學術產出-Theses
Article View/Open
Publication Export
-
題名 學習型預測模型應用於外籍移工借貸
The learning-based credit and risk assessment models for the P2P lending of migrant workers作者 李昀儒
Lee, Yun-Ru貢獻者 蔡瑞煌
Tsaih, Rua-Huan
李昀儒
Lee, Yun-Ru關鍵詞 學習型信用預測模型
學習型風險預測模型
外籍移工
自適應單隱藏層前饋神經網路
learning-based credit assessment model
learning-based risk assessment model
migrant workers
adaptive single hidden layer feed-forward network日期 2022 上傳時間 1-Aug-2022 17:26:19 (UTC+8) 摘要 外籍移工是台灣不可或缺的勞動力之一，其人數從民國80年不到3000人，到民國111年已成長到66萬人，占台灣總勞動人口數約2.8%，是社會中不可忽視的一群勞動力。外籍移工每月會將大部分所得匯回母國以貼補家用，當今天在金錢上有急需時，往往會因為語言隔閡及信託資料缺乏等因素，導致他們在台灣借貸上困難重重，個人的相關權益受損。 此研究透過產學合作，建立一個專給外籍移工使用的P2P借貸平台QLend，去解決上述提到的問題。本研究將重點放在平台裡頭所使用到的學習型信用預測模型 (LCAM) 及學習型風險預測模型 (LRAM)，透過移工基本資料、工作情形、遲還機率及設計的序列模組動態調整 (SMDA) 機制進而去推斷其信用分數及違約風險。由於P2P借貸評估信用風險且借款對象為外籍移工，本研究為先行者，透過文獻回顧與領域專家討論，決定出信用分數及違約風險自變數。透過自變數及SMDA機制最終產生符合學習目標的ASLFN。此研究欲驗證模型提出之SMDA機制之有效性，選擇與KNN及DT (Decision tree) 之現有分類模型進行比較，實驗結果證實SMDA機制是有效的，準確率皆可達八成八，同時也可證實在「信用評估」及「風險評估」上均比KNN及DT來得好。
Migrant workers are one of the indispensable workforces in Taiwan. The number of people has grown from less than 3,000 in ROC 80 to 660,000 in ROC 111, accounting for about 2.8% of Taiwan`s total labor force. It’s a group of labor that cannot be ignored in society. Migrant workers remit most of their income back to their home countries each month to supply for their families. When there is an urgent need today, factors such as language barriers and lack of trust information often make them difficult to borrow in Taiwan. Personal rights are violated. Therefore, through industry-university cooperation, this study have established a P2P lending platform QLend for migrant workers to solve the above-mentioned problems. This research focuses on the learning-based credit assessment model (LCAM) and learning-based risk assessment model (LRAM) used in the platform. Based on the information of migrant workers, work situation, the ratio of late payment, and the proposed sequentially modular dynamic adjusting (SMDA) mechanism evaluate their credit score and default risk. Since P2P lending evaluates credit risk and the borrowers are migrant workers, this study is a pioneer. Through literature review and discussion with experts in the domain, the credit score and default risk independent variables are determined. This study intends to verify the effectiveness of the SMDA mechanism proposed by the model and chooses to compare with the existing classification models of KNN and DT (Decision tree). The experimental results confirm that the SMDA mechanism is effective, and the accuracy rate can reach 88%. At the same time, it can also be proved that it is better than KNN and DT in terms of credit assessment and risk assessment.參考文獻 Altman, E. I., and Saunders, A. 1997. "Credit Risk Measurement: Developments over the Last 20 Years," Journal of banking & finance (21:11-12), pp. 1721-1742.Azam, M. 2015. "The Role of Migrant Workers Remittances in Fostering Economic Growth: The Four Asian Developing Countries’ Experiences," International Journal of Social Economics).Byanjankar, A., Heikkilä, M., and Mezei, J. 2015. "Predicting Credit Risk in Peer-to-Peer Lending: A Neural Network Approach," 2015 IEEE symposium series on computational intelligence: IEEE, pp. 719-725.Chang, H.