A loan passes through various stages or events from the moment it is given till the time it is repaid. Collection strategy of a loan for any financial institution is as important as its lending strategy and delays in repayments not only impacts the financer’s books, it also impacts the borrower as it is also reflected in their credit history
SHG / JLG Collections
A SHG (self help group) is a community based group with 5-20 members. Micro Finance Institutions typically offer group loans and individual loans that have standardized repayment structure. The repayment cycle could be weekly, monthly or fortnightly depending on the scheme and institutions. In a typical collection process either an MFI agent visits the borrower to collect the repayment in cash or the borrower walks to a physical branch to make the payments.
How Data Science Helps
Predictive analytics plays a key role in coming up with behavioral patterns to determine whether a customer is likely to default. A right collection model can be a driving factor behind a product’s collection efficiency. Simple classification model or a scorecard can be trained on the past data to help the collection team to identify the chunk of customers in the current portfolio who display a similar pattern to the ones who defaulted in the same product in the past. It can help the collection team to put more focus on these customers and align their efforts accordingly. This model will run at the start of every collection cycle and its frequency will be similar to the repayment frequency of the customer(weekly, monthly or fortnightly).
The two major category of variables that can be used to identify this pattern are:
- Credit bureau history data.
- Customer’s internal performance data.
Credit Bureau Data
Looking at customer’s credit data tells us the customer’s current market activity and his/her past credit history. Major variables that can help us identify our customer’s potential credit default include:
- Loan taking behaviour:
If a customer is taking a lot of loans simultaneously from other lenders in the market then it is highly likely that they will become overleveraged and a potential defaulter. Also their association with multiple lenders shows that they are not loyal and might ditch you in future if competitors provide lower interest rates.
- Current Market repayment:
If a customer has recently defaulted on their loan in the market, it gives you a clear red flag that he/she might default with you soon as the customer might be facing cash crunch and replaying multiple loans at once is difficult for them. Prioritizing those customers and reaching them first can be the defining factor for your loan.
- Market repayment history:
Even the customers who currently do not have any default in the market can be segregated into two categories. First, customers who today might be at 0 DPD today but in the past they had intermediate defaults for the past loans, they went into DPD but later on repaid the entire amount and cleared all debts. Second, customers who have completely clean bureau history and never went into DPD. Second category customers would be your good customers and you would want them to be segregated from the first category in your collection strategy.
Customer’s Internal Performance Data
You also have repayment history of the customer with you. It can also be broken down into three types of variables
- Individual performance:
Number of months the customer has been on your books and his/her performance over that time period can also be a good indicator. Customers missing their due date and delaying payments but clearing it before month end in recent months can be potential defaulters. Also customers who went into DPD but rolled back in later months can also be default again.
- Group performance:
Since it is a joint liability product, behaviour of each member of the group affects the behaviour of other members. Default of one member of a group can lead to other members also not paying. A group of all credit inexperienced customers can have higher chances of defaulting than the experienced group.
- Agent/Branch change::
Since the entire collection process is physical, change in the collection agent of a customer or branch can also lead to defaults as these on-ground personnel have a good one to one relationship with customers. Change in field teams hampers the relationship between customers and the MFIs.
Machine learning algorithms are fed all of this data from which they learn and create predictions. These algorithms can extract linear and nonlinear patterns in the data which will be difficult for a human(Collection team) to see. A multivariate machine learning model with hundreds of features can easily outperform a univariate rule based collection strategy. Use of applied machine learning can not only give you better results but also a clear interpretability and deeper insights for business to make better decisions. With the help of predictive analytics in collections MFIs can maintain good clean books and can aim to achieve higher profitability.