5 ways debt collection uses machine learning and artificial intelligence

By on February 28th, 2020 in Machine Learning

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!

5 ways to encourage timely customer payments

By on February 21st, 2020 in Industry Insights

Expanding a small business requires a consistent and a steady, growing cash flow. Especially in the early stages of growth, a single, large payment or several smaller payments being delayed could mean the difference between keeping your doors open and closing up shop. 

Your consumers may delay or cancel their payment for any number of reasons: a more urgent financial need arose, they had a disagreement with you about your product or service, they simply forgot to pay, or they adamantly refused to pay for no reason at all. Navigating these situations with your customers can be a challenge and can take time and valuable resources. You have to consider:

  1. How much effort you’re willing or able to put into pursuing payment
  2. How much time you will spend on individual accounts
  3. Whether or not you’re willing to damage a customer relationship (or even lose them as a customer) to secure payment

Unfortunately, there is no right answer to these questions, and your business’ response will vary from case to case. 

Not everyone will pay what they owe

As delayed payments begin to pile up, many small businesses will begin to try to collect on these payments themselves, and the outside options are often limited due to traditional agencies having account volume or account value minimums. Traditional agencies are also seen as greedy, uncompromising, and even sometimes threatening according to a study published in the Journal of Business Ethics. You may only see 50% of whatever they are able to collect, and then also lose out on your customer relationships.

Some customers won’t pay. Period. Newer digital debt collection strategies can help to collect on these accounts and even build up your business’ reputation with consumers, but before you commit to using a 3rd-party collection service, there are some steps you can take to get closer to 100% payment rates! 

1. Have a clear plan for offering credit 

Negotiate payment terms in advance, write them down, and limit how much risk you take on each transaction. It can also help to adopt pre-paid models whenever possible and require a payment instrument before you let customers use your product. 

Your risk team should also be wary of newer customers without an established credit history. If you see a customer start using your product or service and they run up a significant balance in their first few days or weeks, monitor their account carefully. If you run an eCommerce business or a marketplace, frequent and aggressive purchasing sprees from new customers are a major red flag and should be examined before they become larger issues.

2. Charge and invoice promptly

By issuing your invoice or charging a payment instrument immediately following the completion of a job, you can secure payment without leaving room for evading payment.

Beyond that, you can build a (preferably automated) process for following up on chargebacks, outstanding balances, or invoices early and often. There is a careful balance between “often” and “too much” though, so be careful as you set up your contact cadence. Even if you don’t get paid on time, keeping yourself at the top of customers’ minds increases awareness and prepares them to negotiate payment terms when they’re able.

3. Make payment frictionless

Keep a payment instrument on file for your customers and verify it with a $0 authorization. You can also expand your available options and make it easy to set up multiple forms of payment; the more backup payment options you have on hand, the better your chances of completing payment. 

4. Talk to your customers like people

A few stray consumers may actively or angrily refuse to make a payment, but most of your customers want to stay out of debt. If you approach every delayed payment in this way, you can approach payment (and collections) with human in mind, and you can end up retaining a valuable, long term customer.

Customers that you work with may be able to provide invaluable feedback to your team’s processes. Make sure to follow up and talk to them!

Your small business’ goal with receivable management isn’t only to prevent late paying customers, it’s also to retain positive relationships with the most valuable ones. Don’t let a temporary situation ruin a beneficial long term relationship.

5. Prepare an escalation structure

Investing in preventing late paying customers can pay dividends to your bottom line, but retaining some expert help in the event you can’t collect on a delinquent account can be an effective strategy as well. Your risk team may be experts themselves, but accounts recovery is a complex industry to navigate, and if you don’t plan on building a full, first-party collections team in-house, you can form connections with other agencies. 

Having a small business collections partner as a last resort also increases your chances of recovery by informing customers that a delayed payment will likely move to collections. Consumers often recognize that having an account in collections can damage their credit scores and will do their best to pay if they are able.  

It’s not easy to prevent customers from missing the occasional payment, but by following a thorough process you can resolve delayed payments before they can damage your business. 

If delays begin to grow out of hand, you can always reach out to a digital debt collection agency like TrueAccord! Let our team know if you have questions.

Multi-armed bandit models and machine learning

By on February 19th, 2020 in Machine Learning

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.

Email deliverability plays a key role in effective digital communications. Check out our tips for building a scalable email infrastructure.

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.