-Y. 2019. "The Sequentially-Learning-Based Algorithm and the Prediction of the Turning Points of Bull and Bear Markets." Master Thesis, National Chengchi University, Taipei.Chen, S., Wang, Q., and Liu, S. 2019. "Credit Risk Prediction in Peer-to-Peer Lending with Ensemble Learning Framework," 2019 Chinese Control And Decision Conference (CCDC): IEEE, pp. 4373-4377.Chimhowu, A., Piesse, J., and Pinder, C. 2003. "Assessing the Impact of Migrant Workers’ Remittances on Poverty," EDIAS Conference on New Directions in Impact Assessment for Development: Methods and Practice, United Kingdom. Retrieved from https://pdfs. semanticscholar. org/ec9d/9b1f4831b91d346dced0e8e644992e3fb95d. pdf: Citeseer.Čížek, P., and Víšek, J. Á. 2000. "Least Trimmed Squares," in Xplore®—Application Guide. Springer, pp. 49-63.Davis, K. 2016. "Peer-to-Peer Lending: Structures, Risks and Regulation," JASSA:3), pp. 37-44.Dietterich, T. 1995. "Overfitting and Undercomputing in Machine Learning," ACM computing surveys (CSUR) (27:3), pp. 326-327.Dimiduk, D. M., Holm, E. A., and Niezgoda, S. R. 2018. "Perspectives on the Impact of Machine Learning, Deep Learning, and Artificial Intelligence on Materials, Processes, and Structures Engineering," Integrating Materials and Manufacturing Innovation (7:3), pp. 157-172.Everett, C. R. 2015. "Group Membership, Relationship Banking and Loan Default Risk: The Case of Online Social Lending," Banking and Finance Review (7:2).Giudici, P., Hadji-Misheva, B., and Spelta, A. 2019. "Network Based Scoring Models to Improve Credit Risk Management in Peer to Peer Lending Platforms," Frontiers in artificial intelligence (2), p. 3.Hamori, S., Kawai, M., Kume, T., Murakami, Y., and Watanabe, C. 2018. "Ensemble Learning or Deep Learning? Application to Default Risk Analysis," Journal of Risk and Financial Management (11:1), p. 12.Hawkins, D. M. 1994. "The Feasible Solution Algorithm for Least Trimmed Squares Regression," Computational statistics & data analysis (17:2), pp. 185-196.He, F., Li, Y., Xu, T., Yin, L., Zhang, W., and Zhang, X. 2020. "A Data-Analytics Approach for Risk Evaluation in Peer-to-Peer Lending Platforms," IEEE Intelligent Systems (35:3), pp. 85-95.Hochreiter, S. 1998. "The Vanishing Gradient Problem During Learning Recurrent Neural Nets and Problem Solutions," International Journal of Uncertainty, Fuzziness and Knowledge-Based Systems (6:02), pp. 107-116.Hong, J.-C., Yang, Y.-C., Chen, J.-F., and Yang, T.-Y. 2005. "Foreign Workers in Taiwan," National Taiwan Normal University).Huang, S.-Y., Tsaih, R.-H., and Yu, F. 2014. "Topological Pattern Discovery and Feature Extraction for Fraudulent Financial Reporting," Expert systems with applications (41:9), pp. 4360-4372.Huang, Z., Chen, H., Hsu, C.-J., Chen, W.-H., and Wu, S. 2004. "Credit Rating Analysis with Support Vector Machines and Neural Networks: A Market Comparative Study," Decision support systems (37:4), pp. 543-558.Iyer, R., Khwaja, A. I., Luttmer, E. F., and Shue, K. 2009. "Screening in New Credit Markets: Can Individual Lenders Infer Borrower Creditworthiness in Peer-to-Peer Lending?," AFA 2011 Denver meetings paper.Ji, X., Yu, L., and Fu, J. 2019. "Evaluating Personal Default Risk in P2p Lending Platform: Based on Dual Hesitant Pythagorean Fuzzy Todim Approach," Mathematics (8:1), p. 8.Jin, Y., and Zhu, Y. 2015. "A Data-Driven Approach to Predict Default Risk of Loan for Online Peer-to-Peer (P2p) Lending," 2015 Fifth International Conference on Communication Systems and Network Technologies: IEEE, pp. 609-613.Karaa, A., and Krichene, A. 2012. "Credit-Risk Assessment Using Support Vectors Machine and Multilayer Neural Network Models: A Comparative Study Case of a Tunisian Bank," Accounting and Management Information