How Chipper Cash Uses Pinecone Vector Search to Stop Fraud in Real-Time

Chipper Cash, a fintech serving over five million customers across Africa, deployed a Pinecone-powered facial similarity search system to detect and block fraudulent duplicate sign-ups in real time. The solution slashed identity verification latency from up to 20 minutes down to under 2 seconds, and reduced fraudulent sign-ups by 10x across all markets.

Impact

95%+

Selfie verification accuracy

10x

Reduction in fraudulent sign-ups

Under 2 seconds

End-to-end verification latency

Under 200 milliseconds

Pinecone search latency

16%

Promo budget lost to fraud (prior)

Less than 1 month

Implementation time

Challenge

Chipper Cash's third-party KYC verification service became a bottleneck at scale, causing delays of up to 20 minutes during promotions — giving fraudsters time to exploit new-user rewards and costing the company 16% of its promo budget over six months.

Solution

Chipper Cash built an in-house facial similarity verification system using a ConvNet model to generate selfie embeddings and Pinecone as the vector database to search for duplicate users in real time, completing end-to-end verification in under 2 seconds.

Tools & Technologies

What Leaders Say

We have a high bar in terms of security and latency for our users. Many third-party solutions don't meet our requirements, so we typically opt to build or host in-house. Pinecone proved to deliver so much value — with reduced overhead and ultra-low latencies at scale — we didn't need to do much convincing to move forward.

Samee Zahid, Director of Engineering, Chipper Cash

It took us less than a month to build our new in-house facial verification system. We have a real-time, scalable, and secure system thanks to Pinecone. End-to-end latencies for the entire system dropped from up to 20 minutes previously to less than 2 seconds now, with Pinecone doing the search in under 200ms.

Samee Zahid, Director of Engineering, Chipper Cash
Get the full story.

Sign up to read complete case studies, access detailed metrics, and unlock all use cases.

Full Story

Chipper Cash is a fintech company on a mission to expand financial access across Africa, offering seamless cross-border money transfers to more than five million customers in seven countries. As the platform grew, so did its use of new-user promotions — incentive campaigns designed to attract legitimate customers and drive transaction volume. These promotions, however, also attracted bad actors looking to exploit the system by creating multiple fake accounts to repeatedly claim new-user rewards.

To combat fraud, Chipper Cash initially relied on a third-party identity verification service that performed KYC checks, including validation of government-issued IDs and detection of duplicate accounts. While effective at smaller scale, the solution became a serious bottleneck as user volumes surged — particularly during promotional periods. Verification delays stretched to as long as 20 minutes, giving fraudsters a window to redeem rewards before being caught. Over a six-month period, 16% of the company's promo budget was lost to fraudulent sign-ups, and several campaigns had to be shut down early, limiting legitimate user acquisition.

Samee Zahid, Director of Engineering at Chipper Cash, led the effort to build a faster, AI-native alternative. The core idea was to use visual similarity search: convert each new user's selfie into a vector embedding using a convolutional neural network (ConvNet), then query a vector database to find near-identical embeddings from existing users. A high similarity score would flag a likely duplicate account in real time. The team validated the concept with an open-source vector database, but quickly found that managing it at production scale introduced unacceptable operational overhead. After evaluating managed alternatives, they selected Pinecone for its ultra-low latency, scalability to billions of vectors, and minimal infrastructure burden.

The new system — built and deployed in under a month — integrates Pinecone with Snowflake as the data warehouse and a proprietary Facial Similarity Service (FSS) that generates embeddings and orchestrates queries. When a new user submits a selfie, FSS embeds the image and queries Pinecone, which returns the top three closest matches in under 200 milliseconds. The Chipper backend then evaluates match likelihood alongside relevant metadata to make a final determination. End-to-end, the entire verification process now completes in under 2 seconds.

Since going live, Chipper Cash has achieved 95%+ selfie verification accuracy, reduced fraudulent sign-ups by 10x across all markets, and reclaimed promo budget that now flows exclusively to legitimate new customers. Legitimate users enjoy a frictionless onboarding experience, and the company can run longer, more effective promotional campaigns. Encouraged by these results, the engineering team is actively exploring additional AI applications powered by Pinecone.

