[ad_1]
The provision of credit is a key driver of economic growth. However, despite robust regulation and strong fundamentals, the Indian economy suffers from an acute credit gap. A good proxy for this gap is the credit-to-gross domestic product (GDP) ratio which is 50% for India while it is 177% for China. The impact of this gap is acute for micro, small and medium enterprises (MSME) and nano-SME borrowers as the current banking infrastructure does not reach them adequately, citing high operational costs and difficulty in underwriting. This is where the most impressive opportunity lies for artificial intelligence (AI) and machine learning (ML) in credit provision and decision making.
According to ICRA estimates, in financial year (FY) 2024, we saw a 16% growth in credit, with demand led by small value unsecured loans. While this growth rate is healthy, it led to concerns about bad lending practices such as over-indebtedness, shoddy underwriting, which led the regulator (Reserve Bank of India) to tighten lending norms. This tightening will likely reduce loan growth rates to between 11-12% in FY25 and underlines the importance of risk management in the context of small loans, i.e. at extremely low costs.
To understand and measure risk, i.e. the credit-worthiness of a borrower, we need to assess two things: ability to repay and willingness to repay.
AI models provide a versatile toolkit for different stages of the customer lifecycle within financial institutions. These applications broadly fall into several categories:
· Loan decisioning: Using AI/ML techniques in loan decisioning involves using supervised or unsupervised learning algorithms. For example, leveraging ML to analyze credit bureau reports can provide information about incorrectly reported loans, specific repayment structures like bullet repayments, default trends across different sectors and occupations, as well as income distribution within districts and states. Such analysis helps in ascertaining a user’s ability to repay.
· Fraud and bad guy detection: By examining user behaviour during loan application, including interactions with the application, copy-paste tendencies, data correction frequency and changes in connectivity, potential red flags can be identified. On the KYC front, assessing the integrity of user data across various sources helps uncover fraudulent borrowers and assess their willingness to repay.
Early warning signals: After loan disbursement, financial institutions should closely monitor repayment patterns. Bureau data scrutiny and use of ML techniques enable identification of risks, facilitating proactive measures for successful collection.
Operational efficiency: Intelligent systems can streamline operational workflows by learning and automating tasks typically performed by operations teams. The implementation of ML techniques significantly reduces turnaround time (TAT) and reduces error rates resulting from manual interventions.
Improve collection efficiency: In a lending institution, effective collection is paramount. AI models can identify repayment patterns, preferred modes of repayment, and user interactions with communications, enabling proactive issue resolution in collections.
Selecting the appropriate AI/ML algorithm depends on the nature of the business and the quality of the data collected. For institutions dealing with unstructured data, unsupervised learning provides valuable insights. Clustering or association algorithms are viable options for building models in this context. In contrast, supervised learning is more suitable for established financial institutions, which leverages collective intelligence from user data. Regression and classification are the primary algorithm types used in such models.
Two credit sub-sectors are likely to see significant AI-driven growth in the coming years. First, women borrowers who are outpacing men in credit demand, especially for small business loans. Women borrowers typically have less traditional underwriting data available at the time of application, but have ample alternative data in the form of savings + spend, group savings, etc. With custom AI/ML tools, not only can prevalent underwriting gender biases be exposed and eliminated, but they can also lead to better alternative data-based underwriting.
The second sub-sector comprises rural and semi-urban borrowers, where risk assessment often needs to incorporate data beyond the individual borrower such as household income dynamics, seasonality of flows, etc., which is ideal for learning from and applying AI-based models.
Overall, the power of AI/ML tools in transforming how and to whom loans are extended is particularly relevant and important for India’s growth story.
This article is written by Mohit Gupta, Co-Founder, IndiaP2P.
[ad_2]
