Building scalable technology requires constant evaluation and improvement. Experimenting is defined by trying new things and creating effective changes that help teams to make informed decisions around product development. Trying new things creates momentum, and organizations that are driven by experimentation turn that momentum into growth.
Machine learning and artificial intelligence support large-scale, concurrent experimentation that helps these technologies to improve upon themselves. With the right tools in place, you can test a variety of scenarios simultaneously.
For example, we use our systems to track changes in the collection process and better understand how our digital collections efforts can be improved. Since digital-first channels offer thorough tracking and analysis, including real-time tracking on our website, we can learn in short cycles and continuously improve our product.
This kind of frequent experimentation helps to avoid making product development decisions based on untested hunches. Instead, you can test your instincts, measure them carefully, and invest energy where it matters.
Machine learning drives the experimentation engine
Aggregating historical data and processing it using machine learning algorithms and artificial intelligence helps you to understand their effectiveness. Regardless of how intelligent your learning algorithms may be, waiting to test and expand your knowledge base before marching blindly ahead can make or break the success of your product.
To launch an experiment, we follow these steps:
Start with a hypothesis that you want to test
Assign a dedicated team to manage the experiment
Monitor the performance of the test as it is guided by machine learning
B2B companies can benefit from partnering directly with clients to customize experiments for their unique product lines in order to make experimentation-based optimization an ongoing process for both new and existing business. Keep in mind that the goal of product optimization is not always jumping to the finish line.
Understanding how your product works ultimately offers you and your customers more value, but it’s easy to become distracted by positive outcomes. Effective, scalable products require intentional design; if you’ve accomplished a goal, but the path there was accidental, taking a few steps back to review that progress and test it can help you to get a clearer picture and grow the way you want.
Below are two sample experiments we conducted to optimize our machine learning algorithms.
Experiment #1: Aligning Payments to Income
The number one reason payment plans fail is consumers don’t have enough money on their card or in their bank account.
If you align debt payments with paydays, consumers are more likely to have funds available, and payment plan breakage is reduced.
We tested three scenarios: a control, one where we defaulted to payments on Fridays, and one where consumers used a date-picker to align with their payments with their payday. After testing and analysis, we determined that the date-picker approach was the most effective as measured by decreased payment plan breakage without negatively impacting conversion rates.
By understanding which payment plan system was the most effective, we were able to provide our AI content that offered these plans as options to more consumers and integrate the knowledge back into our systems and track those improvements at a larger scale!
Experiment #2: Longer payment plans can re-engage consumers
Customers dropped off their payment plans and stopped replying to our communications.
Customers can be enticed to sign up for a new plan if offered longer payment plan terms.
We identified a select group of non-responsive consumers that had broken from their payment plans and sent them additional text messages and emails. These additional messages offered longer payment plan terms than the plans they broke off from.
Ultimately, we found that offering longer payment plans, even with reference to the consumer’s specific life situations didn’t lead to an increase in sign-ups. The offers that we sent had high open and click rates but did not convert. This indicated that we were on the right track but needed to iterate and come up with another hypothesis to test.
This experiment was especially important because it illustrates that not every hypothesis is proven to be correct, and that’s okay! Experimentation processes take time, and the more information you can gather, the better your results will be in the future.
We’re able to simultaneously update our product and continue experimenting, thanks to algorithms called contextual or multi-armed bandits. Here’s what you need to know about these algorithms and how they help!
Building the newest, most innovative products feels exciting, but building without carefully determined direction can be reckless and dangerous. By regularly evaluating the effectiveness of machine learning algorithms, you can make conscious updates that lead to scalable change, and experimentation paves the way for consistent product improvement.
Machine learning algorithms are playing a key role in the collections industry’s technological growth. Companies are working to integrate artificial intelligence and machine learning into their strategies in response to changing regulations and evolving consumer preferences. These processes can look dramatically different from business to business!
Some technologies are being applied to optimize traditional call and collect strategies while others are building digital-first outreach platforms. Understanding how these algorithms are working for the industry can provide insight into the future of collections.
Business intelligence and analytics
Business intelligence platforms are the foundation for the future of collections. They not only help companies understand how to best reach their existing accounts using traditional collections strategies but also integrate into other digital tools to create powerful automated systems.
