Debt Collection 101: Where to Begin

By on August 7th, 2017 in Debt Collection, Industry Insights

The heydays of 2015 are over, and investors are looking at business operations and growth before opening up their checkbook for the next round of funding. They are pushing for better margins and cash flow. In the past, you focused on top line growth and knew that there’s another round coming. You can’t do that anymore.

You talk to your CFO and it’s obvious that chargebacks and late payments are a bigger line item than you’d want them to be. You don’t need to be a lender for that. You could have chargebacks from people who regret their purchase (but somehow forget to return the item). Some are on post-paid plans but their cards expire. Some use your product, incur penalties, and never pay them. Simply writing off the debt is not an option.  

Why not do collections in-house? You may decide to try an in-house collections department. Your customer service people aren’t too excited about the new tasks, so they make a few calls and send an email, but no one responds. Those that do pick up the phone are sometimes aggressive and your agents can’t handle them. You realize that collections and customer service are not complimentary job functions and need to be separated. You try to hire a collections professional and are shocked by the cultural mismatch. This isn’t going to work. You’re not going to invest a lot upfront in the hopes of recovering 2% of what’s owed to you.

You decide to work with an outside collection agency. These folks don’t speak your language. They don’t even know what an API is. They outsource their collection activity to Guatemala because that’s how they can make 6 calls per day per customer, cheap. They become defensive when you mention your customers don’t like being called and prefer digital channels like email and text. You want them to care about your brand and customers but their agents make commissions on every dollar collected and if they can’t make their numbers, they get booted. You see where this is going. It’s not going to work.

Here’s the thing: debt collection is part of the business lifecycle, and when implemented correctly, can help you get paid while maintaining your brand and customer engagement. It’s possible to collect and keep your customers satisfied. Collections can use digital channels and a self-service system that gives people the payment flexibility they need, improves your chances of recovery, and reduces the time it takes them to commit to a payment. We’ve seen collection rates as high as 27% for eCommerce companies, because many of your customers who fall behind want to pay. They just needed to be treated correctly – in the same targeted, data driven, UX-first approach that you use for the rest of your product. That’s what we spend a lot of time building.

The Debt Collection Rule is Coming in 2017 – Here’s What to Expect

By on August 7th, 2017 in Compliance, Debt Collection, Industry Insights

The CFPB just announced its 2017 rulemaking agenda. In its message, the CFPB states that it has “decided to issue a proposed rule later in 2017 concerning debt collectors’ communications practices and consumer disclosures.” InsideARM puts the date at September of this year. This is great news for consumers, creditors – and even collectors.

The rule is expected to focus on collector communication practices. Judging by the CFPB’s 2016 outline, that includes clarifications on the use of social media and emails for collections, as well as a cap on weekly contact attempts per account.

Emails and social media are consumers’ preferred channels for communication, even with debt collectors. We expect this rule to open the flood gates on responsible, consumer-centric, and scalable collection practices that will benefit everyone involved. We’ve written extensively on how machine learning based, digital first systems collect better than traditional solutions, and we expect these clarifications to greatly aid in giving consumers what they want.

Contact caps continue the trend of limiting the use of phone calls as means to communicate with consumers in the debt collection process. As we wrote before, the biggest challenge to the debt collection industry is that phone calls are becoming irrelevant. The CFPB is continuing the regulatory trends following consumer preference, and while it’s opening up new communication channels, it’s severely limiting phone calls. We expect this trend to worsen.

This rule is a boon for the collection industry. While it may be challenged by those who focus on getting the most profit out of old school technologies, those in the industry who embrace technology and want to help consumers can’t help but appreciate the trend. The regulator is paving the way towards better user experience, better cost adjusted technologies, and an ability to actually help consumers at scale. Industries like e-commerce, tech and fintech have been very focused on consumer experiences and cannot afford to subject their customers to traditional agency behavior.  And major banks and lenders realize that this revolution is coming, and many of them have already engaged in transforming their vendor network and internal operations to be future facing. This rule is another great step on that path.

Response to the FCC Notice of Inquiry (NOI)

By on July 31st, 2017 in Compliance, Debt Collection, Industry Insights

The FCC recently released a Notice Of Inquiry (NOI) on the topic of on-call authentication, and the debt collection industry is again up in arms about its past, rather than embracing its future. Collectors are having a hard time authenticating consumers’ identity on phone calls, and that leads to a lower number of productive conversations. In a detailed article on InsideARM, Stephanie Eidelman correctly states that “While [the proposal] is not aimed specifically at debt collection, the problem is significant in the industry. The next trick would be to assist in helping the consumer authenticate their identity to a legitimate collector, in a way that eliminates the need to share personal information.” Dear collectors, there are wonderful authentication solutions available to you. Put down that headset, turn off your dialer, and turn your attention to the online world.

Consumer preference is changing. 97% of business calls go unanswered, according to Neustar. Phone calls are real-time interactions, imposing on the consumer’s time and attention. Once consumers pick up, they start from deep suspicion towards the person on the other side, who now has to earn their trust while asking for personal information. It’s a stressful situation, especially for someone paid a commission for collected dollars. Often this devolves into a heated exchange between a stressed consumer and an equally stressed collector. Calls aren’t only bad for reaching consumers; they are bad for engaging them in a meaningful exchange, too.

