BLOG

Decision engines, sometimes referred to as decision trees, are software platforms that automate business rules or business decisions – helping you streamline business processes that require decision-making without having to think about it. A decision engine automates these business decisions based on your business needs and the particular criteria the platform’s owner sets out, saving you from manual work and centralizing the decision-making process. 

What does a decision engine need to run? Besides the set of rules (logic), otherwise known as the decisioning workflow, decision engines need data. Lots and lots of data. By accessing and integrating data from multiple sources and applying these ‘rules’ according to your criteria, voila – you can automate decision-making. In the finance world in particular, decision engines are often used to help you make decisions on who to lend to and helps determine which sort of products you can offer your customers.

Automated decision engines can also enable personalized pricing and offers (i.e. finance terms and interest rates), all of which are customizable to your unique needs. Some popular examples in the world of fintech/financial services include: consumer lending, loan origination, credit card approvals, auto financing, point of sale lending like buy now, pay later (BNPL), lending to SMEs, insurance policy approvals, upsell/cross-sell offers, champion/challenger strategies, audits, collections and more.  

Decision engines can help inform various types of business decisions – on everything from basic day-to-day operations to more high-level, strategic business decisions. 

• Strategic Decisions: Strategic decisions are top-level, and tend to be more complex, affecting a much larger portion of the organization and often applicable for a longer term (i.e. changing cost structures or planning for longer-term organizational growth). Decision engines and automated decisioning processes can expedite and streamline various processes, improve efficiency, and allow you to make smarter decisions overall. In the case of financial services, this could mean a shift in deciding who you can lend to in order to expand your overall customer base and plan for growth. Keep in mind that more complex decision execution typically requires a large amount of data, provided from a variety of data sources. Utilizing decision engines and automated decisioning processes can help an organization access, analyze, and action a large variety of data, enabling smarter decision-making.
• Tactical Decisions: Tactical decisions are much more focused on business processes and tend to be shorter-term and less complex. Examples include launching new products, changing product pricing, managing inventory control, and supply chain and logistics. With decision engines, you can more easily analyze performance data and help determine new pricing strategies for your financial services products or look strategically at which demographic or region to target next. 
• Operational Decisions: Focused on day-to-day operations of a business, operational decisions are much smaller in scale. They tend to be related to overall daily production and are usually executed in alignment with the overall strategic vision of an organization. In financial services, decision engines can improve efficiency and help automate or streamline varying day-to-day decisions, including loan approvals, interest rate offers, guidance on collections, merchant onboarding, pricing optimization, compliance processes, identity verification, fraud prevention and more.

So how does a decision engine actually work? And how do decision engines function in a business? While it’s up to each individual organization (and all of the individual business rules within) how they want their business decisions to be executed, there are some basic steps that remain true across the board.

1. Set Desired Outcomes: Look at what your goals are. What are the specific business rules that you need your decision engine or workflows to execute on?
2. Determine Decision Criteria: What are the standards or requirements to which you are making your evaluations or decisions? For example, in the case of many credit applications, particular criteria often include income, job status, age, marital status, debt ratio, etc.
3. Organize Data Sources: To process these business decisions based on your desired outcomes and your determined criteria, what sort of data sources do you need? Do you need traditional credit bureau data, third-party sources, alternative data like rental info, social media presence and web data, etc.?
4. Create Decisioning Workflows: What are the necessary steps in your decisioning process? Use the configuration tools within your decision engine to lay out your workflows and business rules and enable automated decisions.
5. Test and Iterate: Create, test and deploy your modelling scorecards and decisioning process, and look at what happens when a typical customer is put into your system. For example, if a customer applies for a credit card, their information is put into the decision engine, which then pulls in necessary data (identity verification, KYC, income verification, fraud), and rejects or approves based on the initial criteria determined. Is something missing? Can your business process be smoother? Iterate!
6. Determine Next Steps: Where is your threshold for complex applications? Which applications need manual intervention? Straight-through processing enables instant decisions for more simple credit and lending requests, while a rules-driven decisioning process helps to identify and re-route exceptions that require more manual intervention. 
7. Monitor and Optimize: Is your decision engine offering real business value? Keep tabs on your decisioning performance by using the information your decision engine gives you. Identify opportunities for further enhancement of your decisioning process and tools and enable more efficient decisioning – and business growth.

