Replication Data for: Alternative Datasets for Credit Scoring of Thin File Consumers (doi:10.7910/DVN/TJ6RMQ)
(Innovative Data Approaches for Assessing Credit Risk in Limited Credit History Consumers)

View:

Part 1: Document Description
Part 2: Study Description
Part 5: Other Study-Related Materials
Entire Codebook

Replication Data for: Alternative Datasets for Credit Scoring of Thin File Consumers

doi:10.7910/DVN/TJ6RMQ

Harvard Dataverse

2024-07-26

1

Shukla, Deepa, 2024, "Replication Data for: Alternative Datasets for Credit Scoring of Thin File Consumers", https://doi.org/10.7910/DVN/TJ6RMQ, Harvard Dataverse, V1

Replication Data for: Alternative Datasets for Credit Scoring of Thin File Consumers

Non-Traditional Data Sources to Enhance Creditworthiness

Innovative Data Approaches for Assessing Credit Risk in Limited Credit History Consumers

doi:10.7910/DVN/TJ6RMQ

/kaggle/input/review-of-alternative-datasets-for-credit-scoring

Shukla, Deepa (Jaipur National University)

Shukla, Deepa

Gupta, Sunil

Sunil Gupta

2024-07-27

Python

Harvard Dataverse

Gupta, Sunil

Shukla, Deepa

2024-07-27

https://doi.org/10.7910/DVN/TJ6RMQ

Business and Management, Computer and Information Science, Machine Learning Algorithms, Alternative Dataset, Credit Score, Behavioural Finance, Thin File

Digital Credit Scoring

Credit scoring is essential in financial services, allowing institutions to assess consumers' creditworthiness. Traditional credit scoring models heavily rely on extensive transaction history, which often poses a significant challenge for thin-file consumers—individuals with limited credit history. This comprehensive review aims to explore and evaluate various alternative datasets that can be utilised to improve credit scoring for thin-file consumers. By moving beyond traditional transaction profiles, alternative datasets such as social media data, web browsing behaviour, digital footprints, and telecom data offer new dimensions to assess consumer credit risk. Additionally, the review compares the effectiveness of various machine learning algorithms, including support vector machines, neural networks, decision trees, random forests, and hybrid models, in leveraging these datasets for credit scoring. The findings indicate that integrating multiple alternative data sources with advanced machine learning algorithms can significantly improve the accuracy and reliability of credit risk assessments. The comparative analysis of machine learning algorithms used in credit scoring highlights the strengths and limitations of different approaches. Support vector machines (SVM), neural networks, decision trees, random forests, and hybrid models have all shown varying degrees of success in utilising alternative datasets for credit scoring. Hybrid models combine multiple machine learning techniques and are particularly effective in leveraging diverse data sources to provide a robust credit risk assessment. This review underscores the potential of alternative datasets in revolutionizing credit scoring for thin-file consumers. By incorporating new data dimensions and advanced machine learning algorithms, researchers can improve their ability to assess credit risk accurately. Future researchers may continue to refine these models and explore new alternative datasets to enhance credit scoring models using machine learning algorithms.

2024-07-26-2024-07-27

2024-02-18-2024-07-20

https://github.com/Deezpa/Datasets_Review

Dataset Overview - It contains information about various research papers related to alternative data sources for credit scoring. 1. Content of the Dataset: Authors and Year: Lists the authors of the papers and the year of publication. Title: Title of each research paper. Research Objectives: The goals or aims of the research described in each paper. Datasets Used: Types of datasets utilized in the research. Machine Learning Algorithms Employed: The algorithms used in the study. Key Findings: Major conclusions or results of the research. Citations: Links or references to the research papers. 2. Data Categories: The dataset includes a variety of alternative data categories used in credit scoring, such as social media data, web browsing behavior, digital footprints, telecom data, and hybrid data approaches. 3. Purpose of the Data: To categorize and assess the usage of different alternative datasets in credit scoring research for thin-file consumers. This data is used to analyze trends and prevalence of specific data sources in the context of credit scoring. 4. Visualization: The bar chart visualizes the distribution of these alternative data categories across the research papers. It helps to understand which data types are most frequently explored and their relevance in credit scoring models. 5. Analysis of Data: The dataset is organized to show the frequency of different categories of alternative data used in various studies. This analysis helps identify popular data sources and trends in research related to credit scoring. 6. Structure of Data: The data is structured into a table format with columns for serial number, authors and year, title, research objectives, datasets used, machine learning algorithms employed, key findings, and citations. 7. Potential Uses: This dataset can be used for literature reviews, identifying research gaps, and understanding the impact of various alternative datasets on credit scoring models. 8. Insights: The dataset provides insights into how different types of alternative data are used and evaluated in credit scoring research. It highlights the increasing interest in integrating diverse data sources to improve the accuracy and effectiveness of credit scoring models.