These algorithms process large sets of data such as call times, call effectiveness, the value of certain accounts, collections rates, and many other variables. By analyzing this information, teams can optimize their outreach strategies by focusing on accounts that are more likely to be collected on, understand what times of day or channels work the best, and even determine what language to use in conversation with specific subsets of accounts.
Portfolio evaluation and exchange
By adding a clear scoring system to business analytics tools, teams can share their portfolios in an online marketplace with other creditors and debt buyers in order to buy, sell, and even outsource debts as needed.
While debt marketplaces are not new, real-time scoring updates and activity insights provide a dynamic, cloud-based view into a fluctuating market.
Human-like contact center agents
As companies evaluate their data and optimize their outreach, they can also integrate digital agents to interact with consumers over the phone. Artificial intelligence software can be used to create human-like voices and personalized experiences for consumers.
These platforms can operate at scale more easily than sprawling call centers but still rely on a traditional call and collect model that consumers are shying away from. As consumer preferences shift toward digital channels, more machine learning tools can help to optimize for an omnichannel experience.
Digital collections platforms
Digital collections software is able to optimize performance data and leverage it using a diverse, multi-channel communication approach. Phone calls may be included as part of a larger strategy, but these platforms are primarily built around modern consumer channels including email, SMS, push notifications, and direct drop voicemails.
Contextual bandit algorithms take channel selection to a level beyond traditional A/B testing. Even if 10% of your consumers prefer one message type to another, it’s important to understand all of your audience’s preferences.
Digital channels integrate seamlessly with decision making algorithms and can optimize communications in ways that call systems cannot. For example, digital channels like email can reach consumers outside of hours typically limited by the TCPA.
25% of TrueAccord’s consumers access their accounts outside of the 9am to 9pm when traditional agencies cannot legally reach them.
Digital debt collection agencies
Each of these implementations of machine learning help to build a more personalized, more focused, and more forward thinking debt collecting experience for both consumers and creditors. One consistent factor that does limit their effectiveness is the need to build them into existing systems or alter processes at scale.
A collection agency that bears the consumer in mind and has a machine learning-driven, digital-first strategy removes this hurdle and enables a full-service, easy to use experience for both companies and consumers. With these technologies built into a team rather than a product or service, digital debt collection agencies can provide the services outlined above alongside a dedicated infrastructure and a team of technology experts.
Choosing the right tools and support for your company’s collection efforts is more important now than ever before, and understanding the options that are available can help you to future-proof your strategy before it’s too late.
Still have questions? Our team is happy to help make sense of what a digital-first collections agency can do. Set up some time to chat!
The term “multi-armed bandit” in machine learning comes from a problem in the world of probability theory. In a multi-armed bandit problem, you have a limited amount of resources to spend and must maximize your gains. You can divide those resources across multiple pathways or channels, you do not know the outcome of each path, but you may learn more about which is performing better over time.
The name is drawn from the one-armed bandit—slot machines—and comes from the idea that a gambler will attempt to maximize their gains by either trying different slot machines or staying where they are.
How do multi-armed bandits fit into machine learning?
Applying this hypothetical problem to a machine-learning model involves using an algorithm to process performance data over time and optimize for better gains as it learns what is successful and what is not.
A commonly used model that follows this type of structure is an A/B/n test or split test where a single variable is isolated and directly compared. While A/B testing can be used for any number of experiments and tests, in a consumer-facing world, it is frequently used to determine the impact and effectiveness of a message.
You can test elements like the content of a message, the timing of its delivery, and any number of other elements in competition with an alternative, measure them, and compare the results. These tests are designed to determine the optimal version of a message, but once that perfect message is crafted and set, you’re stuck with your “perfect” message until you decide to test again.
Anyone that works directly with customers or clients knows that there is no such thing as a perfect, one-size-fits-all solution. Message A, when pitted against Message B may perform better overall, but there is someone in your audience that may still prefer Message B.
Testing different facets of your communication in context with specific subsets of your audience can lead to higher engagement and more dynamic outreach. Figure 1 below outlines how a multi-armed bandit approach can optimize for the right content at the right time for the right audience rather than committing to a single option.
Rather than entirely discarding Message A, the bandit algorithm recognizes that roughly 10% of people still prefer it to other options. Using this more fluid model is also more efficient because you don’t have to wait for a clear winner to emerge, and as you gather more relevant data, they become more potent.
