Model of Optimizing Correspondence Risk-Return Marketing for Short-Term Lending
Round 1
Reviewer 1 Report
Thank you for this submission and for your effort. The paper investigates an interesting topic and it provides several stimulus for reflections. Despite this, I would suggest to better clarify the main focus of your research because it is unclear in which ways "The results can be applied to customer rela-24 tionship management (CRM) of online non-banking lenders".
More than this, I also would suggest to better define the framework under which the research design is defined with reference to the technology and digital influences. With reference to the point, please consider the following references among the others:
- Caputo, F., Papa, A., Cillo, V., & Del Giudice, M. (2019). Technology readiness for education 4.0: barriers and opportunities in the digital world. In Opening Up Education for Inclusivity Across Digital Economies and Societies (pp. 277-296). IGI Global.
- Hacioglu, U. (Ed.). (2019). Blockchain economics and financial market innovation: Financial innovations in the digital age. Springer Nature.
- Loginov, M. P., & Usova, N. V. (2019, December). Innovation in the national digital financial services market. In International Scientific and Practical Conference on Digital Economy (ISCDE 2019) (pp. 776-781). Atlantis Press.
- Opare, E. A., & Kim, K. (2020). A compendium of practices for central bank digital currencies for multinational financial infrastructures. IEEE Access, 8, 110810-110847.
- Yang, J., Zhao, Y., Han, C., Liu, Y., & Yang, M. (2021). Big data, big challenges: risk management of financial market in the digital economy. Journal of Enterprise Information Management. Vol. 35 No. 4/5, pp. 1288-1304
Author Response
Firstly, we would like to thank the reviewers for the useful comments that improved the new version of our paper. Please find our answers for each point reported below.
Response to Reviewer 1 Comments
Point 1: I would suggest to better clarify the main focus of your research because it is unclear in which ways "The results can be applied to customer relationship management (CRM) of online non-banking lenders".
Response 1: The results can be applied to customer relationship management (CRM) of online non-banking lenders by following ways.
- The proposed optimization model involves applying results to marketing budget allocation. Namely, the scheme of it is presented at Figure 7. According to this scheme marketing budget is structured according CLV levels. According to this marketing funding is directed to those type customers who correspond higher level of CLV. Appling marketing in wider (financial) form facilitates the strengthening of CRM
- Table 2. And Figure 4 involve optimal marketing strategies for customers (borrowers) and estimates potential response in income. Taking account, that at the lending frameworks customers are borrowers. They receive services in form of loan granting and the proposed marketing strategies exactly focuses at better off loan amount (primarily) proposition. This is approach of CRM.
- Proposed model involves automatization of identification type of the customer and it supposed to launch of the corresponding strategy of CRM
Point 2: I also would suggest to better define the framework under which the research design is defined with reference to the technology and digital influences.
We have add the following references:
Caputo, Francesco, Armando Papa, Valentina Cillo, and Manlio Del Giudice. 2019. Technology readiness for education 4.0: barriers and opportunities in the digital world. In Opening Up Education for Inclusivity Across Digital Economies and Societies (pp. 277-296). IGI Global.
Chappell, G., Harreis, H., Havas, A., Nuzzo, A., Pepanides, T., & Rowshankish, K. 2018. The lending revolution: How digital credit is changing banks from the inside. McKinsey & Company) August, at https://www. mckinsey. com/business-functions/risk/our-insights/the-lending-revolution-how-digitalcredit-is-changing-banks-from-the-inside.
Fogoroș T. E., Maftei M., Olaru S. M., Bițan G.E. 2020. From Traditional to Digital: A Study on Business Models in The Context of Digitalization. Proceedings of the 3rd International Conference on Economics and Social Sciences, ISSN 2704-6524, pp. 749-757. https://doi.org/10.2478/9788395815072-074
Guryanova, L., Yatsenko, R., Dubrovina, N., Babenko, V. 2020. Machine Learning Methods and Models, Predictive Analytics and Applications. Machine Learning Methods and Models, Predictive Analytics and Applications 2020: Proceedings of the Workshop on the XII International Scientific Practical Conference Modern problems of social and economic systems modelling (MPSESM-W 2020), Kharkiv, Ukraine, June 25, 2020, Vol-2649, 1-5. http://ceur-ws.org/Vol-2649/
Hacioglu, Umit (Ed.). 2019. Blockchain economics and financial market innovation: Financial innovations in the digital age. Springer Nature.
Kaminskyi, Andrii and Nehrey, Maryna. 2021. Clustering approach to analysis of the credit risk and profitability for nonbank lenders. In CEUR Workshop Proceedings, Machine Learning Methods and Models, Predictive Analytics and Applications - 13th Workshop on the International Scientific Practical Conference Modern Problems of Social and Economic Systems Modelling, MPSESM-W 2021, Volume 2927, 125-136.
