Abstract
Conventional loan avenues generally focus more on the formal sector than the unbanked sector. A peer to-peer (p2p) lending platform built on blockchain can help bridge the gap between potential lenders and borrowers in need of money in a secure and decentralized environment. The Ethereum blockchain allows for the creation of smart contracts to perform actions in the network by setting logic rules and conditions thereby removing the need for middlemen and can be inclusive of the unbanked sector. The p2p platform introduces swarm learning for credit scoring, which is a novel methodology that utilizes smart contracts to train decentralized machine learning models. Each training round happens on the local device with the user data, which then exchanges the training parameters and weights to the machine learning model maintained in the smart contract. This allows for preserving the privacy of the user data by ensuring the data never leaves the device but only the inference does. Upon analyzing the user’s behavior, a statistical credit score is assessed for validating the chances of the user to default his/her loan repayment. The performance of the proposed model that has been trained using the swarm learning technique is close to the model that had been trained in a centralized environment while overcoming the drawbacks of federated learning by incorporating blockchain and swarm methodology.
Similar content being viewed by others
Data availability
The data is private and can be shared when request is sent to corresponding author.
References
Banaeian Far S, RajabzadehAsaar M, Haghbin A (2023) A blockchain-based coin mixing protocol with certificateless signcryption. Peer Peer Netw Appl 16(2):1106–1124
Goel A, Neduncheliyan S (2023) An intelligent blockchain strategy for decentralised healthcare framework. Peer Peer Netw Appl 1–12
Ebiaredoh-Mienye SA, Esenogho E, Swart TG (2021) Artificial neural network technique for improving prediction of credit card default: A stacked sparse autoencoder approach. Int J Electr Comput Eng 11(5):4392
Esenogho E, Mienye ID, Swart TG, Aruleba K, Obaido G (2022) A neural network ensemble with feature engineering for improved credit card fraud detection. IEEE Access 10:16400–16407
Khatri P (2019) An overview of the peer-to-peer lending industry of India. Int J Bus Manag Invent 8(3):1–11
Klein G, Shtudiner Z, Zwilling M (2021) Why do peer-to-peer (P2P) lending platforms fail? The gap between P2P lenders’ preferences and the platforms’ intentions. Electron Commer Res. https://doi.org/10.1007/s10660-021-09489-6
Wu Y, Pan Y (2021) Application analysis of credit scoring of financial institutions based on machine learning model. Hindawi. https://doi.org/10.1155/2021/9222617
Dumitrescu E, Hué S, Hurlin C, Tokpavi S. (2022) Machine learning for credit scoring: Improving logistic regression with non-linear decision-tree effects. Eur J Oper Res 297(3):1178–1192
Konečný J, McMahan HB, Yu FX, Richtárik P, Suresh AT, Bacon D (2016) Federated learning: strategies for improving communication efficiency. arXiv preprint https://arxiv.org/abs/1610.05492
Efe Y (2021) A vertical federated learning method for multi-institutional credit scoring: MICS. arXiv preprint https://arxiv.org/abs/2111.09038
Arora N, Kaur PD (2021) Blockchain empowered framework for peer to peer lending. In: 2021 9th International Conference on Reliability, Infocom Technologies and Optimization (Trends and Future Directions) (ICRITO). IEEE, pp 1–5
Buterin V (2014) A next-generation smart contract and decentralized application platform. white paper 3(37):2–1
Tran KC (2019) Ultimate guide to ethereum lending: ETHLend, MakerDAO, BlockFi, SALT, Dharma & Compound. Retrieved from https://blokt.com/guides/ethereum-lending
Uriawan W, Hasan O, Badr Y, Brunie L (2021) Collateral-free trustworthiness-based personal lending on a decentralized application (DApp). In: SECRYPT. pp 839–844
Behera MR, Shetty S, Otter R (2021) Federated learning using peer-to-peer network for decentralized orchestration of model weights. TechRxiv. Preprint. https://doi.org/10.36227/techrxiv.14267468.v1
Blanco-Justicia A, Domingo-Ferrer J, Martínez S, Sánchez D, Flanagan A, Tan KE (2021) Achieving security and privacy in federated learning systems: Survey, research challenges and future directions. Eng Appl Artif Intell 106:104468
Bhagoji AN, Chakraborly S, Mittal P, Calo S (2019) Analyzing federated learning through an adversarial lens. Proc Int Conf Mach Learn 97:634–643. PMLR
Afaq A, Ahmed Z, Haider N, Imran M (2022) Blockchain-based collaborated federated learning for improved security, privacy and reliability. arXiv preprint https://arxiv.org/abs/2201.08551
Han J, Ma Y, Han Y (2022) Demystifying swarm learning: a new paradigm of blockchain-based decentralized federated learning. arXiv preprint https://arxiv.org/abs/2201.05286
Hewlett Packard Enterprise Labs - swarm learning: Turn your distributed data into competitive edge - https://h20195.www2.hpe.com/v2/GetDocument.aspx?docname=a50000344enw
Warnat-Herresthal S, Schultze H, Shastry KL et al (2021) Swarm Learning for decentralized and confidential clinical machine learning. Nature 594:265–270. https://doi.org/10.1038/s41586-021-03583-3
Yang F, Qiao Y, Qi Y et al (2022) BACS: blockchain and AutoML-based technology for efficient credit scoring classification. Ann Oper Res. https://doi.org/10.1007/s10479-022-04531-8
Zhao Y, Li M, Lai L, Suda N, Civin D, Chandra V (2018) Federated learning with non-iid data. arXiv preprint https://arxiv.org/abs/1806.00582
Universal Bank Dataset. https://www.kaggle.com/lowecoryr/universalbank
https://towardsdatascience.com/how-to-develop-a-credit-risk-model-and-scorecard-91335fc01f03
https://docs.alchemy.com/alchemy/tutorials/how-to-create-an-nft
Vojtek M, Koèenda E (2006) Credit scoring methods. Finance aUver - Czech J Econ Financ 56:152–167. https://www.researchgate.net/publication/285873211_Credit_scoring_methods
Zhang H, Zeng R, Chen L, Zhang S (2020) Research on personal credit scoring model based on multi-source data. In: Journal of physics: Conference series, vol 1437, no 1. IOP Publishing, p 012053
Author information
Authors and Affiliations
Contributions
Conceptualization: Antony Prince John and Jagadhiswaran Devaraj, methodology: Lathaselvi Gandhimaruthian, software -Javid Ali Liakath, validation- Antony Prince John. and Jagadhiswaran Devaraj, formal analysisb- Lathaselvi Gandhimaruthian, investigation- Lathaselvi Gandhimaruthian, resources- Lathaselvi Gandhimaruthian, data curation- Javid Ali Liakath, writing—original draft preparation, Javid Ali Liakath, writing- review and editing, Javid Ali Liakath, visualization- Javid Ali Liakath, supervision- Antony Prince John, project administration- Antony Prince John, funding acquisition- Jagadhiswaran Devaraj. All authors have read and agreed to the published version of the manuscript.
Corresponding author
Ethics declarations
Ethics approval
The authors herewith confirm that the research work is out of their own perception and assure its originality.
Consent to publish
The authors herewith confirm their full consent for publishing their research work.
Conflicts of interest
The authors herewith declare that they have no conflict of interest.
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
About this article
Cite this article
John, A.P., Devaraj, J., Gandhimaruthian, L. et al. Swarm learning based credit scoring for P2P lending in block chain. Peer-to-Peer Netw. Appl. 16, 2113–2130 (2023). https://doi.org/10.1007/s12083-023-01526-5
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s12083-023-01526-5