Following from Figure 1, digital collections strategies can determine which messaging is right for which consumer. Sorting this data in context can mean distinguishing groups based on the size or the age of the debt and determining which message is the most appropriate. In a fully connected omni-channel strategy, the bandit can take a step back and determine which channel is the most effective for each account and then determine messaging.
These decisions take time and thousands upon thousands of data points to get “right,” but the wonder of a contextual multi-armed bandit algorithm is that it doesn’t stop learning after making the right choice. It makes the right choice, at the right time, for the right people, and you can reach your consumers the way they want to be reached.
Machine learning is a powerful tool that many companies can use to their advantage. The ability to have algorithms make decisions based on large scale sets of data enables teams to build efficient, scalable tools. Some of these algorithms require frequent monitoring and management from data scientists in order to get up to speed and continue learning. Others are able to operate and learn on their own in order to generate new information to act on!
Supervised and unsupervised machine learning algorithms both have their time and place. Let’s discuss a few examples, the difference between the two, and how they can be used together to create a powerful, AI-driven strategy for your company!
Supervised Machine Learning
Supervised learning algorithms are trained over time based on foundational data. This data will provide certain features as data points that will teach the algorithm how to generate the correct predictions. Figure 1, below, provides an example of a binary classifier and a set of data about cats and dogs that will teach the algorithm how to identify one or the other!
These models function best in situations in which there is an expected, intentionally designed output. In the example above, the expected output is that the algorithm can properly separate cats from dogs. In digital debt collection, it may be separating accounts that will be easy to collect on from ones that are more difficult.
Classification vs. Regression
The models above are both examples of a supervised learning model that is seeking classification, but supervised learning can also be used to build regression models. The key difference between the two is that in a regression model the output is a numerical value rather than categorical.
A regression-based model may use input features such as income and whether or not they have children to accurately predict a person’s age. When using a regression based model in combination with consumer data, you can even segment demographics for communication and marketing.
For full transparency we want to state that TrueAccord does not use its customer demographic data for these purposes. This is strictly an example.
With proper supervision, these models will become more accurate over time, and the data scientists building them can adjust them as business needs change. Whether you are gathering data using a regressor or a classifier, it is dependent upon the data scientists to build the most effective inputs in order to get the “correct” output.
Unsupervised Machine Learning
While supervised models require careful curation in building proper features that will lead to the “correct” output, unsupervised models can take large sets of unlabeled data and identify patterns without aid. The output variables (e.g. dog or cat) are never specified because it is now the algorithm’s job to process and sort the data based on similarities that it can identify. Using this method, you can learn things about your data that you didn’t even know!
Clustering vs. Association
Just as supervised models have primary methods for training their output data as either classification or regression models, unsupervised models can be trained using clusters or associations. Clustering algorithms gather data into groups based on like-features that exist in the data set.
If you have thousands upon thousands of customer accounts in your system, a clustering algorithm can learn using the customer data and form them into distinct (but unlabeled) groups. Once it has assigned these clusters, data scientists can review the output data and make inferences such as:
This cluster is all of the accounts that have not yet established a payment plan
This cluster is all of the users that started signing up for a payment plan but didn’t finish the process
This new data set then provides the foundation for a new outreach strategy!
Association algorithms are the other end of unsupervised learning algorithms. Associations take the idea of grouping random data points one step further and can make inferences based on the data available. Continuing on from our account creation example, an association-based model can identify two data points and draw conclusions based on the patterns it finds. One such pattern may be:
A person that signed up for an account the first time they opened an email is more likely to pay off their balance.
The algorithm recognizes that multiple steps in a customer’s journey creates another data point. Because association algorithms are still unsupervised, a team of scientists will be responsible for labeling the output data, but the algorithm can outline previously unnoticed patterns.
The power of teamwork
By leveraging both supervised and unsupervised machine-learning algorithms, you can make decisions based on previously unfathomable scales of data. While they cannot necessarily be used to substitute one another, they can be used to create a perpetually improving cycle. Using unsupervised models to extract meaningful information from large data sets and building new supervised models to further hone your data creates more opportunities than ever before.