Systems (11:4), p. 587.Khalil Alsmadi, M., Omar, K. B., Noah, S. A., and Almarashdah, I. 2009. "Performance Comparison of Multi-Layer Perceptron (Back Propagation, Delta Rule and Perceptron) Algorithms in Neural Networks," 2009 IEEE International Advance Computing Conference: IEEE, pp. 296-299.Khemakhem, S., and Boujelbene, Y. 2015. "Credit Risk Prediction: A Comparative Study between Discriminant Analysis and the Neural Network Approach," Accounting and Management Information Systems (14:1), p. 60.Li, L., Zhao, T., Xie, Y., and Feng, Y. 2020a. "Interpretable Machine Learning Based on Integration of Nlp and Psychology in Peer-to-Peer Lending Risk Evaluation," CCF International Conference on Natural Language Processing and Chinese Computing: Springer, pp. 429-441.Li, M., Yan, C., and Liu, W. 2021. "The Network Loan Risk Prediction Model Based on Convolutional Neural Network and Stacking Fusion Model," Applied Soft Computing (113), p. 107961.Li, W., Ding, S., Chen, Y., and Yang, S. 2018. "Heterogeneous Ensemble for Default Prediction of Peer-to-Peer Lending in China," Ieee Access (6), pp. 54396-54406.Li, W., Ding, S., Wang, H., Chen, Y., and Yang, S. 2020b. "Heterogeneous Ensemble Learning with Feature Engineering for Default Prediction in Peer-to-Peer Lending in China," World Wide Web (23:1), pp. 23-45.Lin, X., Li, X., and Zheng, Z. 2017. "Evaluating Borrower’s Default Risk in Peer-to-Peer Lending: Evidence from a Lending Platform in China," Applied Economics (49:35), pp. 3538-3545.Liu, J., Zhang, S., and Fan, H. 2022. "A Two-Stage Hybrid Credit Risk Prediction Model Based on Xgboost and Graph-Based Deep Neural Network," Expert Systems with Applications (195), p. 116624.Malekipirbazari, M., and Aksakalli, V. 2015. "Risk Assessment in Social Lending Via Random Forests," Expert Systems with Applications (42:10), pp. 4621-4631.Mezei, J., Byanjankar, A., and Heikkilä, M. 2018. "Credit Risk Evaluation in Peer-to-Peer Lending with Linguistic Data Transformation and Supervised Learning,").Möllenkamp, N. 2017. "Determinants of Loan Performance in P2p Lending." University of Twente.Ongsulee, P. 2017. "Artificial Intelligence, Machine Learning and Deep Learning," 2017 15th International Conference on ICT and Knowledge Engineering (ICT&KE): IEEE, pp. 1-6.Polena, M., and Regner, T. 2018. "Determinants of Borrowers’ Default in P2p Lending under Consideration of the Loan Risk Class," Games (9:4), p. 82.Preisser, J. S., and Qaqish, B. F. 1996. "Deletion Diagnostics for Generalised Estimating Equations," Biometrika (83:3), pp. 551-562.Rao, C., Liu, M., Goh, M., and Wen, J. 2020. "2-Stage Modified Random Forest Model for Credit Risk Assessment of P2p Network Lending to “Three Rurals” Borrowers," Applied Soft Computing (95), p. 106570.Rousseeuw, P. J., and Van Driessen, K. 2006. "Computing Lts Regression for Large Data Sets," Data mining and knowledge discovery (12:1), pp. 29-45.Serrano-Cinca, C., and Gutiérrez-Nieto, B. 2016. "The Use of Profit Scoring as an Alternative to Credit Scoring Systems in Peer-to-Peer (P2p) Lending," Decision Support Systems (89), pp. 113-122.Serrano-Cinca, C., Gutiérrez-Nieto, B., and López-Palacios, L. 2015. "Determinants of Default in P2p Lending," PloS one (10:10), p. e0139427.Song, Y., Wang, Y., Ye, X., Wang, D., Yin, Y., and Wang, Y. 2020. "Multi-View Ensemble Learning Based on Distance-to-Model and Adaptive Clustering for Imbalanced Credit Risk Assessment in P2p Lending," Information Sciences (525), pp. 182-204.Stone, G. O. 1986. "An Analysis of the Delta Rule and the Learning of Statistical Associations," Parallel distributed processing: Explorations in the microstructure of cognition (1), pp. 444-459.Tsai, Y.