BridgeFund
Streamlining Credit Risk Assessment with AI
Client & Challenge
BridgeFund, a leading Dutch fintech lender, was experiencing rapid growth in its mission to provide accessible and flexible financing solutions to small and medium-sized enterprises (SMEs). However, this success brought a critical challenge: their existing credit risk assessment process was struggling to keep pace. The manual, time-consuming nature of assessing loan applications created a bottleneck, limiting their ability to scale efficiently and make timely decisions. This raised a crucial question:
How could BF use its wealth of data and technological capabilities to enable faster, more accurate and responsible credit risk assessments?
The existing process relied heavily on individual Risk Agent’s judgement, leading to inconsistencies and limited risk differentiation in pricing. Furthermore, the absence of robust risk models, coupled with data quality and infrastructure challenges, prevented BridgeFund from fully capitalizing on its market-leading data advantage.
These pain points highlighted the need for a comprehensive solution that would address both technological and process-related issues, ultimately enabling BridgeFund to achieve its growth objectives while upholding its commitment to responsible lending.
Our Approach & Solution
We led BridgeFund’s “Risk 2.0” project, aiming to develop a system for automated credit risk assessment. We tackled this challenge through a multi-pronged approach, encompassing four key workstreams:
- Data Architecture and Engineering: We revamped BridgeFund’s IT infrastructure and data pipelines to ensure stable data ingestion, improved data quality, and greater availability for analysis. This involved implementing best practices in data architecture and addressing existing bottlenecks in the data flow.
- Modelling: We developed a sophisticated Probability of Default (PD) model utilizing machine learning algorithms. This model was trained on BridgeFund’s extensive transaction data, providing accurate PD predictions for potential customers during the onboarding process.
- Implementation: We facilitated the seamless integration of the PD model into BridgeFund’s credit acceptance process. This involved setting clear boundaries on model usage, training Risk Agents, and establishing robust monitoring systems to ensure ongoing model performance and compliance.
- Long-Term Vision: We collaborated with BridgeFund to envision a new risk portal that would incorporate the PD score and enable a more automated loan request evaluation process. This included designing a Figma mockup to visualize the portal and ensure alignment on the desired features and functionality.
Results And Impact
While we provided the program management and strategic guidance, the success of this project was a true collaboration. We worked hand-in-hand with BridgeFund’s talented data engineers and modellers, whose deep understanding of the data and business context was invaluable. Their technical skills and dedication were essential in bringing the Risk 2.0 vision to life
By successfully delivering the Risk 2.0 project, we helped BridgeFund transform its credit risk assessment process, paving the way for continued growth and success in the competitive fintech lending market. The project’s success was further validated by BridgeFund’s decision to reward us with the agreed-upon bonus, acknowledging the significant value we brought to their operations.
Rapid PD Model Deployment
We successfully developed and implemented the PD model within an ambitious three-month timeframe, underscoring our commitment to delivering tangible results.
Enhanced Risk Assessment
The PD model enabled BridgeFund to make more informed credit decisions, improving risk assessment accuracy and consistency.
Increased Efficiency
The automation of credit risk assessment significantly reduced processing time, allowing Risk Agents to focus on more complex cases and strategic decision-making.
Improved Scalability
The new system provides a scalable foundation for BridgeFund’s future growth, enabling them to handle increasing loan application volumes efficiently.
Data-Driven Decision Making
The integration of the PD model into the risk portal empowered BridgeFund to leverage its vast data resources for more effective and objective credit assessments.
Contact us to learn how we can help your business harness the power of data and AI to drive innovation and achieve tangible results.
Other Cases
FD Mediagroep
How can FDMG create strategic impact with AI over the next two years, and how should it be organized?
Sunweb
How can we make smarter, more dynamic decisions on when to rely on internal stock and when to switch to external flight capacity — in a way that balances margin, availability, and risk?
Kramp
“How can we improve Kramp’s search engine within a short period of time to enhance customer satisfaction, increase sales, and boost operational efficiency?”