Multi-armed bandits and digital debt collection

Collections continues to expand its digital footprint, and combining more in-depth data tracking with an omni-channel communication strategy, teams can clearly understand what’s working and what isn’t. Adapting a bandit algorithm to machine learning-powered digital debt collection provides endless opportunity to craft a better consumer experience. 

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.

TrueAccord is optimizing how our multi-armed bandit algorithms create the ideal consumer experience. Come learn more about how we collect better!

3 essential digital channels for collections

By on February 13th, 2020 in Industry Insights

The debt collection industry is in the midst of rapid change. With the decline of the effectiveness of phone calls and upcoming legislation from the CFPB that includes limiting call volume, it’s more important than ever that your company’s collections strategy diversifies and introduces a digital, multi-channel approach to communicating with consumers.

Determining what digital channels work the best for your collection strategy isn’t an overnight decision, and using them effectively is another hurdle entirely. When reviewing potential communication channels, you have to consider how you want to use them, how you plan to scale them, and what the investment will be for doing those things properly.

Email

According to the State of Collection 2019, email is the most commonly used digital channel used to communicate with consumers in debt (beating SMS text messaging by 45%). Its frequency of use, however, does not mean that it is necessarily being used effectively. Sending manual emails haphazardly can lead to mixed results at best.

Trying to send emails at the scale required of a dedicated agency, however, is even more difficult, and poor email management can lead to low deliverability rates, poor domain authority (you may end up relegated to spam folders), and can even end up getting your company’s sending domains blacklisted from reaching any of your consumers. Figure 1, below, shows Debt Collector A’s email sending volume.

Figure 1

Sending hundreds of thousands of emails per month can seem like an effective strategy at face value, but when deliverability is taken into consideration, that appearance changes.

Figure 2, below, mirrors the bar graph in Figure 1 and represents the percentage of the emails sent from Debt Collector A that are delivered to an inbox vs. those that are filtered into a spam folder.

Figure 2

A 2019 email client market share study by Litmus shows just how valuable it can be to understand how to work with individual email service providers that all come with their own unique challenges and filters to protect their users. Gmail, for example, maintains 28% of email users, but only 1% of Debt Collector A’s emails are reaching Gmail users.

Cost

Emails can be an effective strategy, but doing so effectively at scale requires extensive infrastructure. That infrastructure includes five major things, including bringing on email experts to work with email service providers, detailed performance tracking, and creating valuable content for your consumers to engage with. Simple email may not cost much, but building a powerful email-driven strategy from the ground up won’t be cheap or easy.

Emails can serve as the foundation of an omni-channel digital strategy, but creating an ecosystem for consumers to engage at their convenience requires more than one tool.

SMS text messaging

Smartphones abound, and when Americans are sending roughly 26 billion text messages every day, it’s easy to see the potential in the texting as a collections communication channel. Millennials spend 3X more time texting than calling or emailing, and they hold an average of $4,712 in consumer debt (not to mention mounting student debt) which makes them prime targets for daunting debt collectors hounding them about a balance. This can be intimidating and turn consumers further away from wanting to work with you.

SMS allows for fast, direct contact with consumers that are on the move, don’t have time for a phone call, and may have breezed past an email or two. By creating a flexible system with multiple touch-points across different channels, you can create an organic system of contacting consumers rather that gives them the power to contact your team when and where they want.

Key uses for SMS:

  1. Payment notifications
    1. Following up with customers to confirm a payment can help to reassure them that their next step toward financial freedom is done and increases transparency between your business and consumers. 
  2. Payment reminders
    1. Even consumers on a payment plan might forget once in a while. A ping with a text message can be just enough of a nudge to remind them to log in and make their scheduled payment.
  3. Providing instant access to their account
    1. By providing a one-click option for a consumer to make their payment, you can make taking the next step easy! Pairing this option with a simple online payment portal gives consumers the opportunity for a full self-service experience.
  4. Tracking your performance
    1. As is the case with other digital channels, tracking your data and performance is easier than ever with texting. You can A/B test messaging and get consistent results for improving engagement.

When you’re considering what to include directly as part of the content of a text message, keep in mind that people expect texts to be short! Length aside, make sure to avoid:

  1. Sensitive information (e.g., account balances, credit card information, etc).
  2. Misleading information
  3. Threatening consumers
  4. Harassing consumers

Text messages have a 209% higher response rate than phone, email, or Facebook, and part of the reason for that is that they are digestible and often feel informal and friendly. On the flip side, misleading, threatening, and harassing texts not only deter engagement and damage your brand, they are also illegal.

