Nicolas Gonatas, Beam’s co-founder and Head of Data Science, talks about Beam’s data science philosophy. This post is a follow-up to our series of articles on Beam’s Data Science Philosophy’ and Machine Learning Principles.

What kind of data sources and variables do you consider the most critical for training your machine learning models. How do you ensure data quality and relevance?

The way traditional bureaus source data for their reports and scorecards is through the SACCRA Hub. Every lender in SA has to report its loans and borrower repayment data, by regulation, to the SACCRA Hub. SACCRA generates reports on whether customers are making repayments, and how much of their credit limit they have used. There are however inaccuracies or errors that creep in, called blemishes in the data, which can become problematic. Although bureaus have done a lot of work to fix these issues, the data they use for scorecard building is still not perfect. 

Beam on the other hand connects directly to an applicant’s bank account, accessing user-generated financial data. By obtaining information directly from the bank, we can protect lenders against various types of fraud or manual tampering of PDF statements, it also enables real-time data transmission to lenders with 100% transparency. We see this as important, as the bank statements represent a “truth file” of a user’s spend behaviour and financial position. The user is ultimately giving us permission to analyse their financial position in the most transparent way possible.

What challenges have you encountered in incorporating AI techniques into credit rating and how have you addressed them?

Our biggest challenge over the past six months has been accessing enough data.

The way machine learning works is by learning generalised patterns across large data sets. Algorithms learn these patterns through observing causal relationships across many input and target variables. These patterns become more refined as the dataset grows, allowing models to make accurate predictions across diverse population groups.

A major risk with limited data is model bias, which can arise from various sources including the dataset’s size, collection methods, and inherent historical biases. For instance, a model trained on data from a specific income group, or LSM, would likely develop biases towards that group’s financial behaviours. This results in poor performance when predicting financial behaviours of a lower LSM group due to incorrect associations learned between inputs and outputs.

To combat these challenges, we’ve employed several strategies. Beyond striving for larger datasets, we address data bias and overfitting through techniques such as data augmentation and transfer learning. We also diversify our data sources to ensure our models are trained on datasets that reflect a wide range of demographics and financial behaviours, thereby making our AI models more inclusive and fair.

How do you balance the need for predictive accuracy with the interpretability of AI models, especially in highly regulated Industries?

We ensure both accuracy and interpretability through a battery of tests. These tests are numerous, but are largely either model-specific or model-agnostic. Model-specific methods are tailored to specific types of models, taking advantage of their internal mechanisms and structures. These methods are designed to provide insights into how the model processes inputs to arrive at outputs. 

Model-agnostic methods on the other hand are designed to work with any machine learning model, providing more flexibility. These methods don’t rely on the internal workings of the models, making them more widely applicable and generalisable across various models we test.

This is important, since this allows us to use complex (and thus unexplainable) algorithms (like neural nets), which give us the best performance, and still understand how a final decision is made, across populations, sub-groups or even individual users. This helps steer model development but also ensures we’re not having a disparate impact on the credit decisions of various demographic sub-populations – more simply put – fighting bias.

We use these interpretability techniques, combined with a host of other tools that allow us to fight the risks that may arise from automated decision-making. We collectively call this our “Model Risk Management” framework, and we apply it to all of our machine learning pipelines, ensuring that we get accurate results and that we are following interpretability and broader compliance best practices.

What role do you envision artificial intelligence and machine learning playing in the future of credit vetting and what innovations do you anticipate in this space?

Since the 1980’s, credit scoring at scale has been machine learning driven. The existing scorecards bureaus use are technically machine learning-driven, however they are largely rule-driven and use lots of hand-crafting. Now with the advent and acceleration of big data, novel algorithms and more compute we can unlock new methodologies that weren’t possible previously – being end-to-end “learned”. 

Ultimately, innovation in the credit vetting space will only keep accelerating and the whole industry will see exponential value being added to our vetting capabilities over the next five to ten years.

How is Beam’s approach to credit vetting different to that of traditional credit vetters?

Traditional credit scoring has been somewhat exclusionary, or rather disempowering of people. Consumers have no understanding or influence of their traditional bureau credit score, including whether the data used to evaluate them was accurate or outdated. Beam empowers users to use their own financial data to create a credit profile, whereas before that was completely in the lenders, banks and bureau’s hands. Providers like us are empowering customers to take control of their own financial destinies, providing them with the tools and knowledge they need to improve their financial position in the long run. 

Does Beam reduce exposure to bank statement or transaction fraud?

