學術產出-學位論文
文章檢視/開啟
書目匯出
-
題名 P2P借貸中借款人特徵與貸款表現關係之實證研究:以Lending Club和機器學習方法為例
An Empirical Study of the Relationship between Borrower Characteristics and Loan Performance in Peer-to-Peer Lending: Evidence from Lending Club and Machine Learning Techniques作者 陳槐廷
Chen, Huai-Ting貢獻者 林士貴<br>翁久幸
Lin, Shih-Kuei<br>Weng, Chiu-Hsing
陳槐廷
Chen, Huai-Ting關鍵詞 P2P 借貸平台
貸款目的
貸款率
違約狀態
機器學習
P2P platform
Purpose
Funded Ratio
Loan Status
Machine Learning日期 2023 上傳時間 1-九月-2023 14:57:57 (UTC+8) 摘要 本研究採用 P2P 平台的資料,相較於過往的文獻僅討論小型企業貸款,本研究將全面探討各種貸款目的下的貸款表現,並從借款者和投資者兩種不同角度進行分析,這包括債務整合、小型企業貸款以及信用卡等貸款類型,最後也透過機器學習的方法建構違約及貸款率模型。P2P 借貸平台中的借款者和投資者方面的重要變數包括借款金額、工作年限、年收入、債務收入比、循環信貸餘額等,透過提高借款人的信用特徵和降低投資者的風險意識,可以促進借款人的貸款通過率,並增加投資者對借款人的信任程度,在特定貸款目的(如教育、婚禮等)下,借款金額可能較低,因為這些目的不具備賺錢的能力,可能會增加投資者的風險意識,最後在預測貸款率及違約狀態模型中,XGBoost 表現最佳。
This study utilizes data from a P2P platform. In comparison to previous literaturethat solely focused on small business loans, this research comprehensively discussesthe loan performance across various loan purposes, exploring them from both borrower and investor perspectives. This includes different types of loans such as debtconsolidation, small business loans, credit card loans, and more. Additionally, machine learning methods are employed to construct Loan Status and Funded Ratiomodels. Key variables from the borrower and investor aspects in the P2P lendingplatform include loan amount, years of employment, annual income, debt-to-incomeratio, revolving credit balance, among others.By enhancing the credit characteristicsof borrowers and reducing investors’ risk perceptions, it is possible to promote higherloan approval rates for borrowers and increase investors’ trust in borrowers. For specific loan purposes, such as education or weddings, the loan amounts may be loweras these purposes may not have revenue-generating potential, which could raise investors’ risk awareness.Finally, in predicting loan rates and default status models,XGBoost outperformed other methods.參考文獻 Chen, D., Lai, F., and Lin, Z. (2014). A trust model for online peer-to-peer lending: a lender’s perspective. Information Technology and Management, 15:239–254.Chen, T. and Guestrin, C. (2016). Xgboost: A scalable tree boosting system. In Proceedings of the 22nd acm sigkdd international conference on knowledge discovery and data mining, pages 785–794.Han, J.-T., Chen, Q., Liu, J.-G., Luo, X.-L., and Fan, W. (2018). The persuasion of borrowers’voluntary information in peer to peer lending: An empirical study based on elaboration likelihood model. Computers in Human Behavior, 78:200–214.Jin, Y. and Zhu, Y. (2015). A data-driven approach to predict default risk of loan for online peer-to-peer (p2p) lending. In 2015 Fifth international conference on communication systems and network technologies, pages 609–613. IEEE.Ke, G., Meng, Q., Finley, T., Wang, T., Chen, W., Ma, W., Ye, Q., and Liu, T.