In a technology driven world, effectively gathering and acting on data-driven decisions is essential for success. A growing market of analytical tools combined with an exponentially expanding pool of accessible data means that companies can make more precise decisions than ever before. The realm of machine learning makes accessing and processing that data even easier.
Machine learning is a field of computer science and statistics focused on giving computers the ability to make decisions that they haven’t been explicitly programmed to make. By leveraging data to enable computer systems to make decisions, some of the biggest companies in the world are able to provide better experiences for their users.
The future of debt collection communication is digital, and what better to aid in digital efforts than powerful, adaptable computer models? Here’s what you need to know about machine learning and how it can change your (and your consumer’s) debt collection experience.
How can a machine learn?
Just as a person can learn by consuming more information on a subject, machine learning algorithms are able to learn by aggregating large data sets and identifying patterns, but they still require help getting started! When building a machine learning system, engineers and data scientists collaborate to establish parameters that help the model define data in a set that it can use to extrapolate from. Here’s an example:
A simple, supervised machine learning model known as a binary classifier can serve as a foundation for more complex decision making. Imagine a program that is designed to distinguish cats from dogs. The data scientists building the system know the difference between the two and can pick a few features that are likely to identify one or the other and break the qualitative information into quantitative values that the model can recognize.
Figure 1 (below) depicts how physical features of cats and dogs can be broken down into numbers or binary (Y/N) responses to help the computer model understand what features likely indicate a cat and which features likely indicate a dog!
Once the model has been trained using this data, it can learn what features are most likely correlate to a cat or a dog without the team telling it what to do! (See Figure 2, below).
The binary classifier described here is a supervised learning algorithm, meaning that it still requires designers to engineer its features in order to get it up and running.
Going beyond our cat and dog model, unsupervised machine learning models can aggregate data like this in order to make further predictions and decisions without human involvement!
Applying machine learning to debt collection
So your machine learning algorithm can now fairly reliably recognize the difference between a cat and a dog, but how can this process help in debt collection? When algorithms can slowly learn to distinguish results or users and place them into groups, they can learn to do things like:
Understand what kinds of messaging people respond to
Recognize what kinds of payment offers seem to be accepted
Define different types of consumers
With enough data to analyze and enough features extracted from that data, machine learning algorithms can help you to optimize collections processes. Rather than telling us “this is a cat” or “that is a dog,” a similar system could be used to make observations like:
“This type of account will be especially difficult to collect on”
“That consumer may like to receive fewer emails”
Or even something as specific as “this content might be more engaging for this consumer”
This information can help to inform new collections strategies, dictate the use of different communication channels, or provide further insights into effectively segmenting a customer base.
By crunching enormous amounts of information, an unsupervised machine learning model may be able to recognize patterns in groups that have similar preferences or needs and relay relevant communications to them based on that information!
If you’re interested in learning more about how machine learning can be harnessed to communicate with customers, check out this interview with two of TrueAccord’s data team!
Experimenting to learn more
One way to continue improving a machine learning model’s decision making ability is to provide it with more data and features to learn from. Perfecting a model requires a very scientific (and iterative) approach:
Start with a hypothesis that you want to test
Monitor what decisions it is making based on the data available
Introduce new information
Review how the system operates and what decisions it makes with the newly presented data
By experimenting with various tools and approaches, a debt collection-focused machine-learning model can work in conjunction with data teams to rapidly evolve and improve collections efficiencies at different stages of the collections process.
Machines learn and collections grow
As it becomes more and more difficult to contact consumers in debt, integrating digital collections solutions into a collection strategy is becoming invaluable. Digital debt collection offers more opportunities for in-depth analysis, and by introducing machine-learning to that evaluation process, you can build systems that can support their own growth and improvement!
The more data you have, the better you can collect, and the more you collect, the more data you have. The self-sustaining nature of machine learning is revolutionizing approaches to collections, but it isn’t as easy as it sounds. Building and continuing to maintain complex systems requires a talented team and a stable infrastructure that can support these processes at scale.
Those that can properly build and manage these systems will be the driving forces in the future of the collections industry, so find your partner and learn what you can. Maybe these machines can teach the industry a thing or two.
TrueAccord’s machine learning based system handles millions of consumer interactions a month and is growing fast. In this podcast, hear our Head of Engineering Mike Higuera talk about scaling challenges, prioritizing work on bugs vs. features, and other pressing topics he’s had to deal with while building our system.
