial contiguity”, Applied Geography, 32: 746-756.
Watkins, C. A., 2001, “The definition and identification of housing submarkets”, Environment and Planning A, 33: 2235-2253.
Xu, Y., Chen, R., Du, H., Chen, M., Fu, C., & Li, Y., 2025, “Evaluation of green space influence on housing prices using machine learning and urban visual intelligence”, Cities, 158: 105661.
Yin, Z., Li, W., Li, C., & Zheng, Y., 2025, “The relationship between accessibility and land prices: A focus on accessibility to transit in the 15-min city”, Travel Behaviour and Society, 38: 100914.
Zhao, X., Yang, H., Yao, Y., Qi, H., Guo, M., & Su, Y., 2022, “Factors affecting traffic risks on bridge sections of freeways based on partial dependence plots”, Physica A: Statistical Mechanics and Its Applications, 598: 127343.
Zhu, M., Zhou, C., Yang, Y., Cui, H., & Ma, X., 2024, “Impacts of characteristics of service facilities in metro station area on housing prices”, International Journal of Transportation Science and Technology, 16: 212-221.
三、 其他
交通部，2024，113年民眾日常使用運具狀況調查摘要分析。https://www.motc.gov.tw/ch/app/statistics101?lang=ch&folderName=ch&id=56，取用日期：2026年5月3日。
健保署，2026，115年分級醫療整體成效進度追蹤。https://www.nhi.gov.tw/ch/cp-1740-748d1-3108-1.html，取用日期：2026年6月30日。
內政部戶政司，2025，人口年增加及出生死亡率。https://www.ris.gov.tw/app/portal/346，取用日期：2026年6月2日。
內政部戶政司，2025，各縣市老年人口比率。https://www.ris.gov.tw/app/portal/346，取用日期：2026年5月3日。
衛生福利部，2025，機構執業醫事人員數及每萬人口執業醫事人員數。https://dep.mohw.gov.tw/dos/cp-5301-62356-113.html，取用日期：2026年6月13日。
衛生福利部，2024，113年度全民健康保險醫療統計年報。https://dep.mohw.gov.tw/DOS/lp-5103-113.html，取用日期：2026年6月13日。
桃園市政府市政新聞，2025，桃市府借鏡東京TOD經驗 張市長：建構更完整城市發展藍圖。https://www.tycg.gov.tw/NewsPage_Content.aspx?n=10&s=1480495，取用日期：2026年8月25日。
好時價（House+），常見問題。https://www.houseplus.com.tw/questionsAndAnswers，取用日期：2026年8月25日。