-Y. (2017).Lightgbm: A highly efficient gradient boosting decision tree. Advances in neural information processing systems, 30.Lin, X., Li, X., and Zheng, Z. (2017). Evaluating borrower’s default risk in peer-to-peerlending: evidence from a lending platform in china. Applied Economics, 49(35):3538–3545.Ma, X., Sha, J., Wang, D., Yu, Y., Yang, Q., and Niu, X. (2018). Study on a prediction of p2p network loan default based on the machine learning lightgbm and xgboost algorithms according to different high dimensional data cleaning. Electronic Commerce Research and Applications, 31:24–39.Nowak, A., Ross, A., and Yencha, C. (2018). Small business borrowing and peer-to-peer lending: Evidence from lending club. Contemporary Economic Policy, 36(2):318–336.Serrano-Cinca, C., Gutiérrez-Nieto, B., and López-Palacios, L. (2015). Determinants of default in p2p lending. PloS one, 10(10):e0139427.Zhou, J., Li, W., Wang, J., Ding, S., and Xia, C. (2019). Default prediction in p2p lending from high-dimensional data based on machine learning. Physica A: Statistical Mechanics and its Applications, 534:122370. 描述 碩士
國立政治大學
統計學系
110354029資料來源 http://thesis.lib.nccu.edu.tw/record/#G0110354029 資料類型 thesis dc.contributor.advisor 林士貴<br>翁久幸 zh_TW dc.contributor.advisor Lin, Shih-Kuei<br>Weng, Chiu-Hsing en_US dc.contributor.author (作者) 陳槐廷 zh_TW dc.contributor.author (作者) Chen, Huai-Ting en_US dc.creator (作者) 陳槐廷 zh_TW dc.creator (作者) Chen, Huai-Ting en_US dc.date (日期) 2023 en_US dc.date.accessioned 1-九月-2023 14:57:57 (UTC+8) - dc.date.available 1-九月-2023 14:57:57 (UTC+8) - dc.date.issued (上傳時間) 1-九月-2023 14:57:57 (UTC+8) - dc.identifier (其他 識別碼) G0110354029 en_US dc.identifier.uri (URI) http://nccur.lib.nccu.edu.tw/handle/140.119/146907 - dc.description (描述) 碩士 zh_TW dc.description (描述) 國立政治大學 zh_TW dc.description (描述) 統計學系 zh_TW dc.description (描述) 110354029 zh_TW dc.description.abstract (摘要) 本研究採用 P2P 平台的資料,相較於過往的文獻僅討論小型企業貸款,本研究將全面探討各種貸款目的下的貸款表現,並從借款者和投資者兩種不同角度進行分析,這包括債務整合、小型企業貸款以及信用卡等貸款類型,最後也透過機器學習的方法建構違約及貸款率模型。P2P 借貸平台中的借款者和投資者方面的重要變數包括借款金額、工作年限、年收入、債務收入比、循環信貸餘額等,透過提高借款人的信用特徵和降低投資者的風險意識,可以促進借款人的貸款通過率,並增加投資者對借款人的信任程度,在特定貸款目的(如教育、婚禮等)下,借款金額可能較低,因為這些目的不具備賺錢的能力,可能會增加投資者的風險意識,最後在預測貸款率及違約狀態模型中,XGBoost 表現最佳。 zh_TW dc.description.abstract (摘要) This study utilizes data from a P2P platform. In comparison to previous literaturethat solely focused on small business loans, this research comprehensively discussesthe loan performance across various loan purposes, exploring them from both borrower and investor perspectives. This includes different types of loans such as debtconsolidation, small business loans, credit card loans, and more. Additionally, machine learning methods are employed to construct Loan Status and Funded Ratiomodels. Key variables from the borrower and investor aspects in the P2P lendingplatform include loan amount, years of employment, annual income, debt-to-incomeratio, revolving credit balance, among others.By enhancing the credit characteristicsof borrowers and reducing investors’ risk perceptions, it is possible to promote higherloan approval rates for borrowers and increase investors’ trust in borrowers. For specific loan purposes, such as education or weddings, the loan amounts may be loweras these purposes may not have revenue-generating potential, which could raise investors’ risk awareness.Finally, in predicting loan rates and default status models,XGBoost outperformed other