As we’ve shown, there are a large variety of ways that decision engines can help inform business processes. But how exactly does it do that? In the case of financial services, think of all the manual decisions that require human intervention. If an individual needs a car loan, for example, how does a lender determine if that individual is creditworthy or not? And if they are, what interest rate or repayment terms should they be offered? Having an automated decision engine can streamline the application, approval, and funding process to ensure an efficient, superior customer experience. 

In the auto financing example, applications can move from manual, paper-heavy forms, and hours of sitting in a dealership to simplified, online applications. An individual can easily fill out an application and provide ID, which then allows a decision engine to move that person quickly and easily through the decisioning workflow along a series of pre-determined steps, according to the initial criteria.

In this case, that criteria could start with analyzing data for identity verification (is this person really who they say they are? How old are they? Do they have a valid driver’s license?), then move through to various factors that determine creditworthiness. Does this person have an income that is above our threshold? What is their credit score? How much debt does this person already have, and what is their debt-to-income ratio? Do they have previous loan defaults on their record?

As the decision engine automatically accesses and analyzes all the data required according to the business rules, it moves that application through the workflow based on the answers. Driver’s license? Check, on to the next step! Old enough to own a car? You betcha. Have a job? Yep, move along! But then comes a doozy of a credit score and a record of numerous loans having gone to collections. The buck stops here and the decision engine (as per the initial ‘instructions’ when setting out the original workflow) stops the application and determines that this individual is NOT a risk this lender wants to take.

Of course, not all situations are as black and white as that example, but the beauty of automating business processes with a decision engine is that you can streamline and improve efficiency for many situations and types of applicants, while focusing that most precious resource, humans, on the more complex cases that require manual intervention.

Despite all the wonderful ways that business processes can be improved using decision strategies, there can be no automating decision execution without extensive data and data aggregation. Data, preferably varied and from a wide range of data sources (including historical data), is critical to the decision-making process.

All financial services organizations use data to make informed decisions across the customer lifecycle – but having to manually access and integrate data sources is nothing short of a nightmare. Data consumption has evolved, right alongside the decision engines that data feeds into. It’s impossible to make accurate decisions based on business needs without the right data that aligns with the particular criteria set out. Think back to the examples previously discussed – where do you get information on loan payments, credit policies, credit scores, income to debt ratio, age verification, etc.? It’s all about your customer data sources.

These days, more and more lenders are increasingly looking to a wider range of data sources, including alternative data like rental payments, social media interactions, website info, travel data and more, to ensure: 

• A more accurate view of identity verification
• A more holistic view of risk and creditworthiness
• Better fraud prevention

All this data must be accessed, analyzed, and actioned appropriately to help ensure more accurate, automated decisions that provide value to a business. As The Financial Brand said, “Data, by itself, is not a valuable asset. It’s what you do with it that counts.” Having a variety of data available on-demand is essential for enhancing your automated decisioning. Third-party data providers, connected through a centralized platform or marketplace with a single API, can make this data consumption effortless, giving you the ability to access and integrate numerous data sources in minutes. Use that data to test your decisioning workflows, and then iterate and adapt with ease.

The use of artificial intelligence and machine learning is growing. AI in financial services is seen as a $450 billion opportunity. But how can you use AI most effectively in your decision engines? Using AI/ML to power your decisioning process enables:

• Improved decisioning accuracy
• Superior fraud detection
• Enriched customer relationships
• Improved customer satisfaction
• Expanded customer base
• Optimized pricing
• Revenue growth

McKinsey pointed out that “The continuing advances in big data, digital, and analytics are creating fresh opportunities for banks to improve the credit-decisioning models that underpin their lending processes… the banks (and fintech companies) that have put new models in place have already increased revenue, reduced credit-loss rates, and made significant efficiency gains thanks to more precise and automated decisioning.”

It may seem daunting to try to implement AI into your decisioning processes, but you don’t necessarily need data scientists on your team to make AI impactful. With a technology platform that incorporates both data sources and advanced machine learning into your decision engine, you can make use of advanced decisioning – and get all those benefits listed above.

AI allows you to do things that may be challenging for traditional decision engines, including enabling more approvals for unbanked consumers, adapting to rapidly changing market trends and consumer demands without sacrificing the customer experience, and finding relationships in your data (see? Data is king!) that may be otherwise unseeable. If you do happen to be lucky enough to have data scientists in-house and need to figure out a way to utilize all their expertise in your decision engine or business applications, look for a technology partner that can easily migrate existing models into a user-friendly platform.