Processing PDF bank statements opens lenders up to various degrees of fraud. In many instances, customers add fake salary lines or alter transaction data. By using Beam’s automated bank linking technology, we can drastically reduce the risk of declining credit based on fraudulent information. This is because one would physically have to swipe their card and transfer money around to create fake transactions, adding a financial and unscalable time cost to committing fraud. Since it’s now manual and not cost-free, Beam reduces risk for lenders. 

Furthermore, there’s a built-in KYC element to using our automated bank linking technology. We’ve implemented a host of best practices in fraud management, including ID Verification, Anti Money-Laundering and various other Home Affairs checks. In addition, as we collect more and more data, our machine learning models will be able to identify patterns of fraudulent transactions and start to see what an anomaly bank account will look like, ultimately protecting lenders. 

Summary

At Beam, our machine learning and data science approach focuses on analysing granular bank transaction data in real-time, providing a more precise way to assess an applicant’s current financial situation. This approach is designed to build on traditional credit scoring methods to overcome conventional credit bureaus’ reliance on lagged and sometimes inaccurate information. 

We adopt non-parametric approaches to modelling, leveraging abundant data, increased compute power and evolving architectures, particularly deep learning. We believe it’s important to provide better transparency and include user permission in accessing financial data, so that we can empower individuals in managing their financial profiles. 

To conclude, our data science philosophy and machine learning principles reflect our commitment to innovation and inclusivity in reshaping credit vetting practices, ultimately empowering consumers and mitigating risks for lenders.

This post is a follow-up to our previous post ‘Beam’s Data Science Philosophy’ where Nic talks about Beam’s data science philosophy. In this blog, Nic discusses Beam’s Modelling and Data principles.

What is Beam’s approach to machine learning?

Beam’s philosophy on data science and risk modelling centres on the premise that the advent of machine learning, the significant increase in data generation and computing power over the last two decades have set the stage for a fundamental shift away from traditional credit scoring methods.

Is this an industry standard way of modelling data or is your approach different?

I think Beam is different across two key dimensions, number one being modelling. The way we’re modelling the data is different and modern. If you look at the traditional credit bureaus for example (and maybe this is oversimplifying because we should definitely give them credit) what they do is they use high-level, overly simplistic features about a person to infer credit risk. What do those look like? Typically, these are demographic features, credit account history, how long you have had your various bank accounts open, where you live (using a postal code as a proxy), your education status, an estimate of how much money you make as well as a few other features. 

Further, your typical consumer credit reports and credit scores also use lagged variables, sometimes carrying errors that go unnoticed. For example, your current employment could be out of date or you could have repaid an account that is showing on the credit report as unpaid since it can take up to six months for that information to be reported to a credit bureau.

We actually also use these features since they provide great signal (and in many cases we will combine features and models), but primarily what we’re using in Beam is data coming from bank statements. We analyse bank transaction data at a much more granular level in order to get much richer insight. By doing this, we get a much more up-to-date and thorough picture about a person’s financial behaviour.

Another reason why Beam is an improvement is that we’ve built our platform to keep our users’ data up to date. We can re-score you every hour, day, week or month. Every time you connect to Beam and share your bank account data, we analyse it in real time to the very last transaction you did – even if it was 30 minutes ago, so that’s really the difference.

Is there a proprietary element to this approach where you do this in a way that another company or player wouldn’t have thought to do it or is yours an industry standard approach?

The underlying model architectures we use are completely commoditized. Similar to how GitHub works, where anyone can view, download and use open source code, there’s the equivalent with machine learning models. So for most of our Data Science workflows, the base models and their architectures are open source, so by definition non-proprietary. I’d say that the three key proprietary pieces of our stack are 1) the particular data sources we use, 2) how we use this data and 3) how we merge together our modeling stack with the rest of our product stack. 

You’ve spoken a lot about using alternative data to predict the likelihood that someone will pay back a loan. Is the fact that you’re using alternative data as well as traditional data plus applying these specific risk principles and algorithms a “secret sauce”? 

The general principle with any kind of machine learning is the more data the better. We’re not just disregarding the traditional credit scoring methods that the current bureaus are using. We’ll combine the two together because the reality is that the traditional scoring methods have actually worked pretty well up to now.

If you look at the Actuarial space, we use modelling practices that are 100 years old. At Wits we learned statistical principles that haven’t changed for 200 years. I’ve always believed that we stand on the shoulders of giants – in an academic sense – and we should respect the discoveries they’ve left us. We would be remiss to completely disregard that and think that there’s nothing to be learned from them. I think if you adopt these actuarial risk principles, combined with modern-day compute and modelling technologies – you’ll get the best results. 