Research Papers

https://github.com/Deezpa/Datasets_Review

@misc{deepa_shukla_2024, title={Review of Alternative Datasets for Credit Scoring}, url={https://www.kaggle.com/dsv/9041453}, DOI={10.34740/KAGGLE/DSV/9041453}, publisher={Kaggle}, author={Deepa Shukla}, year={2024} }

10.34740/KAGGLE/DSV/9041453

@misc{deepa_shukla_2024, title={Review of Alternative Datasets for Credit Scoring}, url={https://www.kaggle.com/dsv/9041453}, DOI={10.34740/KAGGLE/DSV/9041453}, publisher={Kaggle}, author={Deepa Shukla}, year={2024} }

Smith, M., & Henderson, C. (2018). Beyond Thin Credit Files. Social Science Quarterly, 99, 24-42.

10.1111/SSQU.12389

Smith, M., & Henderson, C. (2018). Beyond Thin Credit Files. Social Science Quarterly, 99, 24-42.

Cheney, J. (2008). Alternative Data and its Use in Credit Scoring Thin- and No-File Consumers. Banking & Insurance.

10.2139/ssrn.1160283

Cheney, J. (2008). Alternative Data and its Use in Credit Scoring Thin- and No-File Consumers. Banking & Insurance.

Rozo, B., Crook, J., & Andreeva, G. (2021). The Role of Web Browsing in Credit Risk Prediction. Econometrics: Econometric & Statistical Methods - Special Topics eJournal.

10.1016/j.dss.2022.113879

Rozo, B., Crook, J., & Andreeva, G. (2021). The Role of Web Browsing in Credit Risk Prediction. Econometrics: Econometric & Statistical Methods - Special Topics eJournal.

Fu, G., Sun, M., & Xu, Q. (2020). An Alternative Credit Scoring System in China's Consumer Lending Market: A System Based on Digital Footprint Data. Decision-Making in Economics eJournal.

10.2139/ssrn.3638710

Fu, G., Sun, M., & Xu, Q. (2020). An Alternative Credit Scoring System in China's Consumer Lending Market: A System Based on Digital Footprint Data. Decision-Making in Economics eJournal.

Zhou, J., Wang, C., Ren, F., & Chen, G. (2021). Inferring multi-stage risk for online consumer credit services: An integrated scheme using data augmentation and model enhancement. Decis. Support Syst., 149, 113611.

10.1016/J.DSS.2021.113611

Zhou, J., Wang, C., Ren, F., & Chen, G. (2021). Inferring multi-stage risk for online consumer credit services: An integrated scheme using data augmentation and model enhancement. Decis. Support Syst., 149, 113611.

Djeundje, V., Crook, J., Calabrese, R., & Hamid, M. (2021). Enhancing credit scoring with alternative data. Expert Syst. Appl., 163, 113766.

10.1016/j.eswa.2020.113766

Djeundje, V., Crook, J., Calabrese, R., & Hamid, M. (2021). Enhancing credit scoring with alternative data. Expert Syst. Appl., 163, 113766.

Sustersic, M., Mramor, D., & Zupan, J. (2007). Consumer Credit Scoring Models with Limited Data. Banking & Financial Institutions eJournal.

10.2139/ssrn.967384

Sustersic, M., Mramor, D., & Zupan, J. (2007). Consumer Credit Scoring Models with Limited Data. Banking & Financial Institutions eJournal.

Huang, C., Chen, M., & Wang, C. (2007). Credit scoring with a data mining approach based on support vector machines. Expert Syst. Appl., 33, 847-856.

10.1016/j.eswa.2006.07.007

Huang, C., Chen, M., & Wang, C. (2007). Credit scoring with a data mining approach based on support vector machines. Expert Syst. Appl., 33, 847-856.

Jiang, J., Liao, L., Lu, X., Wang, Z., & Xiang, H. (2020). Deciphering Big Data in Consumer Credit Evaluation. International Political Economy: Investment & Finance eJournal.

