聯合國於2015年制定的永續發展目標（SustainableDevelopmentGoals,SDGs）將城市作為關鍵領域，提出了SDG11永續城鄉，首要目標是建設具包容、安全、韌性和永續的城市和居住環境。在此背景下，臺灣也積極響應國際趨勢，推動綠建築、都市更新及公共交通建設等相關政策，以期在促進城市發展的同時，降低環境影響並提升居民生活品質。然而，這些永續發展措施在推動的同時，也引發了住房可負擔性的問題。像是綠建築雖然在能效和環境保護方面具有許多優點，但其較高的建設成本往往轉嫁至市場價格進而導致房價增高，使得低收入等弱勢群體更難以承擔這類住房。同樣，都市更新和交通設施的改善雖然提升了地區房價，卻也可能導致原有居民，尤其是弱勢群體，無法繼續負擔該地區的生活成本，進而被迫遷離。
本研究應用機器學習技術中的隨機森林迴歸模型，輔以計量方法中的特徵價格模型進行比較，透過量化影響房價因素之環境特徵、社會經濟特徵以及永續特徵，來探討臺灣政府因應SDG11指標所對應的相關政策措施，對房價與住房可負擔性的影響。本研究蒐集民國106年、109年及112年，三年度各縣市之實價登錄交易資料，共計175,012筆樣本資料。並從SDG11所涵蓋之28項原始指標中篩選具可得性且符合縣市層級分析需求的13項變數作為「永續特徵」，並輔以「建物特徵」及「環境特徵」共三大面向，作為後續模型分析之變數。
研究發現，在房價預測準確性方面，隨機森林迴歸模型呈現出明顯較佳的模型表現（R²約0.845），且透過特徵重要性的分析可以幫助我們快速判斷影響房價的因素。特徵價格模型雖整體解釋能力稍低（R²約0.642），但透過迴歸係數了解特徵對房價影響的方向，相對隨機森林模型更具可解釋性。透過兩個模型的實證比較，本研究進一步確認人口密度、建物屋齡、都市綠地面積以及都市更新核定案件數等指標對房價皆有顯著影響，亦顯示出部分永續城市指標能夠反映不動產市場價格之變動。

In 2015, the United Nations established Sustainable Development Goal 11 (SDG 11) to promote inclusive, safe, resilient, and sustainable cities. Taiwan has actively implemented related policies, including green buildings, urban renewal, and transportation enhancements. While these efforts support urban growth and environmental protection, they also exacerbate housing affordability issues. Green building and urban renewal projects often raise property prices, disproportionately affecting low-income residents and vulnerable populations.
This research compares a Random Forest regression model and the Hedonic Pricing Model to evaluate the impact of Taiwan's SDG 11 Targets on housing prices. Using 175,012 transaction records from 2017, 2020, and 2023, the study analyzed environmental, building and sustainability characteristical as variable. The Random Forest model demonstrated superior predictive accuracy (R² ~0.845), while the Hedonic Pricing Model offered clearer interpretability (R² ~0.642). The study confirmed significant influences from indicators such as population density, building age, urban green spaces, and urban renewal activities, highlighting how SDG 11 sustainability indicators reflect housing market dynamics.

1.Adair, A. S.,Berry, J. N.,McGreal, W. S.(1996). Hedonic modelling, housing submarkets and residential valuation. Journal of property Research, 13(1), 67-83.
2.Alova, G., Trotter, P. A., Money, A.(2021). A machine-learning approach to predicting africa's electricity mix based on planned power plants and their chances of success. Nature Energy, 6(2), 158-166.
3.Anderson, S. T., West, S. E.(2006). Open space, residential property values, and spatial context. Regional Science and Urban Economics, 36(6), 773-789.
4.Ao, Y., Li, H., Zhu, L., Ali, S., Yang, Z.(2019). The linear random forest algorithm and its advantages in machine learning assisted logging regression modeling. Journal of Petroleum Science and Engineering, 174, 776-789.
