1. NCCU Academic Hub
  2. Publications
  3. College of Social Science
  4. Theses
  5. Item

Publications-Theses

Article View/Open

Publication Export

Google ScholarTM

NCCU Library

Citation Infomation

Related Publications in TAIR

題名 深度學習模型於房價預測之應用：以新北市板橋區為例
Application of deep learning models in housing price prediction: A case study of Banqiao District, New Taipei City
作者 譚方俞
Tan, Fang-Yu
貢獻者 蔡炎龍<br>林馨怡
Tsai, Yen-lung<br>Lin, Hsin-Yi
譚方俞
Tan, Fang-Yu
關鍵詞 房價預測
深度學習
多層感知器（MLP）
異常交易偵測
Housing Price Prediction
Deep Learning
Multi-Layer Perceptron (MLP)
Anomaly Detection
日期 2025
上傳時間 1-Sep-2025 15:45:22 (UTC+8)
摘要 本研究旨在建構一套融合結構屬性、空間資訊與心理參考價格之深度學習房價預測模型，並以新北市板橋區為實證場域，探討其於價格合理性判定上的應用潛力。針對實價登錄資料中可能存在的價格異常問題，本研究提出以多層感知神經網路（Multi-Layer Perceptron, MLP）為基礎架構，並結合殘差學習模組（Residual Block）與多尺度空間異常值剔除機制（MSSOD），以提升模型的訓練穩定性與非線性特徵擬合能力。 研究資料涵蓋 108 至 113 年間板橋區逾三萬五千筆住宅交易紀錄，經資料清理、異常值檢測、地理變數建構與特徵工程後，建立可供模型訓練之輸入特徵。預測目標設定為實際價格與鄰近加權均價之對數差值（log_price_diff），並以 ±10% 誤差區間為合理價格判定標準，設計 ACC@10 作為核心評估指標。 實證結果顯示，本研究模型於測試資料集中達成 ACC@10 為 70.17%、MAPE 為 11.49%、RMSE 約為 22,914 元，顯示具備良好的準確性與實務可用性。進一步以 30 次獨立訓練檢驗穩定性，平均 ACC@10 為 68.95%，標準差僅 0.56%，驗證模型具備高度可重現性。價格區段分析結果亦顯示，模型於中價樣本表現最佳，而高低價樣本之預測誤差相對較大。組件消融實驗則證實，殘差結構與異常值剔除機制皆為提升效能之關鍵要素。 整體而言，本研究模型在理論設計與實務應用層面均具貢獻，能作為市場價格合理性判斷、異常交易預警及政策監理輔助工具之基礎架構。
This study proposes a deep learning model for housing price prediction that integrates structural attributes, spatial information, and psychological reference prices, using Banqiao District, New Taipei City as a case study. The model adopts a Multi-Layer Perceptron (MLP) enhanced with residual blocks and a multi-scale spatial outlier detection (MSSOD) mechanism to improve training stability and nonlinear fitting. Using over 35,000 residential transactions from 2019 to 2024, the prediction target is defined as the log difference between actual prices and nearby weighted averages. A ±10% deviation is set as the threshold for rational price evaluation, with ACC@10 as the main metric. Results show the model achieves an ACC@10 of 70.17%, a MAPE of 11.49%, and an RMSE of about 22,914 NT dollars on the test set. Thirty independent runs confirm robustness, with an average ACC@10 of 68.95% and low variance. Ablation studies further demonstrate that both residual learning and spatial filtering are critical to performance. Overall, the proposed framework provides practical value for rational price assessment, anomaly detection, and housing market supervision.
參考文獻 1.Anselin, L. (1995). Local indicators of spatial association—LISA. Geographical Analysis, 27(2), 93–115. 2.Chen, J., Gao, J., Wu, X., & Xie, L. (2020). House price valuation model based on geographically neural network weighted regression: The case study of Shenzhen, China. Sustainability, 12(16), 6674. 3.Cheng, T., & Li, Z. (2004). A multiscale approach to detect spatial-temporal outliers. Proceedings of the 2004 ACM Symposium on Applied Computing, 576–583. 4.Fotheringham, A. S., Brunsdon, C., & Charlton, M. (2002). Geographically weighted regression: The analysis of spatially varying relationships. Chichester: Wiley. 5.Getis, A., & Ord, J. K. (1995). Local spatial autocorrelation statistics: Distributional issues and an application. Geographical Analysis, 27(4), 286–306. 