Maurice Harary
Facing first party fraud and inconsistent approval rates, user trust was fading
Before using Oscilar's technology, Fluz was dealing with serious issues like payment fraud, first party fraud, and other types of transaction scams. These problems weren't just numbers on a report; they had real-world consequences.
Each time a direct debit payment was declined, it wasn't just a lost sale for Fluz. It also shook the trust that customers had placed in the platform. For a company like Fluz, which aims to provide smooth and hassle-free transactions, these setbacks were more than just minor hiccups; they posed a direct threat to their commitment to putting customers first.
A seamlessly integrated AI-driven defense, turning Fluz's payment fraud and first party fraud losses into wins
Oscilar stood as a significant ally for Fluz, combining its proactive, partnership-driven approach with the exceptional quality of its Machine Learning (ML) models. Rather than just being another vendor, Oscilar became a strategic collaborator, jointly championing Fluz's vision and successes.
During their search for a solution, Fluz encountered several obstacles along the way. They delved into potential solutions like:
Kount, a system predominantly anchored in predefined rule-based algorithms
Riskified’s approval rates were much lower than what Fluz needed to build a viable product.
Alloy was another contender, but they didn’t have ML models that could help Fluz prevent fraud.
Considering the possibility of a customized, in-house solution briefly crossed their minds, but the constantly changing and unpredictable nature of first party fraud and payment fraud patterns made that option appear full of uncertainties.
This is where Oscilar’s value proposition stood out. Our team wasn’t content with merely being a service provider; we aimed to be a partner. We dedicated ourselves to understanding Fluz’s nuanced challenges, ensuring that their ML models were tailored to address their unique first party fraud pain points.
Approvals grew by 20%, building trust and paving the way for next-gen P2P enhancements
Oscilar's unsupervised Machine Learning models identified key patterns in bank transactions, enhancing payment fraud detection.
The holistic modeling approach by Oscilar boosted approval rates and elevated user experience.
Oscilar's integrated backtesting for ML models and rules together accelerated the introduction of new risk policies, quickly addressing emerging fraud trends.
Using Oscilar's technology resulted in marked operational improvements for Fluz, one of which was a 20% rise in approval rates. This wasn't a mere incremental gain; it had a direct impact on key user satisfaction indicators.
By ensuring a more streamlined transaction process for genuine users, Fluz was not just bettering its operational efficiency but also gradually rebuilding and bolstering trust among its user base. This operational modification, facilitated by Oscilar's AI risk platform, played a key role in improving Fluz's standing in a competitive market environment.
With Oscilar’s guidance, Fluz is poised to introduce some impressive updates, such as advanced ML models for virtual cards, dynamic real-time user interfaces highlighting ‘spend power’, and next-gen models to enhance P2P transfers.
>20%
approval rate increase
Automate 90% of your risk decisions
Make better decisions with ML models tailored to your data
60+ pre-built integrations with popular data sources