Plus, the CFPB’s proposed rules will give consumers the ability to opt out of text messaging, and your texting numbers can still be blocked manually. Be selective with the messages you send and consider the consumer experience.

Getting started with texting using certain software companies can be as cheap as pennies per message. Full-scale agencies like TrueAccord also make use of SMS tools as part of a broader collections strategy alongside other digital tools.

Direct drop voicemail

Direct drop voicemails (also known as ringless voicemail drops) are a unique channel that can help supplement a digital communication strategy but can’t do much on their own. Rather than an agent calling a consumer directly, a voicemail is delivered to the recipient’s inbox without their phone ringing (hence the name).

The consumer still receives a message from a pre-recorded voice that can relay much of the same information that they would have gotten from an agent, but they do not feel the urgent response pressure associated with a phone call. Much like text messages, direct drop voicemails can be used sparingly as a touch point to remind consumers of upcoming payments or ask them to check an email or call an agent back.

From a cost perspective, direct voicemail offerings can range from a few cents to a few tenths of a cent depending on the provider, and many companies will charge based on successful drops rather than a flat charge for the volume sent which can avoid costs incurred for out of date or incorrect phone numbers.

Both direct drop voicemails and text messages are legally classified as phone calls by the TCPA as the law applies to “placing a call or text to a consumer using the consumer’s mobile number.” Be careful with when and how you decide to use either channel in your collections strategy!

As consumer preferences and collections law continue to evolve, we should expect to see rapid growth in both existing digital channels as well as the emergence of others! Effectively integrating these tools into your strategy together can create a much larger impact than any one channel in isolation, and teams that build these systems today will be the future leaders of the industry very soon.

5 tips for building scalable email infrastructure

By on February 6th, 2020 in Product and Technology

Using email as a channel for consumer communication seems like a simple way to dive into the digital revolution, but internet service providers (ISPs) actively develop tools to combat spam and abuse.

You may have the best intentions, but these service providers want to help consumers feel like they are protected which means blacklisting and filtering out junk mail. Unfortunately, emails sent by the untrained email sender can veer dangerously close to junk. 

This can make breaking into emailing consumers difficult, but it makes sending emails by the thousands (and millions) impossible without building email infrastructure that is sustainable and scalable. Establishing that infrastructure begins with recognizing the challenges you might face and then considering how to best confront them.

Why scaling email infrastructure is difficult

Email communication is heavily regulated by automated filters and systems in a way that more manual forms of communication aren’t. Cell service providers, for example, do not have nearly as much control over the volume or quality of calls that their customers receive. 

ISPs have dedicated engineers that design algorithms to keep their users happy, engaged, and protected from malicious senders, and an inbox packed with spam mail makes for a poor user experience. These algorithms are not perfect, and when they are designed, they lean on the side of being more restrictive than less which can lead to some misunderstanding. They may accidentally filter out an email from a legitimate sender that, according to their understanding of what is deemed safe, seems suspicious.

To make matters more complicated, each ISP has unique criteria that serve as the basis of their filtering rules. An email that is flagged as spam by Google could land safely in a Yahoo Mail inbox and vice versa. These rules are also constantly changing and updating to fight back against more advanced scammers making it impossible to create a one-and-done solution to properly sending emails at a massive scale.

Here are just a few things that spam filters analyze that you’ll need to consider:

  • Content: What do your emails say? Do you have any suspicious attachments or links?
  • Design: How do your emails look?
  • Sending time: Did your email arrive at 4pm or 4am?
  • Sending volume: How many of these emails did you send out at once?
  • Sending frequency: How often are you trying to email people?
  • Consumer engagement: Is anyone actually opening/clicking your emails?

Working to get all of these answers (and more) right is essential or you might find your email domain permanently blacklisted from one or all of the ISPs that you’re sending to. So what can you do to build a scalable infrastructure and work within these restraints?

How to successfully send email at scale

As we mentioned above, there isn’t necessarily a single, perfect solution for overcoming the innumerable hurdles to large-scale emailing. It takes dedicated and focused strategy to improve your long term inbox placement rates. Here are a few tips that our team keeps in mind as we continue to grow.