5.Cai, C., Yang, C., Lu, S., Gao, G., Na, J.(2023). Human motion pattern recognition based on the fused random forest algorithm. Measurement, 222, 113540.
6.Čeh, M., Kilibarda, M., Lisec, A., Bajat, B.(2018). Estimating the performance of random forest versus multiple regression for predicting prices of the apartments. ISPRS international journal of geo-information, 7(5), 168.
7.Cervero, R., Duncan, M.(2002). Benefits of proximity to rail on housing markets: Experiences in santa clara county. Journal of Public Transportation, 5(1), 1-18.
8.Darst, B. F., Malecki, K. C., Engelman, C. D.(2018). Using recursive feature elimination in random forest to account for correlated variables in high dimensional data. BMC genetics, 19, 1-6.
9.Eichholtz, P., Kok, N., Quigley, J. M. (2010). Doing well by doing good? Green office buildings, American Economic Review (No.100, p. 2492-2509).
10.Fabre, E. A.(2017). Local implementation of the sdgs & the new urban agenda: Towards a swedish national urban policy. Global utmaning.
11.Jean, N., Burke, M., Xie, M., Davis, W. M., Lobell, D. B., Ermon, S.(2016). Combining satellite imagery and machine learning to predict poverty. Science, 353(6301), 790-794.
12.Jiang, M., Wang, J., Hu, L., He, Z.(2023). Random forest clustering for discrete sequences. Pattern Recognition Letters, 174, 145-151.
13.Karuppannan, S., Sivam, A.(2009). Sustainable development and housing affordability. Institute of sustainable systems and technologies.
14.Kestens, Y., Thériault, M., Des Rosiers, F.(2006). Heterogeneity in hedonic modelling of house prices: Looking at buyers' household profiles. Journal of Geographical Systems, 8, 61-96.
15.Klopp, J. M., Petretta, D. L.(2017). The urban sustainable development goal: Indicators, complexity and the politics of measuring cities. Cities, 63, 92-97.
16.Meese, R., Wallace, N.(2003). House price dynamics and market fundamentals: The parisian housing market. Urban Studies, 40(5-6), 1027-1045.
17.Mironiuc, M., Ionașcu, E., Huian, M. C., Țaran, A.(2021). Reflecting the sustainability dimensions on the residential real estate prices. Sustainability, 13(5), 2963.
18.Mohd, T., Jamil, N. S., Johari, N., Abdullah, L., Masrom, S. (2020). An overview of real estate modelling techniques for house price prediction, Charting a Sustainable Future of ASEAN in Business and Social Sciences: Proceedings of the 3ʳᵈ International Conference on the Future of ASEAN (ICoFA) 2019—Volume 1 (p.321-338). Springer.
19.Mora-Garcia, R.-T., Cespedes-Lopez, M.-F., Perez-Sanchez, V. R.(2022). Housing price prediction using machine learning algorithms in covid-19 times. Land, 11(11), 2100.
20.Park, B., Bae, J. K.(2015). Using machine learning algorithms for housing price prediction: The case of fairfax county, virginia housing data. Expert systems with applications, 42(6), 2928-2934.
21.Porciello, J., Ivanina, M., Islam, M., Einarson, S., Hirsh, H.(2020). Accelerating evidence-informed decision-making for the sustainable development goals using machine learning. Nature Machine Intelligence, 2(10), 559-565.
22.Rosen, S.(1974). Hedonic prices and implicit markets: Product differentiation in pure competition. Journal of political economy, 82(1), 34-55.
23.Selim, H.(2009). Determinants of house prices in turkey: Hedonic regression versus artificial neural network. Expert systems with applications, 36(2), 2843-2852.
24.Stevenson, S.(2004). New empirical evidence on heteroscedasticity in hedonic housing models. Journal of Housing Economics, 13(2), 136-153.
25.Storm, H., Baylis, K., Heckelei, T.(2020). Machine learning in agricultural and applied economics. European Review of Agricultural Economics, 47(3), 849-892.
26.Sun, Z., Wang, G., Li, P., Wang, H., Zhang, M., Liang, X.(2024). An improved random forest based on the classification accuracy and correlation measurement of decision trees. Expert systems with applications, 237, 121549.