TrueAccord’s system is machine learning based, but every new product type requires a little bit of tuning to beat the competition. Hear our CSO and VP of Finance in this short podcast about the Conversion Team and what it does to make sure TrueAccord stays ahead of competition.
Our CEO, Ohad Samet, recorded a podcast with Lend Academy discussing the positive impact technology is creating in the collections space and the need for more innovation. Will discuss TrueAccord’s unique approach to debt collection using data-driven, digital communications to create deeply personalized consumer experiences.
The podcast also covers the current state of the collections industry and where it’s likely headed as regulatory pressure, consumer preferences and compliance requirements converge. Will cover how TrueAccord is using machine learning to deliver deeply personalized and engaging experiences for consumers while achieving higher recovery rates across various debt types.
Tune in and learn:
The state of the debt collection industry today and where it’s headed
How the use of machine learning is personalizing the debt collections experience for greater conversions
Why code-driven compliance outperforms traditional collections practices by reducing risk to organizations
How understanding consumers’ preferences for easy, self-service options with flexibility empowers more consumers to pay off their debt and get on a path to financial health
Yesterday, in an article on InsideARM.com, Tim Bauer, the President of InsideARM, described a somber state of affairs:
The TCPA and the 2015 FCC Rules interpreting the act have effectively eliminated the use of technology to efficiently call cell phones. Land line usage is dropping like an anchor. The CFPB is on the brink of announcing proposed debt collection rules that are likely to reduce the number of call attempts that can be made. Now, add this latest call blocking technology and the industry is challenged again.
This is a strong statement from a prominent thought leader in the debt collection industry. Mr. Bauer pointed out many efforts by different regulatory agencies and how they impact call centers: “anecdotal reports of right party connects down by 15-30%”, as the FCC includes debt collection calls as an “unwanted call” category in it’s “robocall” blocking initiatives.
At TrueAccord, we agree. The industry has been seeing tremendous pressure on its ability to call consumers efficiently, not only because of regulatory pressure – this pressure is driven by consumer preference, and the fact that consumers often opt to not pick up the phone, not to mention opening a letter. As strong advocates for technology in debt collection, with our CEO now part of the CFPB’s Consumer Advisory Board, we will continue to support forward thinkers such as Mr. Bauer and others who call for the use of new technologies in debt collection. It is the consumer friendly, smart, and efficient approach for the 21st century, and we strongly encourage our peers in this industry to begin adopting and utilizing these channels in preparation for the CFPB’s expected Notice of Proposed Rulemaking, expected later this year.
Debt collection is a highly litigated activity. Compliance personnel and systems budgets are crowding out other investments. It’s appropriate: debt collectors and creditors are often hit by class action lawsuits and government action, leading to huge fines and settlements. Reducing risk is their primary priority. When examined closely, though, the traditional debt collection model attracts numerous compliance issues. The legacy approach is being replaced by machine learning and digital first systems. These code-controlled systems offer predictable, scalable, and auditable operations that, coupled with best in class user experience, significantly reduce the risk of litigation and regulatory action.
The traditional model invites regulatory scrutiny and lawsuits
Collectors often cite compliance concerns as impediment to adopting new technologies. Lawyers are concerned about TCPA exposure from text messaging, consent requirements for emails, and FDCPA violations when using social media. These concerns are unfounded: text messages can be safely delivered if consent and revocation are properly documented, the CFPB saw no need for consent to email (as reflected by a growing body of opinions, as well as its 2016 rule outline), and social media can be used with restraint. While dragging their feet on evaluating new technologies, compliance departments embrace and perpetuate much bigger risks: the prevalent use of human labor, over reliance on phone calls, and the outdated, fragmented interfaces used by collectors.
Humans are the weakest link in the compliance chain
Traditional wisdom says that only people collect from people. That claim is demonstrably false. People are subject to biases and acting emotionally when interacting with debtors – which is why machine learning based systems collect better than humans. People may be tired, angry, or distracted. They can be baited into violating the FDCPA by a ill-meaning debtor. The prevalent commission-based compensation model, a broken and outdated model for collections, puts them in odds with debtors whenever they interact. Human beings just cannot do error-free work, no matter how trained or experienced they are.