Create valuable content

The first step to making sure your emails are well-received by both users and ISP filters alike is creating the right content. Well-designed UX and carefully curated text are important, but it’s equally important that you steer clear of some phrases and keywords and trigger red flags.

Here’s a list of some spam trigger words that you might want to avoid!

Having a dedicated content team gives you the flexibility to create more personalized and more human messages that have a better chance at reaching your intended audience!

Talk to experts

We know we’ve been thorough, but fully understanding the challenges of sending email at scale isn’t something we can teach you in a few hundred words. TrueAccord has a full team of email deliverability experts on staff that can provide industry specific knowledge and know the ins-and-outs of different ISPs’ requirements. 

They also regularly audit our deliverability rates so that we can iterate on our processes and improve and help segment our domains and IP addresses as we grow.

Segment domains and IP addresses

Thankfully, our email experts can help explain what that last bit means. Segmenting your domains simply means building different domains that you can email consumers from. For example, some of your emails may come from emails@companyA.com and others may come from emails@help.companyA.com. The same goes for segmenting IP addresses; you may send some of your emails from your main office and others from your satellite office.

This process can help to limit the risk to your brand’s reputation with ISPs as you are less likely to take a big hit if only one of your many email addresses makes a mistake (e.g. bouncing frequently, receiving a lot of spam complaints, having many of its emails remain unopened). 

This process is intricate and methodical. Creating ten new domains can’t solve deliverability problems because brand new domains also lack authority. If an ISP’s filters see that a brand new email address is sending out 100,000 emails, it’s likely that it’ll be swept to the side. Which brings us to our next point!

Take it slow

Scaling your program too quickly is heavily penalized even among senders with high engagements. Many well-established companies that want to build a large scale email strategy with their existing customer base make this mistake, and sometimes there isn’t a way to fix it. Placing strict limits on email volume growth can help ensure that ISPs don’t flag your domain.

Track your data

Set your benchmarks, track your performance, and make changes as you go. Data is the life blood of a scalable email program. As you’ve seen, there’s a lot to keep track of, and if any segments of your strategy spring a leak, the ship might sink. 

By frequently and carefully monitoring performance—from open and click rates to inboxing rates to bounce rates—you can maintain a full view of your email strategy and make improvements as you build. 

No one has the power to flip a switch and send millions of emails per month without risk, but if you build slowly, you can lay the foundation for a successful email strategy. If you have any questions, let us know in the comments below! 

TrueAccord sends 40x more emails and has up to 70% higher inboxing rates than other collection agencies. Chat with our team today to learn more about what that means for you!

Supervised vs. unsupervised machine learning

By on February 5th, 2020 in Machine Learning

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!

Building the infrastructure to process this data is the hardest part. Learn more about how TrueAccord is laying the foundation for scalable machine learning systems!

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.

Why customer feedback is so important for your small business

By on January 30th, 2020 in User Experience

Everyone knows that customers are the backbone of a business; if people don’t use your service or buy your product then you won’t have a business for very long. In order to solve this problem, companies often work to bring in as many new customers as possible, but you can’t forget to nurture relationships with consumers that you’ve worked with in the past. 

According to Adobe, 40% of eCommerce revenue comes from returning customers which make up only 8% of total visitors! That number alone should inspire you to get out and talk to your old customers and figure out what they think, but there are quite a few more reasons you should cherish customer feedback and use it to strengthen your company!

Building brand promoters

The omnipresence of social media means that consumers that are excited about your company will shout from the digital rooftops to endorse you. Unfortunately, the power of social sharing also means that the opposite is true: if a person has a particularly negative experience with your brand, they will spread the word around fairly quickly. 

Properly managing customer feedback can dramatically improve your brand’s reliability. A Net Promoter Score measures customer’s satisfaction with a business by asking: “how likely are you to recommend this (product/service) to a friend?” Customers that rate your business at a 9 or a 10 are considered promoters and are your best friend when it comes to spreading the word about your brand. 

Maintaining a high NPS score is challenging, but by focusing some efforts on gathering and listening to customer feedback, you can gradually build effective, organic branding that sets you apart from your competition!

If maintaining customer relationships is so important, you may be hesitant to try and collect on debts for fear of negative feedback. But digital debt collection solutions can support your brand and your bottom line!

Incorporating feedback and iterating

Not every review will revolutionize your business. If you take every negative review to heart, you might start to feel a bit down on yourself, but by analyzing customer feedback in aggregate, you’ll start to see patterns emerge!

