Maximize Value Across the Entire Customer Lifecycle
CREATING COLLECTIONS SUPERPOWERS:
USING PREDICTIVE ANALYTICS TO MAXIMIZE PAYMENTS & BUILD BRAND-DEFINING EXPERIENCES
PREDICTIVE ANALYTICS IN COLLECTIONS: Maximizing Your Payments and Loyalty Building Superpowers
The phrase “not all heroes wear capes” was first said about collections departments back in 1982…
Ok, so that’s not exactly true, but perhaps it should be. The teams behind your collections strategy, whether it’s collections, risk, or operations personnel, are the unsung heroes of your organization. Why? Because they support your customers through what is perhaps the most stressful part of the customer lifecycle, they turn at-risk customers to ones that are loyal for life, and they recoup money that in turn helps your business keep moving forward.
They may not wear capes, but collections professionals create a brand-defining experience that has the power to take you from villain to hero in the eyes of your customers.
1. Disjointed customer experiences – From reliance on dialers to contact customers to difficulty making sure collections experiences are seamless, challenges caused by disparate systems and legacy technology prevent collections teams from creating experiences that build loyalty. 2. Increasing number of at-risk accounts – Economic uncertainty increases defaults and lowers payments. Without strategies that can automate the identification of high-risk accounts, segment those most likely to pay, and allocate resources to high value-at-risk accounts, collections teams face consistently higher risk of write-offs. 3. Reactive collections strategies – Reacting when accounts go into default limits the impact your collections team can have on losses. Without the ability to identify at-risk accounts early, organizations cannot work with customers to proactively prevent default. 4. Growing loan loss reserves – As economic uncertainty drives increasing defaults, financial organizations are forced to increase loan loss reserves to protect against unrecovered funds. Minimizing recidivism rates and improving collections is essential to keeping loan loss reserves under control. Collections Kryptonite: The Four Key Challenges Your Collections Team Needs to Overcome
1
Predictive Analytics – Taking Your Collections Team From Hero to Superhero Today’s collection team faces a more complex and challenging landscape than ever before. To empower your collections department to increase engagement, build loyalty, and maximize payments you need a technology infrastructure that supports efficiency through automation, and smarter decisions through predictive analytics. To take your collections team from hero to superhero we’ll take a look at actionable ways predictive analytics, supported by technology, can help create more efficient and effective collections strategies that reduce delinquency times, lower write-offs, and minimize loan loss reserves.
1. Proactively Predict Delinquencies
When financial services organizations plan their collections strategies it’s common for collections plays to focus on catching accounts early into the delinquency. They rely on collections teams being able to react quickly to delinquent accounts to help control write offs. Working with delinquent accounts early is essential for the success of all businesses, but by reacting to problems rather than predicting and preventing default issues, financial organizations are missing an opportunity to support clients who are showing the early risk behaviors that lead to missed payments. Ever-evolving technology has opened up the opportunity for financial services organizations to actively monitor accounts for early warning triggers that could signal impending financial trouble, such as increasing line usage, changing payment behavior, decreasing credit scores, decreasing income, etc. Predictive models can be deployed to determine which combination of factors most often lead to customers entering the collections process. Using batch, real-time, or hybrid processing methods, organizations can identify risk early on by using predictive risk scores to show which accounts are most at risk. This allows teams to work with customers and provide resources, such as financial health education or access to auto- enroll tools, to help clients make payments more reliably. By proactively working to reduce the number of customers who enter collections, a business can reduce the collateral needed for loan loss reserves, lower the strain on collections teams, and improve overall efficiency.
2
2. Power Micro Segmentation
Traditional segmentation places debtors into broad buckets that determine treatment strategies. With automated processes and predictive analytics, collections teams are able to split customers into smaller micro-segments, which can then be used to route accounts through optimal next steps. To power micro segmentation, collections and risk teams need to use both internal and external data to give a full picture of a customer’s financial position. A variety of predictive models can be used to power segmentation that take into account factors including willingness to pay, ability to pay, presence on do-not-call or similar lists, and engagement among others.
3. Maximize Resource Effectiveness
Collections efficiency is also a key consideration when segmenting customers and optimizing treatment strategies. Predictive models can be used to allocate resources where they can be most effective. To do this, collections teams need to deploy models that answer the question: What’s the best path forward based on not just the customer but also on resource availability and cost? The optimal output from collections analytics models will be segmentation that empowers maximum resource use and money recouped at the lowest possible cost. Many operational data points can be used to assist segmentation including resource availability, resource effectiveness, even which agents are most likely to convert certain types of accounts from default to good-standing.
4. Optimize Payment/Settlement Offers
Empowering your agents to make the right offer at the right time is an essential part of every collections strategy. To do this agents need to be able to see and analyze all of the data, not just from one specific account but all accounts that have defaulted across the business, to understand when the time is right to make an offer and exactly how much that offer should be.
Expecting agents to be able to access and compute that volume of data to make an educated settlement offer is obviously unrealistic, unless they possess analytics superpowers. Which means that many offers might be ower than they could be, reducing the amount repaid. 3
The solution to this problem is analytics tools that can rapidly gather and analyze data on comparable historical cases to predict the optimal offer. This predictive analytics use case can help agents understand what percentage of debt is normally recovered in similar cases so they can use the information as a benchmark to determine the minimum to accept and highest likely repayment amount. So, for example, instead of potentially accepting an offer of, say, 60% of the balance with very little data, they would have the insights needed to know that the benchmark is actually around the 70% mark and at minimum they should accept 65%. With data to guide agents, your collections team will see incremental increases in settlement amounts, supporting lower write offs and loan loss reserves.