Emails and digital communication channels provide a superior customer experience. Emails and social media apps are password protected, simplifying the authentication process. If you require added security, many established companies offer real time authentication solutions that keep the consumer engaged with your system. It is easy to quantify and improve the experience to keep consumers engaged, reviewing their options, until they find one that fits. Consumers can choose to engage in times that work for them, rather than times when collectors are available to take their call. As a result, using digital channels significantly cannibalizes the phone channel: on average, TrueAccord makes 5 call attempts to each account over a 90 day placement period, compared with up to 6-10 attempts per day in call center based operations, and still collects better with lower complaint rates.

Calls pose multiple challenges – from operational ones to legal ones. They are costly and complicated. The FCC’s ATDS ruling is disastrous and further limits the efficacy of phone calls. Yet collectors choose to focus on fighting phone-related regulation instead of finding new ways to communicate with consumers. It is starting to look as though some prefer a contact method that consumers think of as harassing and intrusive, because moving to digital communications is simply outside of their comfort zone.

Using phone in a digital world. A Data Science story.

By on March 16th, 2017 in Data Science, Debt Collection, Machine Learning, Product and Technology
TrueAccord Blog

Contributors: Vladimir Iglovikov, Sophie Benbenek, and Richard Yeung

It is Wednesday afternoon and the Data Science team at TrueAccord is arguing vociferously. The white board is covered in unintelligible hand writing and fancy looking diagrams. We’re in the middle of a heated debate about something the collections industry has had a fairly developed playbook on for decades: how to use the phone for collections.

Why are we so passionately discussing something so basic? As it turns out, phone is a deceptively deep topic when you are re-inventing recoveries and placing phone in the context of a multi-channel strategy.


 

Solving Attribution of Impact

The complexity of phone within a multi-channel strategy is revealed when you ask a simple question: “What was the impact of this phone call to Bob?”

In a world with only one channel, this question is easy. We call a thousand people and measure what percentage of them pay. But in a multi-channel setting where these people are also getting emails, SMS and letters, there is an attribution problem. If Bob pays after the phone call, we do not know if he would have paid without the phone call.

To complicate matters further, our experiments have shown that phone has two components of impact:

  1. The direct effect — the payments that happen on the call.
  2. The halo effect — the remaining impact of phone; for example seeing a missed call from us and going back to an email from us to click and pay.

To solve the attribution problem and capture both components of impact, we define the concept of incremental benefit as:


 

Intuitively, the incremental benefit of a phone call is the additional expected value from that customer due to the phone call. For example, assume Bob has a 5% chance of paying his $100 debt. If we know that by calling him, the probability of him paying increases to 7%, then the incremental benefit is $2 (100 * (0.07 – 0.05)).

 

How we calculate incremental benefit

Consider the incremental benefit equation in the last section. It requires us to predict the probability of Bob paying for each scenario where we call him and do not call him.

Hence we created models that predict the probability of a customer paying. These models take as inputs everything we know about the customer, including:

  • Debt features: debt amount, days since charge-off, client, prior agencies worked, etc
  • Behavioral features: entire email history, entire pageview history, interactions with agents, phone history, etc
  • Temporal features: time of the day, day of the week, day of the month, etc

The output of the model is the probability of payment by the customer given all of this information. We then have the same model output two predictions: probability of payment with the current event history, and probability of payment if we add one more outbound phone call to the event history.

Back to our example of Bob, the model would output the probabilities of 7% and 5% chance of paying with and without an additional phone call respectively.

This diagram is a simplification that omits many variables and the actual architecture of our models

 

Optimal Call Allocation

The last step of the problem is choosing who to call, and when. The topic of timing optimization deserves its own write-up, so we will close with discussing who we call.

Without loss of generality, assume that we would only ever call a customer once. The diagram below has the percentage of customers called on the x-axis. And the y-axis is in dollars with 2 curves:

  • Incremental Benefit — this curve shows the marginal incremental benefit of calling the customer with the next highest IB
  • Avg cost — this horizontal curve shows the average cost of an outbound call

 

There are two very interesting points to discuss:

  • Profit max — calling everyone to the left of the intersection of incremental benefit and avg cost is the allocation that maximizes profit. Every one of these calls brings in more revenue than cost.
  • Conversion max — notice that incremental benefit dips below zero. This is especially true when you remove the assumption that we only call each customer once. The point that maximizes conversion for the client is to call everyone to the left of where incremental benefit intersects with zero.

Our default strategy is to call all customers to the left of the profit maximizing intercept. Interestingly, an intuitive investigation of the types of customers selected reveals customers at two extremes: we end up calling both very high value customers that have shown a lot of intent to pay (e.g. dropped off from signup after selecting a payment plan) and customers where email has been ineffectual (e.g. keeps opening emails with no clicks or no email opens.)

 

Conclusion

The world has become increasingly digital, and a multi-channel strategy is the right response. Bringing the traditional tool of phone, as just one channel within this strategy, forced us to rethink a lot of assumptions and see where the problem led us. We began by replacing the traditional “propensity to pay” phone metric with incremental benefit, found ways to predict this value, and implemented a phone allocation strategy that maximizes profits for the business.