10.2139/ssrn.3312163

Jiang, J., Liao, L., Lu, X., Wang, Z., & Xiang, H. (2020). Deciphering Big Data in Consumer Credit Evaluation. International Political Economy: Investment & Finance eJournal.

Dastile, X., Çelik, T., & Potsane, M. (2020). Statistical and machine learning models in credit scoring: A systematic literature survey. Appl. Soft Comput., 91, 106263.

10.1016/j.asoc.2020.106263

Dastile, X., Çelik, T., & Potsane, M. (2020). Statistical and machine learning models in credit scoring: A systematic literature survey. Appl. Soft Comput., 91, 106263.

Bequé, A., & Lessmann, S. (2017). Extreme learning machines for credit scoring: An empirical evaluation. Expert Syst. Appl., 86, 42-53.

10.1016/j.eswa.2017.05.050

Bequé, A., & Lessmann, S. (2017). Extreme learning machines for credit scoring: An empirical evaluation. Expert Syst. Appl., 86, 42-53.

Jiang, J., Liao, L., Lu, X., Wang, Z., & Xiang, H. (2021). Deciphering big data in consumer credit evaluation. Journal of Empirical Finance.

10.1016/J.JEMPFIN.2021.01.009

Jiang, J., Liao, L., Lu, X., Wang, Z., & Xiang, H. (2021). Deciphering big data in consumer credit evaluation. Journal of Empirical Finance.

He, H., Zhang, W., & Zhang, S. (2018). A novel ensemble method for credit scoring: Adaption of different imbalance ratios. Expert Syst. Appl., 98, 105-117.

10.1016/j.eswa.2018.01.012

He, H., Zhang, W., & Zhang, S. (2018). A novel ensemble method for credit scoring: Adaption of different imbalance ratios. Expert Syst. Appl., 98, 105-117.

Munkhdalai, L., Munkhdalai, T., Namsrai, O., Lee, J., & Ryu, K. (2019). An Empirical Comparison of Machine-Learning Methods on Bank Client Credit Assessments. Sustainability.

10.3390/SU11030699

Munkhdalai, L., Munkhdalai, T., Namsrai, O., Lee, J., & Ryu, K. (2019). An Empirical Comparison of Machine-Learning Methods on Bank Client Credit Assessments. Sustainability.

Aggarwal, N. (2018). Machine Learning, Big Data and the Regulation of Consumer Credit Markets: The Case of Algorithmic Credit Scoring. Discrimination.

10.2139/ssrn.3309244

Aggarwal, N. (2018). Machine Learning, Big Data and the Regulation of Consumer Credit Markets: The Case of Algorithmic Credit Scoring. Discrimination.

Zhu, B., Yang, W., Wang, H., & Yuan, Y. (2018). A hybrid deep learning model for consumer credit scoring. 2018 International Conference on Artificial Intelligence and Big Data (ICAIBD), 205-208.

10.1109/ICAIBD.2018.8396195

Zhu, B., Yang, W., Wang, H., & Yuan, Y. (2018). A hybrid deep learning model for consumer credit scoring. 2018 International Conference on Artificial Intelligence and Big Data (ICAIBD), 205-208.

McCanless, M. (2023). Banking on alternative credit scores: Auditing the calculative infrastructure of U.S. consumer lending. Environment and Planning A: Economy and Space, 55, 2128 - 2146.

10.1177/0308518X231174026

McCanless, M. (2023). Banking on alternative credit scores: Auditing the calculative infrastructure of U.S. consumer lending. Environment and Planning A: Economy and Space, 55, 2128 - 2146.

Wiginton, J. (1980). A Note on the Comparison of Logit and Discriminant Models of Consumer Credit Behavior. Journal of Financial and Quantitative Analysis, 15, 757 - 770.

10.2307/2330408

Wiginton, J. (1980). A Note on the Comparison of Logit and Discriminant Models of Consumer Credit Behavior. Journal of Financial and Quantitative Analysis, 15, 757 - 770.

Ala’raj, M., Abbod, M., & Majdalawieh, M. (2021). Modelling customers credit card behaviour using bidirectional LSTM neural networks. Journal of Big Data, 8, 1-27.

10.1186/s40537-021-00461-7

Ala’raj, M., Abbod, M., & Majdalawieh, M. (2021). Modelling customers credit card behaviour using bidirectional LSTM neural networks. Journal of Big Data, 8, 1-27.