Now to answer your question, the cash flow data part of what Beam does is quite important if you think of the way traditional credit scoring is done by the bureaus. Basically, you need to be “credit active”, in other words, have an existing credit product in order to be scored. As you can imagine, this poses a chicken-and-egg problem for those that are financially excluded, as they are declined credit since they can’t be scored (deemed “thin file customers”) but can’t access the credit product to start building up a repayment history.

What we are doing is we’re learning the mapping between a completely independent data source – bank statement data – and credit outcomes. This is fundamentally more inclusive since ~90% of South Africans have bank accounts. In contrast, some estimates gauge that up to a third of South Africans are “thin file customers” and thus can’t get access to credit.

This being said, all of the data we get access to is user-permissioned, meaning that customers opt-in to sharing their data with us. Most South Africans aren’t aware of the fact that their bank transaction data is actually their property and they have the power and right to share this data with third party service providers like Beam for better and more fair access to financial services. This plays on our core thesis as a business, being that Open Banking and Open Finance can be a huge enabler for the average person, but more on that in another post.

We interviewed Beam’s co-founder and Head of Data Science, Nicolas Gonatas, to unpack his philosophy around building the Beam risk engine.

Nic, tell us about your background.

After graduating from the University of the Witwatersrand with a BSc in Actuarial Science in 2019, I joined PwC as an Actuarial Analyst working across several sectors including Life, Health and Short-term Insurance, Banking and Financial Instrument Valuation. I later moved into the Data Science team since I had a coding background and was somewhat proficient in Python. This move started when I was posted to a team that was tasked with translating actuarial models into Python code in order to better scale up and handle vast amounts of data. We then started to just build our own models from the ground up, and that’s pretty much data science. I worked on that for around two years, ending up managing the team. We consulted to the large Telcos and Banks, building machine learning and risk models – essentially data science within the Actuarial space. Shortly after, I co-founded PYGIO, a software engineering company with Dimitri and Ronnie, where we joined forces with Tim and Adam on Beam. 

What is your role at Beam?

I’m a co-founder of Beam and my role is Head of Data Science, so I look at data, seeing what we require and using novel techniques and modelling practices to predict and manage risk better.

What is your approach or philosophy around data science and risk modelling?

Our core thesis at Beam is that the world has fundamentally changed and that there’s an opportunity to move away from traditional credit scoring methods that use parametric approaches. In this approach, you make assumptions that data follows a particular distribution, together with a series of simplifying assumptions to make a limited class of statistical models make predictions. This approach contrasts with non-parametric methods, which do not assume a specific form for the underlying distribution and are more flexible in adapting to the data’s shape – we subscribe to the latter methodology at Beam.

There are three secular trends driving what’s happened in the last 20 years of machine learning advances. Number one is data. As I’ve said before, there’s more data being generated today than ever before. Think of the footprint one leaves with their bank transaction (think credit card) data, whereas previously it was all cash and was thus untracked. Not to mention the data being generated by one’s internet and social media footprint!

The second piece is compute power. If you look at Moore’s Law, it refers to how exponential growth is at the heart of the rapid increase of computing capabilities. The law was first described by Gordon E. Moore, the co-founder of Intel, in 1965 and it was the observation that the number of transistors on computer chips doubles approximately every two years.

Nic and I studied Actuarial Science at Wits and a mutual friend introduced us to Tim and Adam, who come from entrepreneurial and start-up backgrounds, having successfully built their own tech start-up over the last 6 years, which is now a mature business. We had a lot in common as we’d all been involved in starting and building successful businesses in the software and mobile telecoms spaces and we had experience building and scaling software-based products. So we knew each other socially, and in 2022 we went out for a steak at The Grillhouse and we were discussing the various changes that were happening in our lives as young professionals. Everyone was in a place where they were looking at houses to buy or rent, hoping to buy a new car and trying to apply for credit. At the dinner I shared a story that had happened to me that week and it led to a discussion that resonated with all of us.

A few years ago we started Pygio, a software development business specialising in custom builds and data analytics. By 2023 we were growing steadily and the time had come where I needed a new laptop. So I went to the iStore on Sandton Drive. I had enough savings to buy a new laptop but it was quite an expensive laptop (around R60 000) but, you know, I live on my machine and my machine is my work so getting this upgrade for work was quite important to me. And I really needed this laptop. What happened was I’d asked to get it on credit as I’d heard that the iStore on Alice Lane offered financing through Vodacom. That meant I’d buy the machine and get a Vodacom data package, and I thought, “Why not? I’d rather spend R2,500 or R3,000 a month and pay off this machine over 24 months”, than fork out R60 000 or R 70 000 once off which would hurt my cash flow for the month.

