Company
Leading Fintech Company
Industry
FinTech
Use Cases
Credit Scoring
Risk Assessment
Social Media Data
About This Company
This leading fintech offers digital credit and financial services to consumers and businesses across Southeast Asia. For nearly a decade, it has built advanced credit scoring models to improve financial inclusion in emerging markets.
The Challenge
As a mature fintech, this organization already had strong risk models built on telco data and other traditional sources. But the team saw an opportunity to enhance its credit scoring accuracy and user verification processes, especially across diverse and fast-growing markets.
The goal wasn’t to overhaul its current system, but to add new, harder-to-forge behavioral and identity data to increase resilience and coverage for digital-first and thin-file applicants. Additionally, social media represented a valuable, untapped signal that could be leveraged to better verify users, infer employment status and economic activities to reduce the risk of spoofing.
“SEON was the first organization to unlock social media data for fraud prevention. It’s difficult to capture and even harder to maintain, and that’s what makes it so valuable.”
Product Manager
The Solution
This fintech integrated SEON’s social media intelligence into its scoring model as a complementary, real-time data layer (not a replacement), helping diversify risk assessment and improve coverage in under-documented segments.
What sets SEON apart is the breadth and freshness of its social signals, continuously updated to ensure accuracy and prevent spoofing attempts, which is critical for digital lending.
Key social data signals included:
SEON was deployed across four markets, working seamlessly alongside other providers, including telcos and local credit bureaus, and strengthening the company’s ability to adapt as data provider reliability changes. SEON’s support and technical responsiveness ensured a smooth integration process at scale.
The Results
With SEON, the fintech improved model accuracy and data resilience across Southeast Asia. The social media data layer led to a 1-2% increase in Gini accuracy, a substantial gain that enables more confident credit decisions and can translate into significant reductions in defaults at scale.
Other Key Outcomes:
“The Gini increased 1-2% percent when using SEON. The more diverse data points, the better.”
Product Manager
Social presence signals, such as established Facebook or Skype accounts, continue to provide unique insights that traditional data sources cannot capture, especially in developing markets. For this organization, that means more robust credit models, greater adaptability and greater confidence in scoring decisions, even as customer profiles evolve.
Key Results
