Get more content like this in your Inbox monthly!
Our newsletter consists of curated articles from our top authors.
By Sindhuja Balaji
One of the toughest challenges in agriculture is enabling credit options to farmers. This aspect of agriculture can be incrementally improved by using AI-based credit modelling. Find out how this helps farmers, banks and insurance companies.
It is hard to look at a farmer as a businessman but essentially, that's what he is. He runs a business that requires direction, strategy and also capital. Financing agri ventures has been a constant - government schemes and various banks are involved in extending a line of credit for farmers across the country. In addition, there are several grants and subsidies available for farmers too.
Back in the 80s, it was the NABARD that initiated the trend of extending credit facilities and financial options for farmers, in an attempt to boost the rural economy. The Kisan Credit Card is one of the most notable initiatives by NABARD where the quantum of the loan provided depends on a variety of factors like cost of cultivation, yield percentages, maintenance charges and more. Recently, the central government sanctioned a pan-India Central Sector Scheme - Agriculture Infrastructure Fund, which will provide a medium to long-term debt financing facility for investment in viable projects for post-harvest management infrastructure and community farming assets through interest subvention and financial support.
However, there are many challenges in agri-financing. With fears of Non Performing Assets (NPAs) mainly due to loan defaults, banks are skeptical to lend to farmers. This skepticism isn't entirely unwarrranted. The lack of reliability among farmers is one of the main reasons - a primary concern for any agri lender is "Will the loaner pay back the money with interest on time? Will the loaner's farming activities be sustainable to generate profits in the future as well so I can extend another line of credit with confidence?"
The answers to the above questions usually fails to evoke confidence in a lender. And these are just a handful of concerns and challenges in agri financing. But a gap exists in financing the sector. Can technology provide the answer?
In countries like China, credit scores are linked to one's social media presence and activities. It obviously appears as an exaggerated connection to gauge credit-worthiness, but the more pertinent point to notice is the use of analytics to harness even the most minute and specific details of an individual to tie it back to his financial history. Closer home, the use of AI to assess financial credit worthiness isn't new in the BFSI sector for typically urban clients.
This is an emerging trend in agriculture in India. Several entrepreneurs are exploring how technologies like AI can be used to assess farmers better to extend the most appropriate line of credit. Bangalore-based CropIn is doing exactly that. CropIn’s AI and Machine Learning based platform, SmartRisk, detects cropping patterns and predict the future of the crop. Also, analyze sowing and harvesting pattern using crop stage identification. CropIn’s smartrisk helps to know the agri worthiness of the farmer before lending and post lending monitoring of farmers. Financial companies can look closely at the data points and determine whether the farmer is good or how he does his business or manages his risks.
Water stress and crop health are useful indicators to understand crop success and provides insights for risk analysis of a particular region. SmartRisk helps the business to acquire these data-points as well. Bank employees geo-tag & audit required farm plots as CropIn shares historic reports on crop, health, yield and water stress to clients and further monitor the crop.
Using Cadastral Maps, banks can perform health analysis of plots and make them available for banks to identify top plots for a 50-km radius of a branch. Remote sensing-based image processing for the entire project area is possible that will showcase crops grown, health and estimated yield. For post-code level analysis, remote sensing-based image processing is used on the entire project area showcasing crops grown, health and estimated yield at regular intervals and alarms
These metrics help optimizing loan disbursal process and reduced cost of operations. If less number of people are required for field auditing; it leads to effective NPA management and timely loan collection. Financial institutions like Banks, NBFCs, MFIs can improve the loan qualification process, optimize the loan disbursement process, preemptively assess NPA, perform crop growth analysis to monitor risk in real-time and expand lending portfolios to new regions with higher confidence
This kind of customised, and specific data driven solutions helps banks, NBFCs and microfinance institutions understand agricultural credit risk by region, optimise loan disbursement, manage loan delinquency, manage NPAs and loan collection, use Ag-alterate data for loan underwriting and assess water stress & droughts more.
Several companies like CropIn are making headway in this space, with the aim to ease of agri financing using technology like AI.
About the author
Senior Content WriterSindhuja Balaji is a Senior Content Writer with India AI. She has 10 years of experience as a journalist in print, digital & television media, covering technology, business, culture and city affairs. Prior to joining India AI, she led Content, Social Media & PR Outreach initiatives for the NASSCOM Center of Excellence for IoT & AI. She particularly enjoys exploring the potential of advanced technologies and their impact on the economy, business & policy development
Providing a suite of digital services for enhanced farm productivity
Unused TV spectrum, helium balloon drones for agriculture data transmission