Saberi, M., Mirtalaei, M., Hussain, F., Azadeh, A., Hussain, O., & Ashjari, B. (2013). A granular computing-based approach to credit scoring modeling. Neurocomputing, 122, 100-115.

10.1016/j.neucom.2013.05.020

Saberi, M., Mirtalaei, M., Hussain, F., Azadeh, A., Hussain, O., & Ashjari, B. (2013). A granular computing-based approach to credit scoring modeling. Neurocomputing, 122, 100-115.

Wei, Y., Yildirim, P., Bulte, C., & Dellarocas, C. (2014). Credit Scoring with Social Network Data. Economics of Networks eJournal.

10.2139/ssrn.2475265

Wei, Y., Yildirim, P., Bulte, C., & Dellarocas, C. (2014). Credit Scoring with Social Network Data. Economics of Networks eJournal.

Wang, C., Han, D., Liu, Q., & Luo, S. (2019). A Deep Learning Approach for Credit Scoring of Peer-to-Peer Lending Using Attention Mechanism LSTM. IEEE Access, 7, 2161-2168.

10.1109/ACCESS.2018.2887138

Wang, C., Han, D., Liu, Q., & Luo, S. (2019). A Deep Learning Approach for Credit Scoring of Peer-to-Peer Lending Using Attention Mechanism LSTM. IEEE Access, 7, 2161-2168.

West, D. (2000). Neural network credit scoring models. Comput. Oper. Res., 27, 1131-1152.

10.1016/S0305-0548(99)00149-5

West, D. (2000). Neural network credit scoring models. Comput. Oper. Res., 27, 1131-1152.

Brown, I., & Mues, C. (2012). An experimental comparison of classification algorithms for imbalanced credit scoring data sets. Expert Syst. Appl., 39, 3446-3453.

10.1016/j.eswa.2011.09.033

Brown, I., & Mues, C. (2012). An experimental comparison of classification algorithms for imbalanced credit scoring data sets. Expert Syst. Appl., 39, 3446-3453.

Lee, T., & Chen, I. (2005). A two-stage hybrid credit scoring model using artificial neural networks and multivariate adaptive regression splines. Expert Syst. Appl., 28, 743-752.

10.1016/j.eswa.2004.12.031

Lee, T., & Chen, I. (2005). A two-stage hybrid credit scoring model using artificial neural networks and multivariate adaptive regression splines. Expert Syst. Appl., 28, 743-752.

Mahjoub, R., & Afsar, A. (2019). A hybrid model for customer credit scoring in stock brokerages using data mining approach. Int. J. Bus. Inf. Syst., 31, 195-214.

Mahjoub, R., & Afsar, A. (2019). A hybrid model for customer credit scoring in stock brokerages using data mining approach. Int. J. Bus. Inf. Syst., 31, 195-214.

Arram, A., Ayob, M., Albadr, M., Sulaiman, A., & Albashish, D. (2023). Credit card score prediction using machine learning models: A new dataset. ArXiv, abs/2310.02956.

10.48550/arXiv.2310.02956

Arram, A., Ayob, M., Albadr, M., Sulaiman, A., & Albashish, D. (2023). Credit card score prediction using machine learning models: A new dataset. ArXiv, abs/2310.02956.

Junior, L., Nardini, F., Renso, C., Trani, R., & Macêdo, J. (2020). A novel approach to define the local region of dynamic selection techniques in imbalanced credit scoring problems. Expert Syst. Appl., 152, 113351.

10.1016/j.eswa.2020.113351

Junior, L., Nardini, F., Renso, C., Trani, R., & Macêdo, J. (2020). A novel approach to define the local region of dynamic selection techniques in imbalanced credit scoring problems. Expert Syst. Appl., 152, 113351.

Label:

Systematic Alternative Dataset Review.xlsx

Text:

The findings indicate that social media data provides valuable insights into consumer behaviour and financial reliability, while web browsing patterns and digital footprints offer additional dimensions to assess creditworthiness. Telecom data, including call records and mobile payment history, has proven to be a reliable indicator of financial behaviour. Hybrid approaches, which combine these various data sources, provide a more comprehensive assessment of credit risk, addressing the limitations of relying on a single type of alternative dataset.

application/vnd.openxmlformats-officedocument.spreadsheetml.sheet