Keeping appropriate staffing levels is another challenge for collection teams. Large market participants report 75-100% annual turnover rates (per the CFPB’s operational survey), requiring constant hiring of collection staff. Training and overseeing these new people is a daunting task, especially with the ever changing case law and legislative landscape in the collection space. Providing an efficient and fully compliant collection experience while relying on new and untrained collectors is almost impossible.
Phone calls are a dying communication method
Consumer preference is shifting away from phone calls, but phone call compliance would have been difficult even if that wasn’t the case. Calls are a compliance liability due to their frequency, their real-time nature, and the overall regulatory sentiment towards them.
Collection calls must be frequent to reach consumers. On days when an agent works an account, they may attempt to contact the consumer 4-6 times, often as frequently as 10 times per day. Consumers aren’t picking up the phone, so agents need to make more call attempts to try and reach them. While most states, and the FDCPA, don’t limit call frequency, high frequency of calls often leads to complaints and lawsuits alleging harassment. Collector take this huge risk because calling is the only tool they understand.
Collection calls are also real-time. No matter how elaborate call scripts are and how experienced collectors may be, it is impossible to completely control the development of any individual call. Voice analytics software is limited, unable to identify most baiting and escalation issues. Real time monitoring of all calls by supervisors is financially implausible. Collection agencies are forced to settle for the best training possible, clear escalation paths for collectors whose calls go badly, and hoping for the best. Realistically, when making a large volume of calls, every day will have some potential violation.
Finally, regulation has been working against phone calls for the past few years. The FCC’s ruling limiting the use of ATDS has been devastating, and expecting it to be completely undone by the new commissioner is a pipe dream – government is not debt collectors’ friend. States like West Virginia and Massachusetts have enacted call frequency limitations, and the CFPB’s new rule outline includes a 6-times-per-week limit on call attempts. All signs point to a future where phone calls cannot plausibly be the main channel for collecting debt with any semblance of compliance.
Code driven compliance is here, and it’s a big step forward
Code driven compliance gives us complete control on what actions can be triggered by our system. It’s one of the components in Heartbeat, our machine learning-based, digital first collection platform. Heartbeat is a leap forward in debt collection, and its compliance advantages are many: from better user experience to perfect auditability.
Best in class user experience in debt collection is a compliance advantage
Many if not most of debt collection lawsuits hang on a technicality. A word is arguably missing or written in a debatable way. It’s unclear whether 8 calls or 9 calls constitute harassment. Often, consumers don’t resort to lawyers because they know for a fact they have been wronged – it is often not clear that they have been – but because their experience with the collector has been bad enough to push them to seek defence or retribution. Great user experience is therefore not only a way to improve the creditor’s brand perception and returns, but also a way to reduce the rate of complaints and lawsuits. TrueAccord’s Heartbeat system attempts to contact consumers an average of 3 times per week, compared to 4-6 times a day for traditional agencies. That, paired with best in class web and mobile experience and a helpful customer service department, significantly reduces consumers’ desire to sue for, or complain about, ambiguous technicalities.
Consumers get a consolidated account page showing all their options
Since more than 90% of Heartbeat’s interactions with the consumer do not involve a human collector, human beings are only needed for a fraction of the work. TrueAccord is able to hire skilled workers and pay them a living wage, with no commission component. Knowing that they will earn a good salary working for a technology startup reduces any incentive our team members would have had to fight with or harass consumers. That, in turn, contributes to great user experience and reduces compliance risk.
Pre-approved content and an integrated system eliminate human error
Human error is the biggest challenge for compliance departments. Collectors today need to navigate multiple systems to call, negotiate with, and collect payments from consumers. Updating the results of a call is often a complex process, requiring yet another system. Many requests to unsubscribe numbers, cease and desist communications, or simply to provide debt verification are lost and lead to complaints. This fragmented process is extremely tedious and time consuming, and inherently flawed. Letting collectors write their own emails and text messages is too much risk – something that will surely lead to violations on a daily basis.