27.Vaidya, H., Chatterji, T.(2020). Sdg 11 sustainable cities and communities: Sdg 11 and the new urban agenda: Global sustainability frameworks for local action. Actioning the global goals for local impact: Towards sustainability science, policy, education and practice, 173-185.
28.Zhao, B., Yu, L., Wang, C., Shuai, C., Zhu, J., Qu, S., Taiebat, M., Xu, M.(2021). Urban air pollution mapping using fleet vehicles as mobile monitors and machine learning. Environmental Science & Technology, 55(8), 5579-5588.
29.D. M. Reif, A. A. Motsinger, B. A. McKinney, J. E. Crowe and J. H. Moore, "Feature Selection using a Random Forests Classifier for the Integrated Analysis of Multiple Data Types," 2006 IEEE Symposium on Computational Intelligence and Bioinformatics and Computational Biology, Toronto, ON, Canada, 2006, pp. 1-8, doi: 10.1109/CIBCB.2006.330987.
30.Afonso, B.; Melo, L.; Oliveira, W.; Sousa, S.; Berton, L. Housing prices prediction with a deep learning and random forest ensemble. In Proceedings of the Anais do Encontro Nacional de Inteligência Artificial e Computacional (ENIAC), Salvador, Brasil, 15–18 October 2019; pp. 389–400.
31.Moreno-Foronda, I., Sánchez-Martínez, M.-T., & Pareja-Eastaway, M. (2025). Comparative Analysis of Advanced Models for Predicting Housing Prices: A Review. Urban Science, 9(2), 32.
32.Schläpfer, F.; Waltert, F.; Segura, L.; Kienast, F. Valuation of landscape amenities: A hedonic pricing analysis of housing rents in urban, suburban, and periurban Switzerland. Landsc. Urban Plan. 2015, 141, 24–40.
33.Hong, J., Choi, H., & Kim, W.- sung. (2020). A house price valuation based on the random forest approach: the mass appraisal of residential property in South Korea. International Journal of Strategic Property Management, 24(3), 140-152.
34.Yoo, S.; Im, J.; Wagner, J.E. Variable selection for hedonic model using machine learning approaches: A case study in Onondaga County, NY. Landsc. Urban Plan. 2012, 107, 293–306.
35.Ligus, M.; Peternek, P. Impacts of Urban Environmental Attributes on Residential Housing Price in Warsaw (Poland): Spatial Hedonic Analysis of City Districts; Springer: Berlin/Heidelberg, Germany, 2017; pp. 155–164.
36.張家綺(2021)。都市更新計畫對周邊房價影響之外溢效果：臺灣的實證研究。國立中央大學財務金融學系碩士論文。
37.陳奉瑤、梁仁旭(2018)。綠建築標章之溢價率分析—以新北市住宅大樓為例。臺灣土地研究，21(1)，61-85。
38.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。
39.葉淞暉(2021)。隨機森林中選取重要特徵因子之方法。國立中興大學統計學研究所碩士論文。
40.韓恩之、蔡瑄文、賴淑芳(2016)。捷運交通對房價之影響以台北市為例。地理資訊系統季刊，10(4)，24-28。
41.李姿萱(2024)。基於居住生活行為的綠色品質與居住品質實證分析。國立成功大學都市計劃學系碩士論文。
42.林襼伶(2024)。影響住宅區房價變動因素之研究。銘傳大學財務金融學系碩士碩士論文。
43.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。
44.郭紀子(2017)。物業管理對集合住宅價格之影響。國立政治大學地政學系碩士論文。
45.艾兆蕾(2005)。影響住宅區地價因素之空間分析—以鄉鎮與縣市為例。世新大學經濟學研究所碩士論文。
46.行政院國家永續發展委員會（2023）。《2022臺灣永續發展目標追蹤檢討報告》。中華民國：行政院國家永續發展委員會。
47.行政院國家永續發展委員會（2022）。《臺灣永續發展目標修正版》。中華民國：行政院國家永續發展委員會。