While we’re talking about data integrations, automated workflows, data scientists, machine learning… why go to all this trouble? There is immense value in using decision engines in financial services instead of manually trying to make complex decisions around your business processes. Some of the benefits include:

• Boosted Performance: make decisions faster and more effectively, enabling optimized business performance
• Increased Profits: lend to more customers, without increasing your risk, allowing for better profit margins
• Improved Efficiency: save time and resources, with fewer human interventions needed and the ability to make decisions faster
• Flexibility: change your decision criteria without having to re-do your entire workflow
• Scalability: easily add more data integrations and new criteria or decision parameters to your workflows as your business grows or the needs of your consumers/the market changes
• Focused Resources: save your underwriters’ attention and manual intervention for more complex cases
• Consistency: ensure consistency and stability in your decision-making processes, enabling enhanced customer relationships and reliability in business performance
• Transparency: get full visibility into what your decision engine is doing and measure performance so you can easily optimize
• Capture information: manual underwriting requires manual information capture – with an automated decision engine you can easily maintain information on your customers, your decisions, and your overall performance, which you can then feed back into your decision engine for further optimization

Also read: The Essential Guide to Credit Underwriting

Customer experience is more critical than ever. In an age of having everything available on demand (tv shows, rides, food delivery, workouts), your consumers expect speed. On top of that, they value customization. We want Netflix to know exactly what kind of show we’re up for next or appreciate when our Facebook feed is filled with ads that resonate. According to PwC, 80% of consumers rank speed as a key buying factor, and Salesforce says that 76% of consumers expect customized offers. Who has time for that if you’re busy making all your business decisions manually?

What does the future hold for decision engines? From our perspective, the prospects are bright. Did you know that Forrester recently added Digital Decisioning Platforms to their Wave report? According to Forrester, Digital Decisioning Platforms (DDP) are “an evolution of expert systems, knowledge-based systems, business rules management systems, and decision management systems.” It’s a mouthful, but it’s clear the trajectory is positive when you automate your business decisions. And with the increased acceptance of artificial intelligence and machine learning, the ways in which we can automate decisions will only get more exciting (and profitable).

For Further Reading:

• Five Key Features for Creating the Optimal Risk Decisioning Ecosystem
• How Decision Trees and Rule Engines Work Together
• The Algorithm Challenge – Using AI for Risk Decisioning
• Automation: Powering More Efficient and Effective Credit Decisions
• What is BaaS? (Banking as a Service)

BLOG

Personalized experiences are everything these days, and the world of financial services is no exception. We expect our Netflix recommendations to be spot on, we download apps to preview what a new hairstyle would look like, and we trust our Instagram feeds to offer up relevant ad content… but some traditional financial services institutions are missing the boat on personalized, meaningful customer experiences. And their growth is suffering as a result. Why? In part, because legacy systems (including data infrastructure and decisioning platforms) just can’t handle making more personalized offerings. To truly enhance the customer experience from end-to-end, financial services institutions, both big and small, need to look to an all-in-one, Financial Brand shares, “No matter what the future brings, financial institutions need to develop a strategy that can recession-proof and future-proof their current business models. The banking industry has a once-in-a-generation opportunity to transform legacy business models to become more competitive and more resilient during economic upheaval. By integrating data, analytics, advanced technologies, automation and an up-skilled workforce, banks and credit unions can become more future-ready and agile in a crisis.” 

So, what exactly does the oft-overused term Customer Experience really mean? And why is it so critical to an organization’s success? Broadly, customer experience is the impression your customers have of your brand and your solutions as they interact with you – at all stages of the buyer’s journey, from first view of an ad or consuming your content all the way through to purchasing, onboarding and renewals. Customer experience matters in everything we as individuals consume – think about how you feel about your favorite grocery store, smartphone, hair products or exercise program (is Peloton actually a cult?). Now think about how you feel about your banking apps, your credit cards, your mortgage company, your last auto financing application. Are those everyday financial transactions memorable (in a good way)? Do you feel seen? Do you feel like your needs are being met in a personalized way?

Consumers want instant answers and tailored offers with their lending/banking experiences, with far less waiting and paperwork. With the rapid increase in digital-only banking and fintech innovations like buy now, pay later (BNPL) and embedded financing apps, providing anything less than a stellar customer experience means fewer repeat customers and a decrease in brand value.

Accenture reports that 5% of traditional banks’ revenue is at risk as millions of consumers are enticed by the transparent, tailored offerings of fintechs and neobanks. A 2020 survey of credit union/bank marketing leaders found that personalized approaches are the most effective for engaging people and expanding share-of-wallet. But 44% of those same organizations only send a couple of targeted marketing emails per year. Why? “Limited data insights make it difficult to truly understand a consumer and what they need in the moment.”