-H., Jheng, Y.-J., and Tsaih, R.-H. 2019. "The Cramming, Softening and Integrating Learning Algorithm with Parametric Relu Activation Function for Binary Input/Output Problems," 2019 International Joint Conference on Neural Networks (IJCNN): IEEE, pp. 1-7.Tsaih, R. 1993. "The Softening Learning Procedure," Mathematical and computer modelling (18:8), pp. 61-64.Tsaih, R. 1998. "An Explanation of Reasoning Neural Networks," Mathematical and Computer Modelling (28:2), pp. 37-44.Tsaih, R.-H., and Cheng, T.-C. 2009. "A Resistant Learning Procedure for Coping with Outliers," Annals of Mathematics and Artificial Intelligence (57:2), pp. 161-180.Van Ooyen, A., and Nienhuis, B. 1992. "Improving the Convergence of the Back-Propagation Algorithm," Neural networks (5:3), pp. 465-471.Wang, T., and Li, J. 2019. "An Improved Support Vector Machine and Its Application in P2p Lending Personal Credit Scoring," IOP Conference Series: Materials Science and Engineering: IOP Publishing, p. 062041.Wilamowski, B. M. 2009. "Neural Network Architectures and Learning Algorithms," IEEE Industrial Electronics Magazine (3:4), pp. 56-63.Yang, R.-H. 2022. "An Adaptive Learning-Based Model for Copper Price Forecasting." Master Thesis, National Chengchi University, Taipei, pp. 1-78.Zeng, G. 2020. "On the Confusion Matrix in Credit Scoring and Its Analytical Properties," Communications in Statistics-Theory and Methods (49:9), pp. 2080-2093.Zhang, W., Wang, C., Zhang, Y., and Wang, J. 2020. "Credit Risk Evaluation Model with Textual Features from Loan Descriptions for P2p Lending," Electronic Commerce Research and Applications (42), p. 100989.Zhu, Y., Xie, C., Sun, B., Wang, G.-J., and Yan, X.-G. 2016. "Predicting China’s Sme Credit Risk in Supply Chain Financing by Logistic Regression, Artificial Neural Network and Hybrid Models," Sustainability (8:5), p. 433. 描述 碩士
國立政治大學
資訊管理學系
109356047資料來源 http://thesis.lib.nccu.edu.tw/record/#G0109356047 資料類型 thesis dc.contributor.advisor 蔡瑞煌 zh_TW dc.contributor.advisor Tsaih, Rua-Huan en_US dc.contributor.author (Authors) 李昀儒 zh_TW dc.contributor.author (Authors) Lee, Yun-Ru en_US dc.creator (作者) 李昀儒 zh_TW dc.creator (作者) Lee, Yun-Ru en_US dc.date (日期) 2022 en_US dc.date.accessioned 1-Aug-2022 17:26:19 (UTC+8) - dc.date.available 1-Aug-2022 17:26:19 (UTC+8) - dc.date.issued (上傳時間) 1-Aug-2022 17:26:19 (UTC+8) - dc.identifier (Other Identifiers) G0109356047 en_US dc.identifier.uri (URI) http://nccur.lib.nccu.edu.tw/handle/140.119/141049 - dc.description (描述) 碩士 zh_TW dc.description (描述) 國立政治大學 zh_TW dc.description (描述) 資訊管理學系 zh_TW dc.description (描述) 109356047 zh_TW dc.description.abstract (摘要) 外籍移工是台灣不可或缺的勞動力之一，其人數從民國80年不到3000人，到民國111年已成長到66萬人，占台灣總勞動人口數約2.8%，是社會中不可忽視的一群勞動力。外籍移工每月會將大部分所得匯回母國以貼補家用，當今天在金錢上有急需時，往往會因為語言隔閡及信託資料缺乏等因素，導致他們在台灣借貸上困難重重，個人的相關權益受損。 此研究透過產學合作，建立一個專給外籍移工使用的P2P借貸平台QLend，去解決上述提到的問題。本研究將重點放在平台裡頭所使用到的學習型信用預測模型 (LCAM) 及學習型風險預測模型 (LRAM)，透過移工基本資料、工作情形、遲還機率及設計的序列模組動態調整 (SMDA) 機制進而去推斷其信用分數及違約風險。由於P2P借貸評估信用風險且借款對象為外籍移工，本研究為先行者，透過文獻回顧與領域專家討論，決定出信用分數及違約風險自變數。透過自變數及SMDA機制最終產生符合學習目標的ASLFN。此研究欲驗證模型提出之SMDA機制之有效性，選擇與KNN及DT (Decision tree) 之現有分類模型進行比較，實驗結果證實SMDA機制是有效的，準確率皆可達八成八，同時也可證實在「信用評估」及「風險評估」上均比KNN及DT來得好。 