6.He, K., Zhang, X., Ren, S., & Sun, J. (2016). Deep residual learning for image recognition. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 770–778. 7.Huang, B., Wu, B., & Barry, M. (2010). Geographically and temporally weighted regression for modeling spatio-temporal variation in house prices. International Journal of Geographical Information Science, 24(3), 383–401. 8.Karkar, A., Shekhar, S., Fei, X., & Adams, B. (2020). A multiscale approach for spatio-temporal outlier detection. GeoInformatica, 24(1), 25–63. 9.Kuchler, T., Piazzesi, M., & Stroebel, J. (2023). Housing market expectations. The Quarterly Journal of Economics, 138(1), 1–49. 10.Lu, W., & Chen, Y. (2007). A multi-scale approach to detect spatial outliers. Computers, Environment and Urban Systems, 31(6), 567–587. 11.Selim, H. (2009). Determinants of house prices in Turkey: Hedonic regression versus quantile regression. Applied Economics Letters, 16(17), 1705–1710.
描述 碩士
國立政治大學
經濟學系
111258044
資料來源 http://thesis.lib.nccu.edu.tw/record/#G0111258044
資料類型 thesis
dc.contributor.advisor 蔡炎龍<br>林馨怡zh_TW
dc.contributor.advisor Tsai, Yen-lung<br>Lin, Hsin-Yien_US
dc.contributor.author (Authors) 譚方俞zh_TW
dc.contributor.author (Authors) Tan, Fang-Yuen_US
dc.creator (作者) 譚方俞zh_TW
dc.creator (作者) Tan, Fang-Yuen_US
dc.date (日期) 2025en_US
dc.date.accessioned 1-Sep-2025 15:45:22 (UTC+8)-
dc.date.available 1-Sep-2025 15:45:22 (UTC+8)-
dc.date.issued (上傳時間) 1-Sep-2025 15:45:22 (UTC+8)-
dc.identifier (Other Identifiers) G0111258044en_US
dc.identifier.uri (URI) https://ah.lib.nccu.edu.tw/item?item_id=178764-
dc.description (描述) 碩士zh_TW
dc.description (描述) 國立政治大學zh_TW
dc.description (描述) 經濟學系zh_TW
dc.description (描述) 111258044zh_TW
dc.description.abstract (摘要) 本研究旨在建構一套融合結構屬性、空間資訊與心理參考價格之深度學習房價預測模型，並以新北市板橋區為實證場域，探討其於價格合理性判定上的應用潛力。針對實價登錄資料中可能存在的價格異常問題，本研究提出以多層感知神經網路（Multi-Layer Perceptron, MLP）為基礎架構，並結合殘差學習模組（Residual Block）與多尺度空間異常值剔除機制（MSSOD），以提升模型的訓練穩定性與非線性特徵擬合能力。 研究資料涵蓋 108 至 113 年間板橋區逾三萬五千筆住宅交易紀錄，經資料清理、異常值檢測、地理變數建構與特徵工程後，建立可供模型訓練之輸入特徵。預測目標設定為實際價格與鄰近加權均價之對數差值（log_price_diff），並以 ±10% 誤差區間為合理價格判定標準，設計 ACC@10 作為核心評估指標。 實證結果顯示，本研究模型於測試資料集中達成 ACC@10 為 70.17%、MAPE 為 11.49%、RMSE 約為 22,914 元，顯示具備良好的準確性與實務可用性。進一步以 30 次獨立訓練檢驗穩定性，平均 ACC@10 為 68.95%，標準差僅 0.56%，驗證模型具備高度可重現性。價格區段分析結果亦顯示，模型於中價樣本表現最佳，而高低價樣本之預測誤差相對較大。組件消融實驗則證實，殘差結構與異常值剔除機制皆為提升效能之關鍵要素。 整體而言，本研究模型在理論設計與實務應用層面均具貢獻，能作為市場價格合理性判斷、異常交易預警及政策監理輔助工具之基礎架構。zh_TW
dc.description.abstract (摘要) This study proposes a deep learning model for housing price prediction that integrates structural attributes, spatial information, and psychological reference prices, using Banqiao District, New Taipei City as a case study. The model adopts a Multi-Layer Perceptron (MLP) enhanced with residual blocks and a multi-scale spatial outlier detection (MSSOD) mechanism to improve training stability and nonlinear fitting. Using over 35,000 residential transactions from 2019 to 2024, the prediction target is defined as the log difference between actual prices and nearby weighted averages. A ±10% deviation is set as the threshold for rational price evaluation, with ACC@10 as the main metric. Results show the model achieves an ACC@10 of 70.17%, a MAPE of 11.49%, and an RMSE of about 22,914 NT dollars on the test set. Thirty independent runs confirm robustness, with an average ACC@10 of 68.95% and low variance. Ablation studies further demonstrate that both residual learning and spatial filtering are critical to performance. Overall, the proposed framework provides practical value for rational price assessment, anomaly detection, and housing market supervision.en_US