TrueAccord’s content approval console
Heartbeat takes a code controlled approach to communications. Every outgoing communication is pre-written, then reviewed and pre-approved by TrueAccord’s legal team. Every email, text, web page and letter have to pass TrueAccord’s content guidelines driven by law, policy and procedures, including required disclosures and forbidding certain words and phrases in subject lines, or in the body of communications. Our clients’ legal and content team are also involved in commenting on our procedures as well as specific content items, to make sure we fit each company’s risk tolerance. Heartbeat will only send text messages to numbers that it knows it has express consent to text, and that have gone through an ownership check within a defined time period. Even when collectors respond to inbound consumer emails, they use pre-written replies that then direct Heartbeat how to proceed in serving the consumer. The decision to proactively communicate is strictly based on Heartbeat logic, not on collector whims; collectors cannot decide to contact consumers whenever they see fit.
After contacting consumers, the system monitors their response. Consumers can easily opt out of communications, by replying to a text message or by clicking a link in every email that lets them easily unsubscribe from future email communications. Every email and every payment page contain a link that lets consumers ask for debt verification via a few simple online steps instead of a cumbersome and mail-based process. Every interaction is designed to give consumers an opportunity to ask for more information or limit communications to their preferred channel. Though easy to dismiss as an invitation for abuse, these options increase consumer engagement and result in overall better collections – while significantly reducing complaints about continued communications and missing documentation. These two categories have consistently been the top reasons for filing CFPB disputes ever since its dispute portal was made public.
The compliance firewall: enforcing compliance at scale
Human collectors are expected to remember dozens, maybe hundreds of compliance laws and regulations as well as creditor-imposed rules. It’s an impossible task, greatly simplified by Heartbeat’s Compliance Firewall. Since it controls all contact decisions by code, Heartbeat can enforce its compliance policy at scale on every interaction without needing to train human collectors. Contact timing or frequency, matching content to the right stage in a consumer’s process or preventing the use of unsubscribed contact methods, even making sure that a consumer doesn’t get a payment offer that the creditor didn’t approve – all are controlled by the Compliance Checker. Any attempted action outside of its well defined policy is dropped. Since it’s code controlled, it cannot forget to check the time and call a consumer after 9pm or before 8am.
The Compliance Firewall also allows updates to policies and procedures. Every new update can be implemented with accuracy within days, once the appropriate code is written. By taking judgement away from the collector and subjecting all contact decisions to a data-based, code-controlled system, Heartbeat makes the optimal decision for consumer experience and driving payments, without harassing the consumer or violating the myriad of restrictions that govern debt collection.
The easiest system to audit
Compliance requires tight monitoring, and creditors audit a large sample of collection activities by their vendors. With so many voice calls, even if they are all recorded, complete and accurate audits are impossible. Auditors need to sample cases and hope to find the right patterns, or employ a large and expensive team for sufficient coverage. Heartbeat eliminates almost 95% of phone calls (typically attempting to reach the consumer 3-5 times over a 90 day period), instead focusing on written communication. Back and forth written interactions are easier to capture, store, and search. The system also saves consumers’ browsing pattern on the website and their interactions with the content they receive. It’s easy to track consumer behavior and how the system responded to it, as well as why it made a specific decision. Code controlled compliance means that decisions are easy to replicate and trace back in case they’re questioned.
A readout from TrueAccord’s event-based audit trail
TrueAccord’s system also has an audit interface for creditor audits. Compliance staff can easily search for accounts and review all collection activity – including recorded calls, emails, and every other contact. It’s a much easier approach to compliance and controls than an unwieldy excel file or PDFs dropped in an FTP folder. TrueAccord’s data retention and tracking of consumer behavior provide a fuller snapshot of Heartbeat’s collection decisions and how consumers reacted to them.
Code driven compliance is the future
We examined the inherent risks in traditional collection activities and how sticking to the phone as the leading collection tool in a call center environment creates more risks than rewards. Then, we dove into how code controlled compliance offers predictable, pre-approved, and consistent collection strategies that are easy to audit and understand. The coming years will see more and more creditors and collectors move to these machine learning based systems, as they demonstrate dominance in returns and compliance. It’s time for risk averse compliance departments to realize that they are putting businesses at risk by sticking to their phone-based roots, and look beyond tradition. A whole world of mature, stable and trustworthy technologies awaits.
TrueAccord is a machine-learning and Al-driven 3rd-party debt collection company that is reinventing debt collection. We make debt collection empathetic and customer-focused and deliver a great user experience.
Our digital-first approach to debt collection creates a cycle of collections growth:
1. Improve the perception of the industry
2. Provide a personalized experience
3. Build brand equity and collect