So I thought, “Why not?” I’ve never taken out any credit before, I’ve never had any debt or a credit card, I’ve never had a mortgage. I live at home with my parents (which is great) so I never had a rental property and I bought my car cash with some savings from work. I went through the whole process of applying for credit for this laptop from the iStore and Vodacom. It was a whole process of getting together every possible document in order to prove my creditworthiness – my parents birth certificates, my blood samples, my stool sample, whatever, I gave them everything. It was quite a long process and it took about a week. After going to the store and understanding what I had to provide (bank statements etc.) eventually they came back and told me my credit application was rejected. This didn’t make sense to me at all, but what I later realised is that it was because I was what is known in the industry as a ‘thin file customer.’ But essentially the message from them was, “You’re unlendable.” So for me personally, there was a massive pain point. I ended up buying the laptop using savings, which I didn’t want to do.

The following week I was out to dinner with Nicolas, Tim and Adam and Tim shared his story, which was that he was looking to move out of a rental and perhaps buy a house. He was looking at the options between buying and renting and while going through the process of applying for a rental, very quickly realised that he was also thin-file from a credit bureau point of view which made it difficult for the landlord to accurately risk-rate him. So he also got rejected and was forced back into the rental market. Anyway, we connected over these stories and it occurred to us that we’re not the type of people that are high credit risk, or at least we didn’t perceive ourselves to be. We were cash flow positive. We had stable incomes. We saved more than what we spent on a month to month basis.

“Why was it that neither of us could access credit for reasonable things?”

So we started looking deeper into this problem. And what we uncovered was that we were both ‘thin-file customers.’ And the way we did that was we went and found our credit scores on clearscore.com. We downloaded our credit profile and we were both -1. We thought, “What does -1 mean?” Usually credit scores for lendable consumers are around 750 or 700, but “-1” means that the credit bureau has no data on you. This means that they have no way of telling (based on the information they have) what type of risk you might be. If you’ve never had a credit product, no lender would have ever reported your data to a credit bureau. This catch-22 is part of the problem. 

“It’s a chicken and egg situation: if you don’t have a credit score you can’t get credit, and if you don’t have credit you don’t have a credit score.”

We started doing research around the problem and the market. Some of the questions that came to mind were “I wonder who is solving this?” and “Are there companies that help young people like us (or thin file customers) get credit?” We started thinking about what would need to happen for people to have better access to credit. At this point we had started asking people in our circle who were at a similar life stage whether they had experienced the same problem. The feedback overwhelmingly validated our hypothesis: that getting credit if you have no credit score is a big problem, and no-one is solving it well. 

A Founder’s Perspective: Q&A session with Timothy Strike, Chief Product Officer at Beam South Africa

1. Can you provide a brief overview of your startup and the product or service it offers? 

At Beam, we’re leading the charge in transforming how individuals apply for and manage credit. Our goal is to foster an ecosystem that strengthens connections between lenders and borrowers, unlocking financial opportunities and driving upward mobility. We achieve this by building platforms that share up-to-date, high fidelity and consumer-permissioned data.

2. In a crowded market, what sets your product apart and makes it disruptive? How does it address a gap or pain point that existing solutions might overlook?

We are committed to ensuring a seamless implementation of the product for our customers. We adapt our offering to the needs of each customer, thus reducing the risk associated with the introduction of our technology.

3. What challenges did you encounter while developing your product, and how did you overcome them? Were there any pivotal moments that shaped the direction of your startup?

We take pride in developing systems that are both high performing and highly reliable. As an organisation driven by engineering and product excellence, we face challenges daily related to user experience, usability and engineering decisions. We have implemented a robust monitoring toolset to ensure that we can deal with dependencies as and when they arise.

4. How does your product challenge the status quo in your industry?

Our thesis for optimising risk rating in credit applications is based on a person’s:

1. Propensity to repay debt
2. Their ability to pay debt

In order to achieve this we deploy a technique called “cash-flow underwriting” which looks at the affordability and transactional behaviour of an applicant. 

We have also spent a lot of time and effort to enhance the overall product experience and design, ensuring that it is both intuitive and trustworthy  Every decision we make is aligned with these objectives, providing a refreshing and satisfying experience for our users and customers  From a feature perspective, we offer the ability to connect multiple accounts, categorise transactions and identify risky behaviour buried within bank statement. All of this is fed into our machine learning engine to provide forward looking projections and insights. 

5. What was the initial spark or idea that led to the creation of your startup? How has this idea evolved since the inception of your company?

