Digital Ventures has recently introduced an alternative of financial inclusion from student loans via credit scoring. Alternative credit scoring isn’t limited to the education sector, it was researched and has also become solutions for the agricultural sector, a sector which faces a different financial inclusion problem. Also, it has incorporated Deep Tech and disrupted conventional credit scoring. What are these evaluation criteria and why does the agricultural sector need credit scoring solutions? Let’s find out.
Why do farmers need a personalized credit scoring system?
Although there are banks dedicated to farmers, yet many farmers may not have access to the funds from these banks. This is particularly true for small-scale farmers who don’t meet the criteria. The Initiative of Smallholder Finance who services small enterprises states that there are small-scale entrepreneurs worldwide who need funds of over 450 billion USD but there is only 40 billion USD of available loans.
Taking a closer look, CGAP, a global-scale group working to empower poor people, has surveyed farmers in Asia and Africa. Looking at statistics in Bangladesh, from 3,000 households, they found that there are 43.9% of farmers with wages lower than 1.25 USD per day. Moreover, 66.9% of farmers don’t have access to formal lending services. Therefore, they don’t have the opportunity to be assessed for loans in the system. They depend on informal lending with high interest rates. As a result, this group of people struggles to acquire a better living.
However, the survey discloses that half of the low-income group of less than 1.25 USD are owners and users of smartphones. This shows the readiness to use technology and an alternative to collect their data via new technologies which will go beyond the conventional financial sphere. This is the chance to offer alternative data so loans in the formal system are accessible.
Credit scoring as an alternative for the agricultural sector
Credit scoring for individual farmers emphasizes collecting alternative data. They are mostly information irrelevant to financial histories that use technologies to collect and analyze the data. Popular sources of alternative credit scoring in the agricultural sector are as follow:
- Demographic data. This is general data of an individual such as educational background and transaction records that once weren’t included as credit scores. This includes utility bill and mobile phone service payments. This refers to the person’s ability to manage their financial matters.
- Social information. The credit bureau can use the behavior of friends or family as data as well as other data acquired from the social network. This can also be considered to offer loan amounts that fit the trend and risk.
- Agronomic data. This is an option created for farmers to acquire data from their plantation. Farmers can share their production process data, from planting to cultivating, to the credit bureau.
- Environment data. Undeniably, environmental problems have caused worldwide anxiety. As the agricultural sector is part of the pollution, the farmers’ contribution to the environment is calculated as a credit score. Data is collected from various entities wherein farmers whose activities have less effect on the environment will have a higher chance of receiving investment support along with various other benefits.
- Economical data. Farmers are players in the market and the market has shared data that have tangible values. The credit bureau can utilize the data from farmers in the market to evaluate the risk and offer the proper lending amount. For instance, if farmers are planting crops which are in the market demand, the credit bureau can offer them higher credit scores and better benefits.
Core technologies that are often used to manage data for farmer’s lending offers
- Internet of Things. This technology will help collect intangible data and transform them into numbers. Examples are weather reports used to assess the air quality, the frequency of water or fertilizer usage that reflects a good manufacturing process, and other testing tools for product analysis. Moreover, the Internet of Things can help to promptly transfer data to the evaluator.
- Artificial Intelligence. Data collected from different sources will be massive and diverse, thus, precise calculations by human will require a long period of time. This is coupled with the number of farmers and their need for the loan to match the cultivating time in order to control manufacturing costs. As a result, AI is incorporated so that the data analysis is faster.
Example of startups in credit scoring for agriculture
Today, several startups are developing credit scoring for the agricultural sector. They are scattered in various regions around the world. Some outstanding startup solutions are as below:
- Musoni is a banking platform which focuses only on microfinance services. At present, they are servicing in 14 countries with one of their outstanding services as the loans for agriculture. They have incorporated AI in their credit scoring process.
- FarmDrive is a startup with a credit scoring solution for the agricultural sector in Kenya. They connect farmers and financial institutions on a platform and screen farmers with machine learning technologies.
- FarmGuide is a startup in credit scoring from India. They use data analytics from various data sources. Then, they assess the risk to offer the proper lending amount. Moreover, image processing from satellites is involved to increase precision.
Credit scoring in the agricultural sector is using Deep Tech as solutions for related parties. Farmers gain access to funds and investors are provided standardized tools to assess risks. We have more interesting stories regarding technology, follow us for more updates.