dc.description.tableofcontents 第一章 緒論 1 第一節 研究動機 1 第二節 研究目的 1 第三節 研究資料與範圍 2 第四節 論文架構 3 第二章 文獻回顧 4 第一節 房價影響因素 4 第二節 異常值偵測方法 5 第三節 空間與時空加權迴歸方法 6 第四節 殘差神經網路概述 7 第三章 研究方法 9 第一節 研究流程與資料來源 9 第二節 模型設計與變數建構 10 第三節 變數設計與特徵工程 12 第四節 模型訓練設定與穩定性評估 14 第四章 實證結果與分析 16 第一節 模型效能分析 16 第二節 價格區間誤差分析 18 第三節 模型組件效能比較 20 第五章 結論與建議 23 參考文獻 25zh_TW
dc.format.extent 824762 bytes-
dc.format.mimetype application/pdf-
dc.source.uri (資料來源) http://thesis.lib.nccu.edu.tw/record/#G0111258044en_US
dc.subject (關鍵詞) 房價預測zh_TW
dc.subject (關鍵詞) 深度學習zh_TW
dc.subject (關鍵詞) 多層感知器（MLP）zh_TW
dc.subject (關鍵詞) 異常交易偵測zh_TW
dc.subject (關鍵詞) Housing Price Predictionen_US
dc.subject (關鍵詞) Deep Learningen_US
dc.subject (關鍵詞) Multi-Layer Perceptron (MLP)en_US
dc.subject (關鍵詞) Anomaly Detectionen_US
dc.title (題名) 深度學習模型於房價預測之應用：以新北市板橋區為例zh_TW
dc.title (題名) Application of deep learning models in housing price prediction: A case study of Banqiao District, New Taipei Cityen_US
dc.type (資料類型) thesisen_US
dc.relation.reference (參考文獻) 1.Anselin, L. (1995). Local indicators of spatial association—LISA. Geographical Analysis, 27(2), 93–115. 2.Chen, J., Gao, J., Wu, X., & Xie, L. (2020). House price valuation model based on geographically neural network weighted regression: The case study of Shenzhen, China. Sustainability, 12(16), 6674. 3.Cheng, T., & Li, Z. (2004). A multiscale approach to detect spatial-temporal outliers. Proceedings of the 2004 ACM Symposium on Applied Computing, 576–583. 4.Fotheringham, A. S., Brunsdon, C., & Charlton, M. (2002). Geographically weighted regression: The analysis of spatially varying relationships. Chichester: Wiley. 5.Getis, A., & Ord, J. K. (1995). Local spatial autocorrelation statistics: Distributional issues and an application. Geographical Analysis, 27(4), 286–306. 6.He, K., Zhang, X., Ren, S., & Sun, J. (2016). Deep residual learning for image recognition. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 770–778. 7.Huang, B., Wu, B., & Barry, M. (2010). Geographically and temporally weighted regression for modeling spatio-temporal variation in house prices. International Journal of Geographical Information Science, 24(3), 383–401. 8.Karkar, A., Shekhar, S., Fei, X., & Adams, B. (2020). A multiscale approach for spatio-temporal outlier detection. GeoInformatica, 24(1), 25–63. 9.Kuchler, T., Piazzesi, M., & Stroebel, J. (2023). Housing market expectations. The Quarterly Journal of Economics, 138(1), 1–49. 10.Lu, W., & Chen, Y. (2007). A multi-scale approach to detect spatial outliers. Computers, Environment and Urban Systems, 31(6), 567–587. 11.Selim, H. (2009). Determinants of house prices in Turkey: Hedonic regression versus quantile regression. Applied Economics Letters, 16(17), 1705–1710.zh_TW