Farmer Loan Application Filter — A Data Modeling Tool for Banks and MFIs

FarmGuide
FarmGuide India
Published in
3 min readMar 18, 2019

Every five years, when the Indian subcontinent goes through the election fanfare, politicians travel through dusty rural roads holding rallies and meetings with the farmers promising them several welfare schemes when they come to power.

And each year, a milieu of schemes and subsidised loans are announced by the Finance Minister of India in his budget speech.

The Indian banking system plays a major role in making these schemes and benefits available to the farmers. Some of these schemes are crop loans, Kisan Credit Cards, agriculture insurance schemes, livestock loans, operation loans, infrastructure investment loans etc.

But how do banks decide whom to give loans?

From where do they get their loan applications?

It may seem that there are very obvious answers to these questions but not really.

One of the biggest challenges that Indian banks face is how to establish the creditworthiness of a loan-seeking individual as there is no central data bank to tap into (though RBI plans to work on a digital public credit registry). There is no standard way to determine the credit rating of each farmer.

At present, the banks source their loan applications through direct selling agents (DSAs), banking correspondents (BCs) or primary agriculture co-operatives (PACS).

Farmer Loan Application Filter — A Data Modelling Tool

These individuals and small institutions work on the ground and have built relationships with farmers in their areas over the years. Sometimes, the commercial banks partner with regional rural banks (RRBs) or microfinance institutions (MFIs) to route loan applications since they don’t have a bank branch in every village.

The whole process of reaching out to the beneficiary is quite people-dependent and thus, comes with its inherent bias and lack of objectivity.

Can this issue be resolved? Is Farm Loan App’s filter the way out?

FarmGuide proposes a farmer loan application (farm loan app) with a filter mechanism to determine the rightful beneficiaries of the loans. The app is based on the data that is being captured in the loan application form.

The FarmGuide loan application filter can be customised as per the bank’s needs and criteria.

The app can reduce the manual effort put in by banks in accepting or rejecting loans applications making the whole process efficient, cost-effective and objective.

It would ease the banks in meeting their targets for the priority sector lending (PSL) and reduce the agriculture-related bad debts of the banks as well.

Another Way Out of Loan Waivers — Data Modelling in Agriculture

With the rising protests by the farmers all over India, several state governments have announced loan waiver schemes to ease the financial burden on the farmers.

However, such populist measures are often criticised by experts for increasing inefficiency in the banking system and raise the fiscal deficits of the states to unsustainable levels. Is there another way out?

Data modelling and technical expertise of agritech startups such as FarmGuide have a huge role to play.

Apt use of technology can not only reduce the manual work and bias in processing loan applications but also bring to the forefront a pool of farmers with poor credit rating.

These farmers may have a poor rating for several reasons like the kind of crop they are growing, unavailability of cash flow, lack of irrigation on farmland etc.

But these farmers also need capital to better their situation and extra guidance to improve their farming practices to become sustainable.

Highlighting such pool of farmers and studying their situation can enable the government to design better policies and target them at a much micro level, thus benefiting them deeply.

--

--