The idea for Beam originated from a thought experiment focused on applying a technical and machine learning driven approach to the underserved credit market. This discussion emerged in response to the data published by the regulatory body, which ultimately led to us developing an MVP, the response from stakeholders in the industry revealed that such an approach had not yet been fully explored in the space.

6. How do you envision your product changing the way people or businesses operate in the long term? What impact do you hope it will have on the industry as a whole?

Our goal as a company is straightforward: to enhance people’s financial well-being by expanding their credit opportunities and aiding in assisting them in managing their obligations. Our aim is to offer reassurance to those feeling strain from broader economic factors. We focus on two key areas:

1. At the application stage, by guaranteeing that credit is extended to those who are capable of managing it
2. Equipping individuals with effective tools to manage their financial commitments

7. Startups often pivot or iterate their products based on user feedback. How has customer feedback influenced the development of your product, and what role does user experience play in your ongoing strategy?

We are fortunate enough to have met people along the way who share our sense of frustration about the problem. These discussions have had a crucial role in informing our product roadmap and development. What has been inspiring is the wide range of interest we’ve received, spanning from enterprises with thousands of employees to smaller scale lenders. 

8. As founders, what is your vision for the future of your startup? How do you see your product evolving, and what milestones do you hope to achieve in the next few years?

Our goal is to create a positive impact, driven by two core motivations: the passion for the technical challenges that align with our ambitions, and a commitment to making a difference by aiding those who are burdened by an inability to manage their finances effectively. We firmly believe that the application of software and machine learning can produce tangible, real world benefits for both borrowers and lenders.
 

9. Disruption can sometimes face resistance from established players. How do you navigate challenges with incumbents in your industry, and what strategies do you employ to gain market acceptance for your innovative product?

We do not see ourselves as competitors to the incumbent players, but rather as a complement to a lenders’ toolkit and a guardian for consumers, whether at the point of application or in their ongoing financial journey. 

About Beam

Beam is a fintech company founded in South Africa. Our software solution helps organisations make better credit decisions by seamlessly distilling a broad range of data sources in real-time

We enable risk officers to access all the information they need to analyse their customers in one place, and make it easy to make more informed choices throughout the credit and risk lifecycle. Our state-of-the-art software and API-driven model enable better collaboration and visibility between credit professionals, technical teams and management.

Industry Statistics

• 2023-Q3: 23.06% of consumers who have unsecured credit were late on repayments
• 2023-Q3: 21% of consumers who have secured credit were late on repayments
• 2023-Q3: 68,9% of credit applications are rejected
• Average Bureau Net Promoter Score: -38.5

The digital transformation within financial services has ushered in numerous new avenues for lenders to engage with their customers. Advances in Europe and North America have showcased the success of lenders who adopt more sophisticated underwriting strategies that leverage current data on affordability and behaviour-based insights.

Consumers are keen to establish relationships with merchants and businesses with whom they make long-term commitments, particularly in personal contexts like credit arrangements.

The above statistics highlight a fundamental issue in consumers’ perceptions and handling of their credit responsibilities, indicating a need for a significant reformation of the landscape

Advancements in Technology and Data Science

By harnessing cutting-edge technology and machine learning methodologies, Beam’s capabilities surpass mere document gathering and analysis. Instead, they enable the precise construction of a prospective borrower’s risk profile in real-time, utilising thousands of data points.

Beam’s product suite is intentionally crafted for simplicity, empowering users to quickly reach a conclusive ‘yes’ or ‘no’ decision.

Importantly, Beam integrates seamlessly into existing lending operations; it does not require applicants to navigate cumbersome procedures. Instead, Beam is implemented as a toolkit to enhance revenue and customer satisfaction.

With the potential introduction of Open Finance regulation in South Africa, companies like Beam are well positioned to accelerate big data, AI and API-first distribution models to provide lenders with a more accurate, real-time view of consumer’s financial behaviour, their financial position right now as well as being able to predict their financial behaviour in the future.

It’s time to recalibrate the credit industry

Our vision encompasses two strategies:

1. Advocate for a revolution in loan decision-making, enhancing the economic landscape by broadening access for consumers with limited credit histories. By placing machine learning-driven assessments of affordability and financial standing at the heart of underwriting, we aim to ensure that loans are not extended to individuals who may not be able to manage them.
2. Create a network that sustains lender-borrower relationships beyond the initial loan origination. This will empower consumers to make informed decisions regarding their credit commitments.

We intend to do this by developing best-in-class tools and product experiences, and by fostering a consumer-permissioned and lender-supported ecosystem. This ecosystem will not only comply with the regulations set forth by the NCR but will also be vibrant and dynamic, challenging the status quo and propelling the industry forward.