Opare, Edwin Ayisi, and Kwangjo Kim. 2020. A compendium of practices for central bank digital currencies for multinational financial infrastructures. IEEE Access, 8, 110810-110847.
Vasileva Valya. 2019. Development of Consumer Lending by Non-Bank Credit Companies in Bulgaria. Economic Archive, (1), pp. 65-76.
Yang, Jinlei, Yuanjun Zhao, Chunjia Han, Yanghui Liu, and Mu Yang. 2021. Big data, big challenges: risk management of financial market in the digital economy. Journal of Enterprise Information Management. Vol. 35 No. 4/5, pp. 1288-1304.
Reviewer 2 Report
Journal of Risk and Financial Management
Manuscript jrfm-1949164
Model of Optimizing Correspondence Risk-Return-Marketing for Short-term Lending
Reviewer Comments
Thank you for the opportunity to review your manuscript. The paper presents a model for optimising correspondence risk-return-marketing for short-term lending by non-banks. While the topic is interesting, I have some significant concerns about the paper in its current form, and offer my comments in the spirit of helping the authors to the paper further. My are outlined in the following sections.
Although the topic may be of importance in the finance area, specifically lending by the non-banking sector, the paper does not adequately justify this positioning in the academic literature.
The paper diverges from the usual format and approach of an academic study in a number of ways. Fundamentally, the conceptualisation is not at all clear. There is very little discussion outlining the conceptual rationale for the paper, and a general absence of supporting academic references. For example, the links between marketing, IT, short-term lending need to be made much clearer, particularly in the context of the study and the model being developed. Since this is a theoretical paper, there needs to be much closer connections with existing theoretical perspectives and current research.
These comments also apply to the methodology, where, for example, there is no explanation as to why logistic regression is the preferred analytical approach. The techniques used are largely not referenced, neither are they explained. While borrowers are segmented into four segments, there is very little indication of how the segments might differ in terms of demographics, which is an important aspect.
The results section combines some elements of a literature review, and inconclusive statements about how the results lead to the development of the conceptual model. The structure and presentation of the results section could be improved.
The contributions of the study are not well articulated, nor are the implications for future research or for practice. There is considerable scope to develop these, particularly with reference to current knowledge and the relevant research literature.
Finally, the paper needs to be proofread for correction of grammar and syntax.
I wish you well for the further development of this paper.
Comments for author File: Comments.pdf
Author Response
Firstly, we would like to thank the reviewers for the useful comments that improved the new version of our paper. Please find our answers for each point reported below.
Response to Reviewer 2 Comments
Point 1: the paper does not adequately justify this positioning in the academic literature.
Added lines 131-140: Our research is concerned with the trend of the fintech development. The development of fintech is discussed widely in the academic literature (Caputo et al. 2019, Hacioglu 2019, Guryanova et al. 2020, Opare & Kim 2020, Yang et al. 2021). More narrowly, there are academic publications for the digitization of lending (Vsileva et al. 2022, Chappell et al. 2018). Moreover, this trend implied a digital approach to the transformation of business models, involving the implementation of business processes digitally (FogoroÈ™ et al. 2020). At this context, our paper absolutely corresponds to form digital model (Figure 8.) for online non-banking lending, which immanent part of digitalization in finance
Point 2: the conceptualisation is not at all clear
The conceptualization in the article reveals itself in linking up conception of CLV and conception risk-return correspondence at the frameworks of online non-bank lending.
Point 3. there is no explanation as to why logistic regression is the preferred analytical approach
We have analyzed different approaches of scoring construction methodologies (Random Forest, Credit score boost and other). The basic benefit of logistic regression is the transparency of scorings characteristic. It possible to clear understand what characteristics are used and what are their significances. There demographic characteristic “Age”
Added lines 258-261: It is necessary to note, that we tested different approaches to scoring construction (such approaches are presented in (Kaminskyi & Nehrey 2021). Namely, random Forest (RF), Extreme Gradient Boosting (XGBoost) and some other. But we selected logistic regression because it easier to implement, interpret, and very efficient to training.
Point 4: Future research
Future research is actual at the form of upgrade the scoring models. Online lending is actively developing in the area of alternative data. And new characteristics permanently arise. So, data mining with focus to alternative data one of the basic direction of future researches at this context.
Added lines 425-430: The unconditional component of further research should be the development of customer relationship management in the conditions of financial services digitalization. The issues discussed in our study identify more financial aspects of marketing budget allocation. At the same time, the forms of interaction with the customer in the conditions of digitalization are changing and these changes, in our view, are an interesting object for study.