zh_TW dc.description.abstract (摘要) Migrant workers are one of the indispensable workforces in Taiwan. The number of people has grown from less than 3,000 in ROC 80 to 660,000 in ROC 111, accounting for about 2.8% of Taiwan`s total labor force. It’s a group of labor that cannot be ignored in society. Migrant workers remit most of their income back to their home countries each month to supply for their families. When there is an urgent need today, factors such as language barriers and lack of trust information often make them difficult to borrow in Taiwan. Personal rights are violated. Therefore, through industry-university cooperation, this study have established a P2P lending platform QLend for migrant workers to solve the above-mentioned problems. This research focuses on the learning-based credit assessment model (LCAM) and learning-based risk assessment model (LRAM) used in the platform. Based on the information of migrant workers, work situation, the ratio of late payment, and the proposed sequentially modular dynamic adjusting (SMDA) mechanism evaluate their credit score and default risk. Since P2P lending evaluates credit risk and the borrowers are migrant workers, this study is a pioneer. Through literature review and discussion with experts in the domain, the credit score and default risk independent variables are determined. This study intends to verify the effectiveness of the SMDA mechanism proposed by the model and chooses to compare with the existing classification models of KNN and DT (Decision tree). The experimental results confirm that the SMDA mechanism is effective, and the accuracy rate can reach 88%. At the same time, it can also be proved that it is better than KNN and DT in terms of credit assessment and risk assessment. en_US dc.description.tableofcontents 摘要 IAbstract IIIChapter 1 Introduction 1Chapter 2 Literature review 42.1 P2P lending for x-attribute 42.2 Learning-based approaches on P2P lending credit risk forecast 52.3 The adaptive learning-based forecasting model of (Yang, 2022) 82.3.1 The single-hidden layer feed-forward network (SLFN) with the single output node 102.3.2 Weight-tuning associated with SLFN with the single output node 112.3.3 The adaptive single hidden layer feed-forward network (ASLFN) with the single output node 12Chapter 3 The learning-based credit and risk assessment model 143.1 The sequentially modular dynamic adjusting (SMDA) mechanism 153.2 The inferencing model via SMDA mechanism 23Chapter 4 Experiment design 244.1 Data description 254.1.1 Input variables 254.1.2 Output discussions 324.1.3 Encoding method of category type data 344.2 Data preprocessing 344.2.1 Data normalization 344.2.2 Missing value 354.2.3 Dataset sampling 374.3 Model performance measures 38Chapter 5 Experiment results 425.1 Optimized hyperparameter 425.2 Credit score 455.2.1 Training result 455.2.2 Testing result 475.2.3 Overall performance in credit score assessment 495.3 Default risk 505.3.1 Training result 505.3.2 Testing result 525.3.3 Overall performance in default risk assessment 54Chapter 6 Conclusion and future work 566.1 Conclusion 566.2 Limitations and future work 57References 58Appendix A – Credit score assessment in testing 65Appendix B – Confusion matrix of credit score assessment in testing 67Appendix C – Confusion matrix of credit score assessment in overall 69Appendix D – Default risk assessment in testing 71Appendix E – Confusion matrix of default risk assessment in testing 73Appendix F – Confusion matrix of default risk assessment in overall 75 zh_TW dc.format.extent 4013864 bytes - dc.format.mimetype application/pdf - dc.source.uri (資料來源) http://thesis.lib.nccu.edu.tw/record/#G0109356047 en_US dc.subject (關鍵詞) 學習型信用預測模型 zh_TW dc.subject (關鍵詞) 學習型風險預測模型 zh_TW dc.subject (關鍵詞) 外籍移工 zh_TW dc.subject (關鍵詞) 自適應單隱藏層前饋神經網路 zh_TW dc.subject (關鍵詞) learning-based credit assessment model en_US dc.subject (關鍵詞) learning-based risk assessment model en_US dc.subject (關鍵詞) migrant workers en_US dc.subject (關鍵詞) adaptive single hidden layer feed-forward network en_US dc.title (題名) 學習型預測模型應用於外籍移工借貸 zh_TW dc.title (題名) The learning-based credit and risk assessment models for the P2P lending of migrant workers en_US dc.type (資料類型) thesis en_US dc.relation.reference (參考文獻) Altman, E. I., and Saunders, A. 1997. "Credit Risk Measurement: Developments over the Last 20 Years," Journal of banking & finance (21:11-12), pp. 1721-1742.Azam, M. 2015. "The Role of Migrant Workers Remittances in Fostering Economic Growth: The Four Asian Developing Countries’ Experiences," International Journal of Social Economics).Byanjankar, A., Heikkilä, M., and Mezei, J. 2015. "Predicting Credit Risk in Peer-to-Peer Lending: A Neural Network Approach," 2015 IEEE symposium series on computational intelligence: IEEE, pp. 719-725.Chang, H.-Y. 2019. "The Sequentially-Learning-Based Algorithm and the Prediction of the Turning Points of Bull and Bear Markets." Master Thesis, National Chengchi University, Taipei.Chen, S., Wang, Q., and Liu, S. 2019. "Credit Risk Prediction in Peer-to-Peer Lending with Ensemble Learning Framework," 2019 Chinese Control And Decision Conference (CCDC): IEEE, pp. 4373-4377.Chimhowu, A., Piesse, J., and Pinder, C. 2003. "Assessing the Impact of Migrant Workers’ Remittances on Poverty," EDIAS Conference on New Directions in Impact Assessment for Development: Methods and Practice, United Kingdom. Retrieved from https://pdfs. semanticscholar. org/ec9d/9b1f4831b91d346dced0e8e644992e3fb95d. pdf: Citeseer.Čížek, P., and Víšek, J. Á. 2000. "Least Trimmed Squares," in Xplore®—Application Guide. Springer, pp. 49-63.Davis, K. 2016. "Peer-to-Peer Lending: Structures, Risks and Regulation," JASSA:3), pp. 37-44.Dietterich, T. 1995. "Overfitting and Undercomputing in Machine Learning," ACM computing surveys (CSUR) (27:3), pp. 326-327.Dimiduk, D. M., Holm, E. A., and Niezgoda, S. R. 2018. "Perspectives on the Impact of Machine Learning, Deep Learning, and Artificial Intelligence on Materials, Processes, and Structures Engineering," Integrating Materials and Manufacturing Innovation (7:3), pp. 157-172.Everett, C. R. 2015. "Group Membership, Relationship Banking and Loan Default Risk: The Case of Online Social Lending," Banking and Finance Review (7:2).Giudici, P., Hadji-Misheva, B., and Spelta, A. 2019. "Network Based Scoring Models to Improve Credit Risk Management in Peer to Peer Lending Platforms," Frontiers in artificial intelligence (2), p. 3.Hamori, S., Kawai, M., Kume, T., Murakami, Y., and Watanabe, C. 2018. "Ensemble Learning or Deep Learning? Application to Default Risk Analysis," Journal of Risk and Financial Management (11:1), p. 12.Hawkins, D. M. 1994. "The Feasible Solution Algorithm for Least Trimmed Squares Regression," Computational statistics & data analysis (17:2), pp. 185-196.He, F., Li, Y., Xu, T., Yin, L., Zhang, W., and Zhang, X. 2020. "A Data-Analytics Approach for Risk Evaluation in Peer-to-Peer Lending Platforms," IEEE Intelligent Systems (35:3), pp. 85-95.Hochreiter, S. 1998. "The Vanishing Gradient Problem During Learning Recurrent Neural Nets and Problem Solutions," International Journal of Uncertainty, Fuzziness and Knowledge-Based Systems (6:02), pp. 107-116.Hong, J.