Similar Cases

MB
Millennium bcp
2.6x higher
conversion rate lift — owned media (bigquery audiences vs. other first-party audiences)

Millennium bcp, Portugal's largest private bank, used Google Cloud's BigQuery machine learning tools to build predictive audience models for personal loan campaigns. By segmenting existing customers by propensity to borrow, the bank dramatically improved both owned and paid media performance. The result was a 2.6x higher conversion rate and a 36% drop in cost per acquisition.

Financial ServicesBBigQueryGAGoogle Analytics 4
IE
Intercontinental Exchange
Qualitative shift
it visibility

Intercontinental Exchange (ICE) operates global financial exchanges, clearing houses, and mortgage technology serving markets worldwide. To move beyond lagging IT metrics like SLAs and satisfaction surveys, ICE deployed Moveworks’ HelpBot on Microsoft Teams, powered by an NLU-driven Employee Experience Insights (EXI) engine that converts raw IT tickets into a prioritized action list. EXI revealed hidden pain points—including that Outlook was ICE’s top driver of IT issues—giving the IT leadership team visibility they previously couldn’t achieve with conventional analytics.

Financial ServicesMAMoveworks AI Assistant
E
Ellevest
50–70%
style guide error correction time saved

Ellevest is a women-focused financial services and investing platform founded on the premise that the financial industry was built for men and has left women behind. With 20 writers producing 150+ articles annually and an intersectional style guide that evolves with cultural norms, the team adopted Writer to enforce brand consistency and compliance at scale. Time spent correcting style guide mistakes has dropped by 50–70%, and writers across the company now ship content aligned to Ellevest’s voice without requiring intensive manual editorial review.

Financial ServicesWWriter
NA
New American Funding
360 hours
weekly hours saved

New American Funding (NAF) is one of the largest independent mortgage banks in the US, with a marketing team of nearly 60 people spanning content, performance marketing, brand communications, and social. Facing an overwhelmed content operation across a regulated industry, NAF deployed Writer’s enterprise generative AI platform to streamline content production, enforce compliance guardrails, and maintain brand voice at scale. The platform now saves the team 360 hours per week and has compressed content tasks from hours to minutes.

Financial ServicesWWriter
SB
Shinhan Bank
1.2M+
staff hours saved annually

Shinhan Bank is one of South Korea’s largest financial institutions, operating more than 800 branches and serving millions of customers. Facing a workforce burdened by repetitive compliance, loan review, and data-transfer tasks across siloed systems, the bank launched the ‘My Bot’ initiative—deploying personal digital assistants to all 14,000 employees using Automation Anywhere’s platform. The result is one of the world’s largest enterprise digital assistant deployments, saving over 1.2 million staff hours annually and automating more than 100,000 property loan reviews each year.

Financial ServicesAAAutomation Anywhere
W
WEX
~30%
developer productivity increase with github copilot

WEX, a global fintech company that processes payments for fleet management, employee benefits, and corporate spending, consolidated a fractured developer ecosystem of 300+ Azure DevOps organizations onto GitHub Enterprise and deployed GitHub Copilot across its engineering workforce of 1,700+. The result was approximately 30% higher developer productivity, ~60% ROI on Copilot licenses, and a 99% reduction in deployment cycle times.

Financial ServicesGEGitHub EnterpriseGCGitHub Copilot
V
Vanguard
12%
search result accuracy improvement

Vanguard partnered with Pinecone to build Agent Assist, an internal RAG-powered AI chat tool that helps customer support representatives find answers faster and more accurately. By replacing keyword-based search with hybrid vector retrieval, Vanguard achieved 12% more accurate search results and meaningfully reduced call times — even during high-demand periods like tax season.

Financial ServicesPSPinecone Serverless
B
BM25
F
Fiserv
$10M
sla penalties avoided

Fiserv built safe, scalable AI automation on UiPath Platform with built-in governance, avoiding $10M in SLA penalties and onboarding 20,000+ QSR locations on schedule.

Financial ServicesUPUiPath Platform