CSRLoan: Cold Start Loan Recommendation with Semantic-Enhanced Neural Matrix Factorization

Recommending loan products to applicants would benefit many financial businesses and individuals. Nevertheless, many loan products suffer from the cold start problem; i.e., there are no available historical data for training the recommendation model. Considering the delayed feedback and the complex semantic properties of loans, methods for general cold start recommendation cannot be directly used. Moreover, existing loan recommendation methods ignore the default risk, which should be evaluated along with the approval rate. To solve these challenges, we propose CSRLoan for cold start loan recommendation. CSRLoan employs pretraining techniques to learn the embeddings of statements, which captures the intrinsic semantic information of different loans. For recommendation, we design a dual neural matrix factorization (NMF) model, which can not only capture the semantic information of both loan products and applicants but also generate the recommendation results and default risk at the same time. Extensive experiments have been conducted on real-world datasets to evaluate the effectiveness and efficiency of the proposed CSRLoan.

[1]  Chongren Wang,et al.  A Deep Learning Approach for Credit Scoring Using Feature Embedded Transformer , 2022, Applied Sciences.

[2]  Wanan Liu,et al.  Credit scoring based on tree-enhanced gradient boosting decision trees , 2021, Expert Syst. Appl..

[3]  Xiangliang Zhang,et al.  A Graph-based Approach for Trajectory Similarity Computation in Spatial Networks , 2021, KDD.

[4]  Zhixin Li,et al.  Modelling risk and return awareness for p2p lending recommendation with graph convolutional networks , 2021, Applied Intelligence.

[5]  Nipon Theera-Umpon,et al.  A Partially Interpretable Adaptive Softmax Regression for Credit Scoring , 2021, Applied Sciences.

[6]  W. Verbeke,et al.  Cost-sensitive learning for profit-driven credit scoring , 2020, J. Oper. Res. Soc..

[7]  Luciano Floridi,et al.  GPT-3: Its Nature, Scope, Limits, and Consequences , 2020, Minds and Machines.

[8]  Iadh Ounis,et al.  A Heterogeneous Graph Neural Model for Cold-start Recommendation , 2020, SIGIR.

[9]  Chao Zhang,et al.  Spatiotemporal Activity Modeling via Hierarchical Cross-Modal Embedding , 2020, IEEE Transactions on Knowledge and Data Engineering.

[10]  Zhiguo Gong,et al.  A Common Topic Transfer Learning Model for Crossing City POI Recommendations , 2019, IEEE Transactions on Cybernetics.

[11]  Srinivasan Parthasarathy,et al.  EndCold: An End-to-End Framework for Cold Question Routing in Community Question Answering Services , 2019, IJCAI.

[12]  Enhong Chen,et al.  Finding potential lenders in P2P lending: A Hybrid Random Walk Approach , 2018, Inf. Sci..

[13]  Hong Zhu,et al.  Mining social lending motivations for loan project recommendations , 2017, Expert Syst. Appl..

[14]  Chao Zhang,et al.  SERM: A Recurrent Model for Next Location Prediction in Semantic Trajectories , 2017, CIKM.

[15]  Tat-Seng Chua,et al.  Neural Collaborative Filtering , 2017, WWW.

[16]  Deborah Estrin,et al.  Collaborative Metric Learning , 2017, WWW.

[17]  Zi Huang,et al.  Joint Modeling of User Check-in Behaviors for Real-time Point-of-Interest Recommendation , 2016, ACM Trans. Inf. Syst..

[18]  Enhong Chen,et al.  Portfolio Selections in P2P Lending: A Multi-Objective Perspective , 2016, KDD.

[19]  Shou-De Lin,et al.  Fairness-Aware Loan Recommendation for Microfinance Services , 2014, SocialCom '14.

[20]  Jie Tang,et al.  Addressing cold start in recommender systems: a semi-supervised co-training algorithm , 2014, SIGIR.

[21]  Stathes Hadjiefthymiades,et al.  Facing the cold start problem in recommender systems , 2014, Expert Syst. Appl..

[22]  L. Rokach,et al.  Facebook single and cross domain data for recommendation systems , 2013, User Modeling and User-Adapted Interaction.

[23]  Mingxuan Sun,et al.  Learning multiple-question decision trees for cold-start recommendation , 2013, WSDM.

[24]  Fernando Ortega,et al.  A collaborative filtering approach to mitigate the new user cold start problem , 2012, Knowl. Based Syst..