-C., Yang, Y.-C., Chen, J.-F., and Yang, T.-Y. 2005. "Foreign Workers in Taiwan," National Taiwan Normal University).Huang, S.-Y., Tsaih, R.-H., and Yu, F. 2014. "Topological Pattern Discovery and Feature Extraction for Fraudulent Financial Reporting," Expert systems with applications (41:9), pp. 4360-4372.Huang, Z., Chen, H., Hsu, C.-J., Chen, W.-H., and Wu, S. 2004. "Credit Rating Analysis with Support Vector Machines and Neural Networks: A Market Comparative Study," Decision support systems (37:4), pp. 543-558.Iyer, R., Khwaja, A. I., Luttmer, E. F., and Shue, K. 2009. "Screening in New Credit Markets: Can Individual Lenders Infer Borrower Creditworthiness in Peer-to-Peer Lending?," AFA 2011 Denver meetings paper.Ji, X., Yu, L., and Fu, J. 2019. "Evaluating Personal Default Risk in P2p Lending Platform: Based on Dual Hesitant Pythagorean Fuzzy Todim Approach," Mathematics (8:1), p. 8.Jin, Y., and Zhu, Y. 2015. "A Data-Driven Approach to Predict Default Risk of Loan for Online Peer-to-Peer (P2p) Lending," 2015 Fifth International Conference on Communication Systems and Network Technologies: IEEE, pp. 609-613.Karaa, A., and Krichene, A. 2012. "Credit-Risk Assessment Using Support Vectors Machine and Multilayer Neural Network Models: A Comparative Study Case of a Tunisian Bank," Accounting and Management Information Systems (11:4), p. 587.Khalil Alsmadi, M., Omar, K. B., Noah, S. A., and Almarashdah, I. 2009. "Performance Comparison of Multi-Layer Perceptron (Back Propagation, Delta Rule and Perceptron) Algorithms in Neural Networks," 2009 IEEE International Advance Computing Conference: IEEE, pp. 296-299.Khemakhem, S., and Boujelbene, Y. 2015. "Credit Risk Prediction: A Comparative Study between Discriminant Analysis and the Neural Network Approach," Accounting and Management Information Systems (14:1), p. 60.Li, L., Zhao, T., Xie, Y., and Feng, Y. 2020a. "Interpretable Machine Learning Based on Integration of Nlp and Psychology in Peer-to-Peer Lending Risk Evaluation," CCF International Conference on Natural Language Processing and Chinese Computing: Springer, pp. 429-441.Li, M., Yan, C., and Liu, W. 2021. "The Network Loan Risk Prediction Model Based on Convolutional Neural Network and Stacking Fusion Model," Applied Soft Computing (113), p. 107961.Li, W., Ding, S., Chen, Y., and Yang, S. 2018. "Heterogeneous Ensemble for Default Prediction of Peer-to-Peer Lending in China," Ieee Access (6), pp. 54396-54406.Li, W., Ding, S., Wang, H., Chen, Y., and Yang, S. 2020b. "Heterogeneous Ensemble Learning with Feature Engineering for Default Prediction in Peer-to-Peer Lending in China," World Wide Web (23:1), pp. 23-45.Lin, X., Li, X., and Zheng, Z. 2017. "Evaluating Borrower’s Default Risk in Peer-to-Peer Lending: Evidence from a Lending Platform in China," Applied Economics (49:35), pp. 3538-3545.Liu, J., Zhang, S., and Fan, H. 2022. "A Two-Stage Hybrid Credit Risk Prediction Model Based on Xgboost and Graph-Based Deep Neural Network," Expert Systems with Applications (195), p. 116624.Malekipirbazari, M., and Aksakalli, V. 2015. "Risk Assessment in Social Lending Via Random Forests," Expert Systems with Applications (42:10), pp. 4621-4631.Mezei, J., Byanjankar, A., and Heikkilä, M. 2018. "Credit Risk Evaluation in Peer-to-Peer Lending with Linguistic Data Transformation and Supervised Learning,").Möllenkamp, N. 2017. "Determinants of Loan Performance in P2p Lending." University