A more intelligent approach to debt collection with machine learning and AI

Machine learning can help fintech lenders, retail banks, financial services firms and collection agencies make debt recovery more effective, maximize ROI and improve customer satisfaction metrics.

Lending has always been risky business, what with delinquencies, defaulting and inefficiencies that come with it. But it is heading into even more choppy waters. Global consumer debt is estimated to be a whopping $46 trillion and the collection success rate in many geographies is alarmingly low. In the US alone, $600 billion of household debt is considered delinquent.

Considering the size of outstanding debt, even a small percentage improvement in debt collection numbers can majorly impact the profitability of lenders. With the Big Data revolution, machine learning and AI can be leveraged to improve recovery, while also addressing some of the other challenges that lenders face.

Some challenges faced in debt recovery

#1 Balancing efficiency with customer experience

Customers today have high service expectations from lenders. Even seemingly small efforts such as responsiveness on social media and personalized communication can make a big impact on how customers perceive the lender’s brand. These may even determine their loyalty to it.

Thus, it is important that the lender is able to offer a consistently delightful experience to the customer across their journey. In reality, however, a poor collection experience often ends up leaving the customer unhappy or angry, irrespective of how pleasant their origination or support experience has been. This can have a major impact on the brand perception and undermine the investments put into customer acquisition.

#2 One-size-fits-all communication methods

While the size of outstanding debts varies, not all defaulters have the same profile, behavior or motivation factors. However, lenders and collection agents often follow a cookie cutter approach in their communication: a stern and matter-of-fact tone, firmly worded messaging. This one-size-fits-all approach can negatively impact recovery because it may intimidate or anger customers even further.

#3 Abuse of collection practices

According to this CFPB Survey, one out of every four US customers contacted by debt collectors reported that they felt threatened. Nearly 40% of them were contacted more than 4 times a week by collectors, often at inconvenient times. And three out of four customers reported that in spite of requests to stop calling, collectors continued to do so.

With regulations also not always clear on the number and frequency of collection calls and how collectors may use voicemail, emails and texts, the customers are left at the receiving end of abuse from collection agents; but the brunt of their frustration and anger is borne by the lender’s brand.

Innovations in debt collection with AI and ML

With digitization, lenders — both traditional banks and financial services companies — have access to a lot of valuable customer data. This data can be analyzed with the help of AI and ML-powered tools to derive insights that open new doors to the optimization of collections, increased recovery and profitability, and customer satisfaction. AI and ML find application in four main areas in debt recovery.

Prediction of customer delinquency

The AI tool analyzes hundreds of parameters from FICO score and income to history and borrower’s behavior through the journey. Knowing who is likely to default will forewarn, and thus forearm, the lender. And allow them to formulate pre-emptive strategies for recovery. Edgeverve’s AI-powered FinXEdge Collect solution, for instance, evaluates internal transaction data (loan details, credit score, income, etc), external factors (weather, job data, GDP, micro and macro-economic events) and behavioral influencers (voice data, demographics and call notes) to predict delinquencies and recommend proactive outreach strategies for high risk customers.

Segmentation of borrower risk

This helps direct collection efforts towards the customers who are not only at risk of defaulting but also most likely to pay their debt. Much of debt collection effort is still manual with follow-up calls, emails and other forms of reach out done at an individual level. AI tools like FinXEdge Collect help improve process efficiencies, productivity and compliance through intelligent segmentation and prioritization of accounts along with prime-time recommendations for reach out.

Personalized communication

The aim here is to bring back the human element into the debt recovery process and thereby, improve customer response. Certain communication channels work best for certain kinds of customers. Machine learning tools can help:

Tailored recovery/settlement proposals

In most conventional collection practices, the decision on what recovery or settlement terms to propose to a customer was mostly left to the instinct and experience of the debt collectors, with loose guidelines in place. Machine learning tools can actually bring method to this madness. They leverage data to identify different customer profiles: those who are in a temporary state of hardship but who can and are likely to settle debts later versus those who plan on defaulting or have no intent to settle. These tools can also recommend the right settlement terms to propose to each of these customer types.

If you are a financial institution with a customer-centric approach wanting to leverage customer data to improve debt recovery and enhance customer experience, FinXEdge Collect may be just right for you. Find out more and request a meeting here.

Here’s How AI Can Help Credit Unions Transform Their Debt Collection Practice

Credit unions are the new favorite of the borrowers with their membership seeing a whopping 1.1% increase in the first quarter of 2019* in US alone. However, this has also led to the increase in delinquencies, pulling credit unions back and forth in their growth journey.

As the banking landscape changes with the evolution of technology and customer expectations, it requires credit unions also to evolve in order to grow and stay relevant. Apart from developing new methods of interaction, this also requires the credit unions to evolve their collection strategies. To be able to transform their collections operations, credit unions need to make the processes more intelligent and at the same time focus on providing a great experience to their customers.

How do they go about their collections now?

Traditional recovery methods are still favored upon by collections teams, leaving an stale experience for both the members as well as the credit unions due to not keeping up with the trends in customer behaviors and expectations. In many cases, aggressive collection strategies have also hampered the relationship with the members resulting in severe legal implications.

What if the credit unions could identify and mitigate risks? Today, there are ways to leverage predictive analytics to know if a member would turn delinquent or not. With growing business needs, challenging economic conditions and ever-evolving borrower’s profile, you need something which can dig deep into the data and provide you with insights that can help devise flawless strategies. This is where artificial intelligence makes its grand entry.

How can AI help?