5. Optimize Contact Strategies
To create brand-defining customer experiences, collections teams need to move beyond the automated dialer to power collections strategies. A customer-first approach to collections means engaging with customers at the right time in the right way. Collections experiences need to be cohesive, so customer interactions are streamlined, effective, and as unobtrusive as possible. While many dialers focus on general ‘high success’ times in the day to contact customers, risk and collections teams can implement predictive analytics models that analyze data, such as contact history or account activity, to predict the optimal contact time and method. To implement analytics models to determine the how and when, an organization needs to create a cohesive collections system that brings all relevant information into one place. By providing a source of truth for collections and risk teams, a business can ensure that customer interactions are all documented and accessible and all information can be easily used to inform models. In a time when customers are choosing which debts to prioritize, creating brand experiences that build engagement and customer loyalty is vital for both increasing willingness to pay and improving customer retention. Optimization of contact strategies with do-not-call, email, and contact logic also empowers collections teams to focus high cost contact methods on high value-at-risk accounts, allowing teams to maximize efforts on the areas offering highest returns. Conversely low-cost methods can be triggered for accounts that are most likely to respond to a gentle nudge. Email, text, and voicemail can all be used to encourage self-cure with the ultimate goal of getting customers to enroll in autopay to reduce recidivism rates. 4
6. Prioritize Collections Agencies
When collections strategies fail, predictive collections analytics can still be used to maximize recovery rates. One effective use case for predictive analytics is predicting which collections agency is most likely to recover from a specific account. Models can rapidly analyze historical collections data to determine which agency is has had the most success with similar accounts in the past. Models can also take into account the bandwidth of an agency, number of cases recently sent to each agency, and the likely percentage of a debt each will recover.
Using this information, a collections team can prioritize the allocation of debts to specific agencies based on value-at-risk and other key KPIs in an effort to maximize the amount recovered.
7. Optimize Collections Models
Perhaps the most valuable tool predictive analytics can bring to your team is the ability to optimize collections models. From machine learning models to champion-challenger tests, analytics can help you ask and answer ‘what if’ questions to iterate on and improve your collections models. You can analyze model performance in real-time to get early warning notifications of dips in model performance. You can test new data sources to find ways to improve model accuracy. You can identify and eliminate the strategies that lead to increased recidivism rates. Model optimization helps you create incremental improvements and test new strategies across the entire collections ecosystem, which in turn improves efficiency, increases repayments, and lowers the level of loan loss reserves your organization needs.
5
Powering Predictive Analytics – Supporting Collections Superpowers While many superheroes gain their powers through freak accidents or genetic quirks, your collections and risk teams don’t need seek out radioactive spiders or have been born on a distant planet to implement collections analytics. In fact, building the ecosystem to support predictive analytics is achievable in just a few months.
The teams supporting your collections strategies will need to focus on three key areas:
Data Integration
Data holds the answers to your collections questions, such as is this account high risk? Is this account likely to self-cure? How is this strategy performing? Can we make changes to reduce recidivism? What’s the best way to engage with a specific customer? What’s the best resource to maximize payment on a particular account? What strategies build the most customer loyalty? Data provides both historical and real-time insights that improve the accuracy of your predictive models and in turn the effectiveness of your collections team. Connecting disparate systems and integrating data into your analytics tools is an essential step in implementing collections analytics. This poses a challenge for many organizations, where integrating data sources can often take weeks or months. Choosing an analytics tool that simplifies integration and creates easy access to data rapidly reduces deployment time and empowers a faster return on investment.
Automation
Automating the manual processes that burden collections teams, such as outreach to those likely to self-cure, allows you to focus valuable resources on the tasks that computers can’t handle, such as engaging with and supporting customers. Analytics tools can determine which accounts can be handled through automation and which need human intervention. The same tools can automate the decisioning which places accounts into specific segments, determines next best steps, and initiates contact strategies through dialers, text, and email systems.
6
With the right automation tools, you can automate the entire collections process up to the point where your brand experience and customer-first approach determines that human engagement is the right next step!
Analytics and Decisioning Tools
To power world-class collections strategies, you need to be able to rapidly deploy predictive analytics models and decisioning processes. Implementing, testing, and deploying analytics tools such as predictive and machine learning models, needs to be simple, whatever model language or data science tool you are using. However, for many organizations model deployment is a challenge, often relying on a vendor or development team to recode the model into a language their current system supports. When selecting or building technology to power collections analytics and decisioning, it’s essential that end users are able to test and deploy models in any language, to support collections agility. Collections Analytics: The Cape Your Collections Team Needs to Fly Collections analytics are the superpowers your team needs to fly your customers from at-risk to loyal-for life. With the right technology and a talented risk team to implement world-class predictive analytics and decisioning strategies, empowering your collections department to increase payments and lower write-offs is a goal that’s rapidly achievable. With benefits including increased efficiency, effectiveness, and payments collected, implementing collections analytics is win-win decision that will take your collections organization from hero to brand- building superhero.
7
To find out how Provenir can help your business implement predictive analytics in your collections processes.
Contact us today
8
Page 1 Page 2 Page 3 Page 4 Page 5 Page 6 Page 7 Page 8 Page 9Made with FlippingBook Digital Publishing Software