FICO scores will be soon improved by predictive analytics. This new approach is more accurate and can extend to the entire debt management process.
Badly assessed financial risks were at the core of the financial crisis in the late 2000s. Banks and credit companies used faulty models which did not highlight the real threat of the mortgages granted. When the housing bubble burst, it led to the collapse too big to fail financial institutions and the recession of the entire economy for a few years. All these problems could have been avoided with proper risk hedging tools.
Imagine if a piece of software could tell you the repayment probability both for current, but also for future clients. Of course, that is what the FICO scoring model aims to do, but as we’ve seen, it has not been entirely successful. FICO stands for FI (Financial Accounting) and CO (Controlling). Models based on predictive analytics which use big data could have a better chance of foreseeing repayment chances. Yet, most companies have not adopted these tools yet.
Let’s go through a brief presentation of the applications for predictive analytics in the debt collection business.
Risk assessment: client scoring
As mentioned before, since the late 80s the FICO score has been the gold standard for evaluating loan application and creditworthiness. It even comes in a few different flavours, including auto FICO, and healthcare FICO.
Machine learning and specifically predictive analysis can take this process beyond a simple number and create a 360-degree portrait of the client, taking into consideration more than just the credit history and current debts. Now, it can include data from social media, spending patterns and more.
Such a tool would be great for foreign clients who have no previous FICO score but would be great business partners, like foreign investors. It would also offer a fair chance to recent college graduates or other young people.
By taking into consideration a broader array of input data, the accuracy of the prediction improves consistently, and it can also be refined to a very personal level. The new outcomes can go as far as setting an individual credit score limit to minimize potential damage.
Compute pay or default propensity
Using survival models, each client account can be evaluated for its likeliness to become a potential loss. If an account is in a continuous downward trend regarding its motivation or ability to pay it should be treated as a potential risk before it actually becomes one.
Predictive analysis models can determine the payment patterns which indicate that a client is struggling. For example, it could start with being just a few days late, or paying two instalments at once. Any variation from the usual payment schedule should be a red flag for the system.
A mechanism could be put in place which self-triggers when an unwanted pattern emerges. The system could reach out to the client and ask them if they need help if they are going through a difficult financial moment to offer solutions before debt starts build up.
Forecast cash flow
Any business wants to know what they can expect regarding future cash flows. Financial institutions are no different and predictive analysis can help them make more accurate projections when it comes to expected receivables.
Since in the risk assessment part the model was able to identify those clients who have the potential to be late or default completely, it follows that it is foreseeable to say which clients will pay.
Debt collector’s business models depend on the ability to predict the success of collection operations and evaluating outcomes at the end of each month even before the billing cycle begins.
This helps redirect the workforce from focusing on clients who were going to pay anyway towards those who are most likely not to meet their obligations.
Enhance the client relationship
Not only can predictive analysis tell you which clients are the highest risks for your business, but it can also identify when it’s best to get in touch with them for maximum results. For example, if they work in shifts, it’s best to call them whey they are not at work or resting, which could be outside regular business hours.
Showing your clients that you care about their habits and lifestyle improves your chances of them listening to your call agents and ultimately raising the collection rates. Of course, to train the system, you need the logs of past conversations.
Predict call value
As in any business, debt collectors aim to maximize their ROI by letting the call agents focus on the most promising accounts instead of just following a list approach. By using predictive analytics as described before, the model can allocate a likelihood score to each potential call and rank them in the company’s CRM.
The model usually works by computing the repayment probability, taking as a modifier the event “call”. That means, in fact, calculating the likelihood when the client is not called and the probability when it receives a call. This is a very simplistic approach, yet it highlights the way such models could make a difference for the bottom-line.
As in all models related to big data, the primary problem is related to data cleaning. Since it’s a matter of garbage in, garbage out, before making any prediction, the company dealing with this task needs first to build the pipeline to bring in the date, clean it and use it for training the neural network.
Another challenge might be related to various personal data protection regulations and privacy matters.
Ready, set, predict
To put it all together, it’s worth mentioning that predictive models can make a difference when it comes to revenue for debt collection agencies. It can boost conversion rates by targeting the right people, at the right time. Of course, an in-depth analysis could go as far as identifying the message which would influence the client the most.
Targeting the right clients also means more productivity for call centre agents and less wasted work hours. Having a mathematical model behind the decisions eliminates bias and makes the process fair.