What does your risk decisioning platform have to do with the customer experience? In one word… everything. While some financial institutions are still using siloed environments and separate vendors or partners for data, decisioning workflows, analytics models and business insights, the more agile, adaptable organizations are looking at unified, all-in-one decisioning platforms. One solution that integrates real-time data, advanced analytics, artificial intelligence and machine learning (AI/ML), and decisioning automation can help accelerate digital transformation for a more customer-centric experience. With a unified solution, you can:

• Make smarter, more accurate decisions
• Shorten the product development lifecycle and get new products/offerings to market faster
• See real-time views of decisioning and performance data to uncover actionable business insights
• Create streamlined user experiences across the customer lifecycle
• Scale and grow your business to respond to market trends and consumer demands (with fewer growing pains for your loyal customers along for the ride)
• Democratize data access for more holistic views of your customers
• Optimize pricing and product offerings
• Expand your customer relationships with personalized upsell/cross-sell offers

McKinsey doesn’t hold back: “Predictive customer insight is the future.” Their article on ‘Future of CX’ predictions states that “those with an eye toward the future are boosting their data and analytics capabilities and harnessing predictive insights to connect more closely with their customers, anticipate behaviors, and identify CX issues and opportunities in real time.” While customer success teams and feedback surveys will always have a place in understanding the consumer experience, it’s clear that real, actionable data that can be analyzed in real-time is a game-changer.

But accessing, integrating, and analyzing data is not the only challenge facing financial institutions who desire a better experience for their customers. In today’s ultra-competitive landscape, doing so at speed is critical. As the Financial Brand shares, “Speed is a competitive weapon. The ability to see market trends, adjust strategies, innovate, create new solutions, make tactical decisions, and deploy resources quickly provides a business advantage… Banks and credit unions can no longer respond to opportunities and challenges with a legacy banking timetable.” But being able to adapt your offerings and pivot to new products or strategies quickly is next-to-impossible without an integrated, unified solution.

If you’re overwhelmed by the idea of choosing yet another technology partner, don’t fret. We’ve looked at some key factors to consider when evaluating decisioning platforms.

• No-code Management: Can you easily integrate systems, change processes, and launch new products, without relying heavily on your IT team and/or your technology vendors? Is your team empowered with a low/no-code UI (see, the customer experience matters in absolutely everything!) that can offer you things like pre-built data integrations and drag-and-drop functionality?
• Connected Data: Do you have easy access to both real-time and historical data, including alternative data sources? Can you centralize your data sources (goodbye silos) so users can more efficiently manage various data sets across the credit lifecycle and make smarter decisions?
• Centralized Control Across the Lifecycle: Can you bring together data and decisioning to better manage identity, fraud, and credit decisions across the entire lifecycle of the customer? Are you able to efficiently connect all systems to fully understand customer needs and personalize user experiences? When consumers are expecting seamless experiences, with tailored financial services and protection from fraud, can your technology deliver?
• Auto-Optimization: Does your decisioning platform get more accurate each time decisions are made? Are you able to see how your current risk models are performing, and can you respond to these performance shifts once you’ve spotted them? Instead of relying on humans or individual systems to uncover opportunities for improvements, can you connect all systems and power a continuous feedback loop that keeps optimizing your decisions?
• Ability to Scale: Your systems may be working well enough for now, but as the industry continues to grow more and more competitive… can they adapt and scale with you in the future? Does your decisioning solution simplify your growth or inhibit it?

A unified decisioning platform not only powers more accurate decisions across the entire customer journey, but it enables rapid growth and innovation opportunities. Instead of waiting for vendors to make workflow changes or sifting through siloed sets of data, you can spend more time focusing on what matters – your customers. Adapt as the market shifts, diversify to meet your customers’ needs, personalize offers to encourage engagement and brand loyalty. The opportunities for enhancing the customer experience are endless – and with a holistic, unified view of your data and decisioning, you don’t have to compromise your risk strategy to do so.

Ready to get smarter?

BLOG

We spoke to YapStone, a payment platform taking the world by storm, and asked them how their new credit decisioning model has helped expand their company at a rapid rate, on a global scale. Through advanced analytics, model development has taken place quickly and effectively for YapStone. Here, they talk us through how credit scoring, open banking data, and credit risk models have facilitated their growth, allowing them to sit amongst industry leaders.

In a time when virtually anyone can sell goods or services on the internet, real-time merchant onboarding and risk and fraud monitoring capabilities have become imperative.