These patterns won’t appear overnight, and even some patterns may not give you the direction you’re looking for (it is still your business after all). That said, if you have dozens of customers asking for a new feature or piece of content, imagine how many more customers want the same thing that aren’t asking!

By listening to customer feedback and building new tools that your customers are looking for, you can demonstrate that you listen to them and further improve retention. Plus, incorporating these changes into your customer lifecycle can pay big dividends! 

Promoters will continue to support your brand, bring in new customers, and in the long run, they will continue to spend more as your brand relationship improves. A survey by Bain & Company shows that customers actually spend more in months 31-36 of their relationship with a brand than they do in the first six months.

Creating a self-sustaining system

Feedback helps your business to grow and meet the ever-expanding needs of your market. If you don’t listen to your customers and build in a vacuum, you may soon realize that you were not solving the root of a problem. This isn’t to say that every customer suggestion or idea is the right one for your business, but if you take the time to listen to your customers you’ll build their trust and might just find the next right step. 

5 tips for recognizing debt collection phishing scams

By on January 29th, 2020 in User Experience

When communicating with debt collectors it’s important to ensure they are legitimate before making a payment. Scammers posing as debt collectors will pressure you aggressively, use threatening language, and will not provide any documentation to verify the debt.. When a scammer is attempting to collect a fake debt using an email it’s called a phishing scam.

The vague nature of scammer scare tactics combined with the sense of urgency in their communications make for a worrisome case, but if you keep a level head and follow these quick tips, you can protect yourself from phishing scams.

1. Verify the sender’s email address

Scammers will often make themselves appear legitimate by operating under a company or other authority figure’s name, but they cannot replicate a sender’s address. For example, if you receive a collections communication from TrueAccord, it will be from one of our company domains meaning that the email address (after the @ symbol) will either read “trueaccord.com” or a related address.

Even if you are anticipating communications from a collector (or anyone else for that matter), take a second to review the “From” address confirm that they are who they say they are. And in the case of collections, if they seem suspicious or don’t have a company domain, don’t respond to the email or click on any links.

2. Validate but do not click on links

Debt collection phishing scams are designed to collect private information—like your credit card number or bank account and routing numbers—by tricking you into providing that data. Some of them are even more malicious and will try to get you to download malware directly onto your computer.

Any links provided in the body of the email could redirect you to fake sign-in pages that will share your login credentials with the scammer, payment portals designed to capture account numbers, or even prompt you to download malware that could jeopardize the security of your entire device.

In order to check that the links in the email are legitimate, you can hover your mouse cursor over the link to see a link preview, likely at the bottom of your screen with the full URL. Make sure that you do not click when previewing the link, especially if you spotted a suspicious email address.

By hovering your mouse cursor over the link without clicking, you can make sure that the link address information matches the information in the email explaining where the link will direct you.

3. Investigate the company

If a collector’s information seems accurate, but you don’t recognize the debt the most surefire way to dissuade a phishing scam is to probe more deeply. Look up the debt collection company online see if the company is registered with the Better Business Bureau, conduct a Certified Business Search through RMAI or and email the company’s support team to confirm they sent the message.

Like we mentioned above: a scammer’s best friend is an unaware consumer.

If the content of the email is legitimate, they will also have a way for you to validate your debt before you pay them a penny. Call, write, or email  the debt collection company directly and request additional documentation Scammers won’t offer additional details because they don’t have it—a company that collects real debt will. 

4. Take your time to process the content

Scammers know that they don’t have much time to get the information they want. Once a recipient of a phishing email can process the details and recognizes that they don’t add up, the scam is a bust. This is why scammers posing as debt collectors rely on aggressive, manipulative, and urgent language. They may threaten legal action or other types of harm and will stop at nothing to make you pay as soon as possible.

Real debt collectors will not resort to these tactics, and many of the actions that these scammers threaten are actually against the law. Don’t let explicit language and threats pressure you into paying; while being in debt has obvious downsides, fake debt does not. By remaining patient and seeing through their smoke and mirrors, you can report the email as a phishing attempt and safely move on with your day.

5. Check for spelling and grammar errors

Phony debt collectors are hoping to catch you off guard. Their phishing emails are designed to look professional on the surface, but with a careful eye, they can easily be picked apart. Scammers target distracted, uninformed, and unaware consumers which is why their messages are often hastily thrown together. 

