International Journal of Computer Applications |
Foundation of Computer Science (FCS), NY, USA |
Volume 180 - Number 35 |
Year of Publication: 2018 |
Authors: Bhaumik Choksi, Alisha Sawant, Sai Subhasree Pakina |
10.5120/ijca2018916888 |
Bhaumik Choksi, Alisha Sawant, Sai Subhasree Pakina . Blockchain-based Smart P2P Lending using Neural Networks. International Journal of Computer Applications. 180, 35 ( Apr 2018), 51-55. DOI=10.5120/ijca2018916888
Over the past decade, there has been an exponential growth in the number and scale of online lending and crowdfunding platforms. However, these platforms lack a reliable and transparent metric to predict the credit-worthiness of an applicant. They also have a single point of failure and are vulnerable to certain security issues. This paper proposes a Blockchain-based decentralized lending platform that uses deep learning to predict the risk associated with an applicant. The paper also discusses how such a system can be implemented and deployed. The experimental results show how ensemble training can help lower the bias of individual neural networks and provide better predictions for this use case.