methods. en_US dc.description.tableofcontents 摘要 iAbstract ii目次 iii圖目錄 iv表目錄 v第一章 緒論 1第二章 文獻回顧 3第三章 研究方法 6第一節 邏輯斯迴歸 6第二節 決策樹 7第三節 隨機森林 7第四節 LGBM 8第五節 XGBoost 9第四章 實證結果 11第一節 資料描述及資料處理 11第二節 借款者方面 142.1 各貸款目的下對於貸款率之迴歸分析 142.2 借款者在貸款率下實證分析 16第三節 投資者方面 183.1 各貸款目的下對於貸款狀態之邏輯斯迴歸分析 183.2 投資者在貸款狀態下實證分析 21第五章 結論及未來展望 24第一節 結論 24第二節 未來展望 25附錄 A 26參考文獻 27 zh_TW dc.format.extent 1059853 bytes - dc.format.mimetype application/pdf - dc.source.uri (資料來源) http://thesis.lib.nccu.edu.tw/record/#G0110354029 en_US dc.subject (關鍵詞) P2P 借貸平台 zh_TW dc.subject (關鍵詞) 貸款目的 zh_TW dc.subject (關鍵詞) 貸款率 zh_TW dc.subject (關鍵詞) 違約狀態 zh_TW dc.subject (關鍵詞) 機器學習 zh_TW dc.subject (關鍵詞) P2P platform en_US dc.subject (關鍵詞) Purpose en_US dc.subject (關鍵詞) Funded Ratio en_US dc.subject (關鍵詞) Loan Status en_US dc.subject (關鍵詞) Machine Learning en_US dc.title (題名) P2P借貸中借款人特徵與貸款表現關係之實證研究:以Lending Club和機器學習方法為例 zh_TW dc.title (題名) An Empirical Study of the Relationship between Borrower Characteristics and Loan Performance in Peer-to-Peer Lending: Evidence from Lending Club and Machine Learning Techniques en_US dc.type (資料類型) thesis en_US dc.relation.reference (參考文獻) Chen, D., Lai, F., and Lin, Z. (2014). A trust model for online peer-to-peer lending: a lender’s perspective. Information Technology and Management, 15:239–254.Chen, T. and Guestrin, C. (2016). Xgboost: A scalable tree boosting system. In Proceedings of the 22nd acm sigkdd international conference on knowledge discovery and data mining, pages 785–794.Han, J.-T., Chen, Q., Liu, J.-G., Luo, X.-L., and Fan, W. (2018). The persuasion of borrowers’voluntary information in peer to peer lending: An empirical study based on elaboration likelihood model. Computers in Human Behavior, 78:200–214.Jin, Y. and Zhu, Y. (2015). A data-driven approach to predict default risk of loan for online peer-to-peer (p2p) lending. In 2015 Fifth international conference on communication systems and network technologies, pages 609–613. IEEE.Ke, G., Meng, Q., Finley, T., Wang, T., Chen, W., Ma, W., Ye, Q., and Liu, T.-Y. (2017).Lightgbm: A highly efficient gradient boosting decision tree. Advances in neural information processing systems, 30.Lin, X., Li, X., and Zheng, Z. (2017). Evaluating borrower’s default risk in peer-to-peerlending: evidence from a lending platform in china. Applied Economics, 49(35):3538–3545.Ma, X., Sha, J., Wang, D., Yu, Y., Yang, Q., and Niu, X. (2018). Study on a prediction of p2p network loan default based on the machine learning lightgbm and xgboost algorithms according to different high dimensional data cleaning. Electronic Commerce Research and Applications, 31:24–39.Nowak, A., Ross, A., and Yencha, C. (2018). Small business borrowing and peer-to-peer lending: Evidence from lending club. Contemporary Economic Policy, 36(2):318–336.Serrano-Cinca, C., Gutiérrez-Nieto, B., and López-Palacios, L. (2015). Determinants of default in p2p lending. PloS one, 10(10):e0139427.Zhou, J., Li, W., Wang, J., Ding, S., and Xia, C. (2019). Default prediction in p2p lending from high-dimensional data based on machine learning. Physica A: Statistical Mechanics and its Applications, 534:122370. zh_TW