KiRTi: A Blockchain-based Credit Recommender System for Financial Institutions

Aim

       The main aim of this project to remove the third party agent between the perspective lenders and perspective borrowers.

Abstract

       In this paper, we propose KiRTi, a deep-learning based credit-recommender scheme for public blockchain to facilitate smart lending operations between prospective borrowers (PB) and prospective lenders (PL) to eliminate the need of third party credit-rating agencies (CRAs) for credit-score (CS) generation. Thus loan grants to PB from PL is secured, authorized, and automated so as to expedite the disbursement process. KiRTi stores PB historical transactions, current assets, and liabilities as time-series sequenced data in a public blockchain. The sequenced data is fetched from blockchain by a long-short term memory (LSTM) model that generates CS for loan recommendations based on proposed lending algorithms for PB and PL. To ensure real-time updation of CS, edge-weights are updated based on boolean indicators from PB and PL, which indicates the successful repayments and loan-defaults. The process is iterated to improve the accuracy of edge-weights and generated CS to ensures the correct credibility of PB for future lending. Smart contracts (SC) are proposed for automatic setup of loan repayments between PB and PL. To model the LSTM recommender scheme, a German credit dataset from UCI repository is considered with 1000 credit-histories of PB, with 700 successful repayments and 300 defaults. KiRTi achieves an accuracy of 97.5% in comparison to conventional approaches with an Fmeasure of 0.98304. The security evaluation of KiRTi shows that it has computation cost of 20.96 ms and communication cost of 121 bytes compared to other state-of-the-art approaches.

Existing System

        In existing system, d the overall loan disbursement cycle is slow and tedious in nature. This is due to complex co-relations that exist among diverse set of parameters like- previous credit histories, defaults, and length of repayment cycles. Also, loan grants are subjective to PL profit margins, with different levels of uncertainty, depending on PL prospective. For some PL, loss (defaults) is more critical than gains (repayments), and vice-versa. Thus, the recommender models might assign different scores to same PB, which results in the proportionality of the assessed risk by PL. This approach is flawed as even a missed repayment can affect CS resulting in the calculation of high risk. Also, CS generated through recommender models does not take into account new PB having a good reputation and high assets as their credit histories are absent.

Problem Definition

• Overall loan disbursement cycle is slow and tedious in nature.
• This approach is flawed as even a missed repayment can affect CS resulting in the calculation of high risk.

Proposed System

      In proposed System, loan disbursement cycle is high. Perspective lenders and perspective borrowers have direct communication. So, that they can know their details clearly. In this approach we implement a sentiment analysis to read a borrowers reviews. For using sentiment analysis we can find out the total percentage of positive reviews negative reviews. Based on the reviews and positive negative reviews percentage PL will decide to lend the loan to that particular user or not. So that maximum users can get a loan without any difficulties. We will store the perspective lender lending details and perspective borrower’s payment history in block-chain.

Advantage

• Every perspective borrower has a possibility to get a loan from lender.
• Perspective lenders and perspective borrowers had to know each other’s identity.