of Twente.Ongsulee, P. 2017. "Artificial Intelligence, Machine Learning and Deep Learning," 2017 15th International Conference on ICT and Knowledge Engineering (ICT&KE): IEEE, pp. 1-6.Polena, M., and Regner, T. 2018. "Determinants of Borrowers’ Default in P2p Lending under Consideration of the Loan Risk Class," Games (9:4), p. 82.Preisser, J. S., and Qaqish, B. F. 1996. "Deletion Diagnostics for Generalised Estimating Equations," Biometrika (83:3), pp. 551-562.Rao, C., Liu, M., Goh, M., and Wen, J. 2020. "2-Stage Modified Random Forest Model for Credit Risk Assessment of P2p Network Lending to “Three Rurals” Borrowers," Applied Soft Computing (95), p. 106570.Rousseeuw, P. J., and Van Driessen, K. 2006. "Computing Lts Regression for Large Data Sets," Data mining and knowledge discovery (12:1), pp. 29-45.Serrano-Cinca, C., and Gutiérrez-Nieto, B. 2016. "The Use of Profit Scoring as an Alternative to Credit Scoring Systems in Peer-to-Peer (P2p) Lending," Decision Support Systems (89), pp. 113-122.Serrano-Cinca, C., Gutiérrez-Nieto, B., and López-Palacios, L. 2015. "Determinants of Default in P2p Lending," PloS one (10:10), p. e0139427.Song, Y., Wang, Y., Ye, X., Wang, D., Yin, Y., and Wang, Y. 2020. "Multi-View Ensemble Learning Based on Distance-to-Model and Adaptive Clustering for Imbalanced Credit Risk Assessment in P2p Lending," Information Sciences (525), pp. 182-204.Stone, G. O. 1986. "An Analysis of the Delta Rule and the Learning of Statistical Associations," Parallel distributed processing: Explorations in the microstructure of cognition (1), pp. 444-459.Tsai, Y.-H., Jheng, Y.-J., and Tsaih, R.-H. 2019. "The Cramming, Softening and Integrating Learning Algorithm with Parametric Relu Activation Function for Binary Input/Output Problems," 2019 International Joint Conference on Neural Networks (IJCNN): IEEE, pp. 1-7.Tsaih, R. 1993. "The Softening Learning Procedure," Mathematical and computer modelling (18:8), pp. 61-64.Tsaih, R. 1998. "An Explanation of Reasoning Neural Networks," Mathematical and Computer Modelling (28:2), pp. 37-44.Tsaih, R.-H., and Cheng, T.-C. 2009. "A Resistant Learning Procedure for Coping with Outliers," Annals of Mathematics and Artificial Intelligence (57:2), pp. 161-180.Van Ooyen, A., and Nienhuis, B. 1992. "Improving the Convergence of the Back-Propagation Algorithm," Neural networks (5:3), pp. 465-471.Wang, T., and Li, J. 2019. "An Improved Support Vector Machine and Its Application in P2p Lending Personal Credit Scoring," IOP Conference Series: Materials Science and Engineering: IOP Publishing, p. 062041.Wilamowski, B. M. 2009. "Neural Network Architectures and Learning Algorithms," IEEE Industrial Electronics Magazine (3:4), pp. 56-63.Yang, R.-H. 2022. "An Adaptive Learning-Based Model for Copper Price Forecasting." Master Thesis, National Chengchi University, Taipei, pp. 1-78.Zeng, G. 2020. "On the Confusion Matrix in Credit Scoring and Its Analytical Properties," Communications in Statistics-Theory and Methods (49:9), pp. 2080-2093.Zhang, W., Wang, C., Zhang, Y., and Wang, J. 2020. "Credit Risk Evaluation Model with Textual Features from Loan Descriptions for P2p Lending," Electronic Commerce Research and Applications (42), p. 100989.Zhu, Y., Xie, C., Sun, B., Wang, G.-J., and Yan, X.-G. 2016. "Predicting China’s Sme Credit Risk in Supply Chain Financing by Logistic Regression, Artificial Neural Network and Hybrid Models," Sustainability (8:5), p. 433. zh_TW dc.identifier.doi (DOI) 10.6814/NCCU202200880 en_US