At YapStone, we know this very keenly because the bulk of our users are not simply selling products to strangers they will never meet – they are inviting consumers into their homes.

Twenty years ago, we couldn’t have imagined we’d be comfortable inviting complete strangers to stay in our home for extra income, but thanks to vacation rental marketplaces like HomeAway, Airbnb, and Kigo, “living like a local” has become the preferred way to travel. As a result of this undeniable trend, YapStone now processes about $18 billion (and growing) in electronic peer-to-peer transactions every year.

Further challenges to marketplaces are emerging with the rise of Alternative Payment Methods (APMs). Consumers in different countries or regions have their APMs of choice, using them to pay securely with their local currency. As the payment partner, we have to ensure that these methods suit our customer’s lifestyle, and that they can securely pay using their preferred payment methods in their local currency, while sellers receive the funds seamlessly in their local currency.

YapStone has been able to capitalize on the growth of apartment and vacation rentals, where the average ticket size is large and the risk is high, by developing proprietary technology focused on reducing the risk of fraud and loss to our marketplace partners. YapStone’s trust and safety solutions are highly flexible and designed to service all marketplace types, allowing us to diversify our portfolio and grow our business beyond apartment and vacation rental marketplaces.

YapStone is unique in that we offer a full service, end-to-end payments acceptance, customer service, and risk management solution, including instant and advanced payments, to our marketplace partners.  Therefore, it is a necessity for YapStone to verify the traveler and authorize their payment method, as well as verify the vacation property’s existence and ownership. Our goal is to deliver trust and safety to our marketplace partners, allowing them to spend more time focused on growing their business, while leaving risk management to the expert team at YapStone.

YapStone uses a layered, risk-based approach focused on the persona of any particular client interaction.  Within the persona, we are continuously monitoring the purchaser of the good or service, the payment instrument being presented, and the asset or property they are renting.  To accomplish this, YapStone utilizes proprietary data science and predictive analytics augmented with 3rd party data to achieve the most accurate risk scoring.

Given our scale, and the risk associated with high average tickets and the speed at which fraud can happen, it was critical for us to choose a tool that allows a risk analyst to react quickly to an escalating threat.

In 2017, we selected Provenir as a key strategic partner in the development of YapStone’s next-generation risk decisioning platform. The tool provides the ability to house our proprietary underwriting and fraud models, serve as the hub for our third-party risk vendor integrations delivering powerful adapters to augment our proprietary risk methodologies and data, and conduct A/B and regression testing for new or proposed model changes, all delivered through a simplified user interface that doesn’t require a PhD in computer science to use.

We maintain a highly competitive edge over other payment facilitators because of the way we mitigate risk for our marketplace partners and assume the liability for each transaction. Using our proprietary technology in partnership with Provenir, YapStone is able to provide marketplaces with high levels of automation for merchant onboarding and risk management aimed at improving speed to revenue and reducing losses for our clients.

We have a very exciting future ahead of us, made particularly bright by having partners like Provenir who help us deliver innovative solutions to our existing customers and new faces. As we expand into new territories, the demand for innovation in risk decisioning will be high. The team at YapStone looks forward to staying on the forefront of this new wave of marketplace payments.

Companies invest lots of time and money developing risk models to figure out which  customers are the best bets for loans and credit, including auto lending, mortgages, credit cards, BNPL and more.

Operationalizing these models,  developed in tools like Excel, SAS, Python, and R, within risk decisioning processes often turns out to be challenging. This is especially true with complex models built in R. Lots of risk decisioning ‘solutions’ demand that you manually translate the R model (or any other model that you are using) into code that it can understand. You need high-priced programming resources and lots of time to connect the R model to the risk decisioning process.

It’s much more efficient to use a risk decisioning solutions which are model-agnostic – in other words, a solution that doesn’t care how the model is constructed. Provenir’s AI-Powered Decisioning Platform is a great example of this model-agnostic approach. With this platform, models developed in a variety of tools can easily be imported, mapped, tested and validated using simple wizards.

Provenir automatically generates a list of the data fields; all users have to do is pick the data Provenir needs to send to the model, as well as the data the model should send back to Provenir to drive the decisioning. This entire process takes just a few minutes, which means you not only gain an effective way to maximize the value of your models, but can also instantly adapt risk decisioning processes whenever a model changes.  Automating your risk decisioning not only saves you time and money – it improves your decisioning accuracy and allows you to focus your resources on growing and scaling your business.

What is a decision engine and how does it help your business processes?