This means that phishing emails are much more likely to have typos, spelling errors, and issues with proper grammar. Read the message carefully and remain suspect if a message doesn’t make sense or look like they were thrown through a quick Google translate.

Stay informed and stay safe

It’s easy to feel overwhelmed by debt, and mounting debts from multiple sources can make it feel like you’re in a spiral. Scammers that send phishing emails prey on vulnerable consumers and take advantage of those financial fears, but keep these tips in mind and protect your financial well being. 

Machine learning and debt collection 101

By on January 28th, 2020 in Machine Learning

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. 

Streaming services are able to automatically curate precise recommendations for their viewers, email service providers can more accurately filter and categorize incoming emails, and collection agencies can more effectively contact consumers in debt.

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! 

Figure 1

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). 

Figure 2

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:

  1. Start with a hypothesis that you want to test
  2. Monitor what decisions it is making based on the data available
  3. Introduce new information 
  4. Review how the system operates and what decisions it makes with the newly presented data
  5. Iterate

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. 

4 tips for improving your collections strategy this tax season

By on January 23rd, 2020 in Industry Insights

The 2020 tax season is getting started early this year! The IRS will begin accepting returns for the 2019 tax year as soon as January 27th, but what does this mean for your business? According to the National Retail Federation, in 2018 and 2019, 34% of consumers intended to use their tax refund to pay off debts. With over $142 billion distributed through refunds last year, that leaves us with somewhere around $48 billion dollars directed toward debt payments across the country.

With numbers like that, it’s no surprise that tax season is to debt repayment rates what the winter holiday season is to massive retail sales. Let’s take a look at how you can make good on collecting while it’s on your customers’ minds this season!

Provide flexible payment options

US consumers have racked up over $4 trillion in debt, and that total has been steadily increasing for years. For many consumers, paying off a debt in full or even in the amounts offered can seem insurmountable. This is especially true of consumers that have multiple debts to pay off. 

With a surplus of tax return money burning a hole in their pockets, they have an opportunity to begin to relieve some of their debt pressure. By providing consumers with more flexible payment options, they feel comfortable knowing that they are taking steps toward financial well-being without having to commit their entire refund to a single payment.

In fact, we’ve seen that 60% of consumers that start on a payment plan will pay in full, settle in full, or remain active on that plan once they’ve started it! Getting your foot in the door can make all the difference.

Make yourself accessible

Being able to offer new payment options to consumers is one thing, but getting a hold of them to discuss those options is an entirely different challenge. Traditional collections agencies continue to work on a call and collect system, and they are reaching fewer and fewer consumers. As the number of consumers interested in answering their phones continues to decline, businesses have to consider new contact channels.

Effectively contacting consumers in debt starts with meeting them where they are: online. Your consumers are filing their W-2s, adding up their assets, and managing their incoming returns through tax software and banking apps. By reaching consumers by email, SMS, or even push notifications, you can introduce your payment plan options where they can see it without the pressure of a call from an agent.

Personalize (and humanize) your communication

Great payment options that consumers can afford? Check.

Reaching consumers when and where they are? Check.

Now how do you work to get consumers to follow through if you don’t have an agent on the phone? When a company is selling a product or service, there is a clear distinction between sales and branding. As you ramp up your tax time collection strategy, consider the impact of building trust in your brand rather than pressing consumers to pay right then and there. 

Even the most compelling payment options on the market and the most stellar team of collectors in the industry can’t solve for the fact that your customers may have other debts that they are making a priority. But if they recognize your brand as the one they can communicate with, as the team that understands their struggle, as the team that’s willing to work with them, they’re more likely to pay. Not only that, they’re more likely to work with you again in the future!

Partner with the right team

Many businesses, especially smaller businesses, take responsibility for collecting outstanding balances on their own, but collections is a complex industry from both a tactical and legal perspective. Compliance can be a massive, tangled hurdle for even the most diligent teams to clear. By finding the right debt collection agency to partner with, you can save you and your team the time and resources that would be invested in recovering lost revenue (and navigating the 538 new pages of the CFPB’s collections rules) and focus on what you do best.

Tax season is on its way, and customers want to clean up their debts as much as you want to recover on their delinquent accounts. Providing a compassionate and accessible collections strategy can offer great results for both your company and the consumers you serve, and if you need some back up, make sure you find the right agency for you.

Still looking for a new collection strategy for tax season 2020? You can reach out to our team to get started today!