Data-driven financing is the future, writes Tim Armstrong, co-founder of Silver Birch Finance and head of its receivables financing and data science team.
By harnessing deep customer insights, behavioural nuance and cross-industry expertise, Silver Birch is delivering tailored, client-centric solutions that outperform traditional receivables financing models.
Clients understand their data better than the market
The premise of traditional receivables financing – that external financiers can assess customer credit risk better than the businesses that serve those customers – is fundamentally flawed. At Silver Birch Finance, our work shows that businesses have an intimate, nuanced understanding of their customers’ payment behaviours that no third-party assessment can replicate.
Consider the case of a multinational telecommunications provider we work with across multiple European markets. This client keeps detailed records not just of payment timings, but of customer interactions, service usage patterns and even the types of devices used to access their services. Their collections team can predict which customers may pay late based on subtle behavioural cues – the frequency of customer service contacts, changes in usage patterns, or even the timing of handset upgrades based on the specific handset model. Yet traditional receivables financing models have ignored this detailed data, relying instead on generic credit scores that do not capture these critical behavioural indicators.
Our Portfolio Receivables Monetisation (PRM) solution builds financing structures that incorporate the client’s knowledge – and backs that knowledge by underwriting the performance of their receivables.
Customers pay bills based on importance, not just ability
Traditional credit analysis runs on the assumption that customers pay when they can, and default when they cannot. This framework ignores the reality that payment decisions are often strategic choices reflecting complex hierarchies of priority.
Our work with a Latin American energy provider during the Covid-19 pandemic illustrated this principle. As lockdowns disrupted economic activity across the region, we saw that consumers were more likely to pay their bills than before Covid hit – despite GDP falling, a situation traditionally linked with increased consumer delinquency. We incorporated this insight into our models to optimise our analysis.
The commercial sector reveals even more complex payment hierarchies. A manufacturing client provided data showing that their customers exhibited completely different payment patterns. Some customers paid within 15 days on average, others were often more than 60 days late. This pattern was consistent and held true regardless of the customer’s overall financial health.
By considering these hierarchies in our financing models, we’re able to help clients achieve advance rates that reflect the true risk profile of their receivables.
Tailored solutions aligned with client operations
PRM recognises that financing structures should conform to how businesses work, and adjust as the business models evolve.
An example comes from our work with a multinational corporation that had grown through acquisitions. The client’s operations were spread across several ERP systems. Traditional financiers needed system integrations before considering receivables purchases, presenting the client with a dilemma: either undertake a multi-year, multi-million-dollar systems unification project, or forgo receivables monetisation entirely.
Rather than requiring system standardisation, we allowed the client to send us the data from each system independently, in whatever format suited them. We then combined the different data sets, creating a unified data model. This allowed us to begin purchasing receivables within three months, compared to the 18-month timeline needed for system integration.
The operational benefits extended far beyond faster implementation. Because we preserved each subsidiary’s processes, local finance teams could continue working with familiar systems rather than struggling with imposed changes. This supported operational efficiency while still providing corporate treasury with the liquidity benefits of receivables financing.
Over time, our data aggregation even helped show opportunities for process improvement. By comparing collection performance across the different ERP systems, we could pinpoint which legacy processes delivered the best results, improving the client’s operational integration.
Another dimension of operational tailoring involves financing flexibility. Traditional receivables facilities often impose rigid usage requirements: minimum purchase volumes, fixed scheduling or long-term commitments. These structures often clash with the variable working capital needs of growing businesses.
We addressed this challenge for a technology services provider experiencing rapid but uneven growth. The company’s receivables fluctuated significantly from quarter to quarter, driven by project timelines and enterprise procurement cycles. Traditional lenders had offered a facility sized to peak receivables volumes, leaving the client paying for unused capacity during trough periods.
Our solution incorporated a dynamic advance rate that automatically adjusted based on the composition of their actual receivables, and did not require the company to sell receivables unless they needed to.
Diverse teams solve problems more effectively
Financial innovation thrives at the intersection of disciplines. Our approach draws on insights from fields as varied as high-energy physics, behavioural economics, actuarial statistics and professional sports analytics – a deliberate strategy that offers unique solutions.
Our work shows the power of this approach. Faced with the challenge of predicting prepayment behaviours, we use techniques like those used at CERN, such as Monte Carlo simulations. As CERN’s algorithms sift through petabytes of collision data to find meaningful events, so our models parse vast receivables datasets to find subtle behavioural signatures that predict early repayment.
Perhaps most unexpectedly, techniques from sports analytics have informed our approach to portfolio optimisation. The same statistical methods used to evaluate the likelihood of Premier League players becoming injured have helped us construct optimal receivables portfolios for clients.
This multidisciplinary approach doesn’t just enhance our models – it expands the types of solutions we can envision. When an energy client struggled with the requirement to impose higher bills on small businesses and consumers, our team, led by a former central banker, developed a solution inspired by monetary policy tools. We created a ‘term transformation facility’ that allowed the client to increase bills gradually over time, but receive the cash for those future payments today – effectively “lending” duration between different receivable pools, smoothing out their working capital position.
Conclusion: Data-first finance
Receivables finance stands at an inflection point. Traditional approaches, constrained by rigid credit frameworks and standardised manual processes, are increasingly inadequate in today’s complex environment. Silver Birch represents a new paradigm – one that recognises clients as experts in their own receivables, understands the behavioural realities of payment decisions, adapts to operational realities rather than demanding conformity, and uses diverse perspectives to drive innovation.
As economic uncertainty persists and working capital management grows more strategic, the advantages of a data-driven approach will increase. Businesses that embrace data-driven, client-centric receivables financing will gain a competitive advantage – not just in liquidity management, but in customer relationships, operational efficiency and strategic flexibility.
Silver Birch Finance is delivering this advantage for corporates and investors. Refined through years of cross-industry experience and continuous innovation, the PRM solution offers a path beyond the limitations of traditional receivables finance.
The future belongs to businesses that recognise their receivables not as static balance sheet items, but as dynamic assets containing insights and opportunities – and to financiers sophisticated enough to help unlock that potential.
About the author
Tim Armstrong is a co-founder of Silver Birch Finance, where he leads receivables financing and data science. He has 25 years’ experience across investment banking and financial services, with roles at Morgan Stanley, Merrill Lynch, Deloitte, KPMG and a UK fintech. A former British Army Officer and BP engineer, Tim holds an MA in Physics from Oxford and an MBA from London Business School.