While AI and its capabilities such as ML and NLP have been leading the digital transformation for financial institutions for long now, debt collection is a relatively new area where AI hasn’t been explored much, It can however empower credit unions with its intelligent predictions and recommendations, which can help reduce risks.

AI and ML can transform the debt collection practice for credit unions in majorly two ways. One – by embedding intelligence into their collection strategies and two – by enhancing contact strategies through intelligence.

AI can help in segmenting the customers better by identifying patterns and behavior thereby empowering credit unions to recognize customers at risk of going delinquent versus non-delinquent. This helps target the right members to follow-up for debt collection, thereby ensuring smooth experience for those who pay on time. Accurate customer risk segmentation achieved with the help of AI helps financial organizations enhance customer experience with personalized collection and communication strategies. For instance, reducing outreach plans or call investments for low-risk customers will help save costs and ensure better experience. Similarly, for mid-risk customers, prioritization can be based on value at risk, call value and risk scores. For high risk customers, trying an early loss mitigation plan will help.

Why is AI still a far-fetched idea?

While it does have a lot of benefits, when an organization implements AI into its process, it is easier said than done. Credit Unions adopting these new technologies face a lot of challenges including the complexity of integrating AI application with existing infrastructure, lack of knowledge about AI/ML technology, lack of proven record of AI/ML initiatives and concerns with data quality and security. There are also many myths surrounding the implementation of AI with regards to data transfer, security and transition from old systems to new, which stop credit unions from going completely digital. Not to forget the additional woes of training, which is required to understand the digital aspects to overcome rising organizational challenges during implementation.

Amidst so much doubts and fears, there is definitely a need for a solution, which can intelligently drive the collection strategies, at a reasonable cost, while enhancing customer experience and reducing operational challenges. Also, the solution should be easy to understand, implement, secure and compatible with the existing systems, and which can help derive the desired outcome in just a few weeks.

One such solution with FinXEdge Collect, which leverages credit history, customer behavioral scores and macroeconomic factors for an accurate segmentation and prioritization of delinquent accounts. A unique and effective solution, which can accurately identify customers in different risk categories early in the cycle and follow up by creating personalized resolution strategies, considering the financial disposition and behavioral aspects of the borrower. FinXEdge can be synced with existing core collection systems and does not require additional resources for training. This works for credit unions – as they can avoid changing their existing systems and training their resources. Factors such as easy implementation and faster time-to-market, unbiased data model, unified view of customer accounts and audit ability for regulatory purposes make FinXEdge the ideal choice for companies concerned about growth and value cycles.

Interested in learning more? Click here to download a detailed thought paper on ‘How can Credit Unions transform debt collections by leveraging AI’

You can also click here connect with our experts to understand how you can leverage FinXEdge Collect for your enterprise.

What do Enterprise Personal Bots (EPB) mean & how do they work?

In this second article in the personal bots series, we will extend the concept of personal bots to the enterprise scenario. In the last article, we focused on how personal bots triggered on-demand can perform tasks on behalf of the employee, even in his/her absence.

While personal bots can automate any task (personal or official), in a corporate setup, controlled distribution of personal bots to automate repetitive official tasks can yield desired benefits. Organizations usually have set procedures for their employees to follow or to execute standard tasks for each role. The same set processes can be codified through the automations and distributed as personal bots, to be utilized by employees as and when they need. This version of personal bots, where the enterprise controls the definition, configuration, and distribution of bots and execution of bots, occurs on an individual employee’s machine on-demand is called EPB or Enterprise Personal Bots.

How do Enterprise Personal Bots add value?

As organizations grow, their internal processes become complex, primarily because tasks get distributed across groups, and multiple hand-overs happen. Business complexities also add to these process complexities. To keep pace with market changes, often, the internal processes and applications are “patched up” on-the-go, resulting in inefficient and not-so-user-friendly enterprise applications. Pretty soon, employees across the organization are performing repetitive tasks, copying and pasting data from one application to another, exchanging data over excel even though apps exist, and extracting data from documents. This process takes up considerable time and effort of the employees and takes away their focus from creative value-added tasks. From a human resources point of view, it promotes a culture of mediocracy, where mastery in such repetitive tasks becomes critical.

Enterprise Personal Bots come handy in this situation. It can automate tasks that are now repetitive and don’t add any significant value. It will free up employees from mundane tasks, allowing them to work on tasks that require creative decision making and improving customer experience. From an employee satisfaction perspective, it will be a huge boon as the frustrations of inefficient processes and enterprise apps are reduced.

How do Enterprise Personal Bots work?

Enterprise Personal Bots work with a centralized configuration and distributed execution model, which means that the bots are pre-configured centrally, by subject matter experts. Individuals in the organization playing various roles, including Project Manager, Accountant, or Recruiter, typically identify tasks for automation. Tasks executed by each role are analyzed in detail to identify repetitive activities that take considerable time but require little decision making. Such tasks are then standardized by creating templates for Inputs, Outputs, and any intermediate human intervention. The remaining part of the task is automated using RPA.

These pre-configured bots are then deployed (using the organization’s existing SMS push or another mechanism) on an individual employee’s machine of that specific role. Employees for each role then trigger these bots as and when needed, with their credentials and inputs. They can continue to do other work, while the bots perform the tasks and alert once done. Centrally, the bot execution and effort savings can be monitored on the dashboard.

Thus, the Enterprise Personal Bots combine the power of attended automation and personalization of bots with the control and discipline of the organization. They have the potential to free up significant time and effort of the employees, unleashing the true human potential of the workforce.

As with any technology, EPB come with their nuances and challenges. In the next few posts, we will examine the Enterprise Personal Bots from different dimensions of Security, Governance, Monitoring, and Licensing.