Contact Us

Cutting Fraud Detection Latency to Real Time for a Leading Card Issuer

Cutting Fraud Detection Latency to Realtime For a Leading Card Issuer

Cutting Fraud Detection Latency to Real Time for a Leading Card Issuer

  • Technology: AWS, DBT, Apache Airflow, Apache Kafka, Snowflake
  • Industry: Fintech, Financial Services
Cutting Fraud Detection Latency to Realtime For a Leading Card Issuer

About Client

The client is a leading credit card provider, running a large and complex digital estate that spans both web and mobile. At the center of it is the platform powering their card and card-less products. Every action a customer takes, opening an account, making a payment, triggering a fraud check, flows through this platform as an event, across seven different business areas: accounts, closed loop transactions, tenant management, payments, customer data, fraud, and end-of-day processing.
That’s a lot of data moving fast, from a lot of different places.

Business Objectives

The client’s customer, transaction, fraud, and account data all originated from the same platform, but no single, trusted version of that data existed. Seven business areas each maintained their own view of the truth, and teams routinely reconciled numbers by hand, resulting in delays and, at times, inconsistent answers to the same question.
In the absence of a governed data layer, analysts and engineers often queried raw event data directly to complete their work, increasing the risk of inconsistent or inaccurate reporting. Fraud detection added urgency to the problem. Fraud signals lose their value once the moment to act has passed, and next-day batch processing could not keep pace with the speed fraud requires.
The platform also needed to scale with the business. Each new product or event type introduced additional manual engineering effort, slowing the pace at which new data could be put to use.
The client needed a governed, real-time data foundation that business teams, analysts, and data scientists could rely on, without direct access to raw event data.

Solution

Kenexai designed and built a real-time data platform on Snowflake, using Kafka to stream every event the moment it happens, and Airflow to keep the whole pipeline running on schedule.
Rather than dumping raw data into one big pile, we built the platform in layers, each with a clear job:
  • Landing — events arrive from source, organized by business area, ready to be picked up automatically as new event types are introduced.
  • Staging — data lands exactly as it came in, untouched, with the key identifying details extracted so downstream automation knows what it's looking at.
  • Raw Vault — this is where the data gets structured for the long term, using a modeling approach (Data Vault 2.0) built specifically to survive change. Source systems can evolve without breaking everything downstream.
  • Business Vault — business logic gets applied here, and the data gets shaped for fast, efficient querying, including the ability to see exactly what an account or customer looked like at any point in time.
  • Infomart — the finished product. Business teams get their own datasets, BI tools get clean reporting tables, and data science gets an analytics-ready layer, each getting exactly what they need, nothing more.
Every transformation from raw data to finished dataset runs through dbt, which means every number can be traced back to the exact event it came from, with full testing built in along the way.
The result is a platform that only processes what’s changed, rather than reprocessing everything every time, which keeps it fast and keeps compute costs in check even as data volumes grow.
Snowflake Data Life Cycle

Architecture Diagram

Benefits
All seven business areas now flow into a single, governed platform. Teams no longer need to reconcile numbers across silos or query raw events to complete their work, giving the business one consistent view.
Fraud data reaches a usable state in less than one minute, giving downstream fraud systems the speed they need to act before the opportunity to intervene has passed.
Business users, BI teams, and data scientists can work from datasets built for how they work, without needing to understand the underlying architecture.
Every number in every report can be traced back to its original event, with timestamps intact. This supports confidence in reporting while meeting internal and external audit requirements.
Automated, incremental processing has removed the need for manual reconciliation across account, customer, and transaction data, allowing teams to focus more on analysis and less on data cleanup.
Onboarding a new event type is now a configuration exercise rather than a re-architecture, allowing the platform to keep pace as the client’s product portfolio continues to expand.
Also, data retention and full historization are built into the platform by design, supporting regulatory obligations.
Legacy pipeline optimization reduced processing time by approximately 50%, while Snowflake warehouse optimization reduced Snowflake costs by 20–30% through workload-based right-sizing.

In Our Customers’ Words

Excellent to work with in every way. Proactively identified solutions to the problem in the initial design and the recommended solutions. Work has top-notch. Results delivered on time. Communication was excellent.

David Mann

United States

They took us from square one, building a smart data strategy – everything from collecting data to dishing out real-time insights. With their help, we’ve seen some major improvements. We would give them a thumbs-up for anything data-related.

Eric A.

Real-estate Company

Real pleasure consulting with Kenexai to set up our company’s entire data warehouse and dashboards on AWS. I will definitely be reaching out to them for future work to be done. Our project was effective and 100% achieved what I planned to do in the beginning, in a shorter time frame and with less effort than I expected.

Hans

United States

CCR Data perform complex data migrations, we needed and extra pair of hands to restore an Oracle database and transfer the data to a Microsoft SQL database ready for our migration analysts to do their stuff. We would not hesitate in recommending or using Kenexai again and would be happy to outsource bigger projects to them in the future.

Henry Sykes

Director - CCR Data

Working with Kenexai was a game-changer for us. Thanks to Nitesh from Kenexai, our data strategy is on point and giving our business a major boost!

Jason Wood

Auto Finance Company

I have used RA on numerous occasions over the past 2 years, specifically with Nitesh Solanki for the delivery on PDI ETL jobs. I am very happy with him and the high level of quality work he has provided. He seems to be available all the time and works extremely hard to deliver high quality solutions.

Mark Scriven

Technical Director - Value Ad

They truly understand what they do. Their restaurant analytics provide real-time insights into our operations and customer behaviors, and it has made a significant difference in our business.

Patrick

Restaurant Business

Working with Kenexai has been fantastic! Thanks to their AI and ML-powered solution, we’ve made great progress. Their expertise helped us spot and prevent fraud in rentals and make us trustworthy.

Remi Martens

Hospitality business

Kenexai has made a real difference for our insurance firm. Their know-how in fraud detection is top-notch. Their data strategies have been a big help, and we are seeing great results. We are quite pleased with what they’ve done for us

Sharon White

Insurance Firm

Insights That Move,
Impact That Matters.

Turning insights into meaningful impact with tailored solutions, every step of the way.
Contact Us
top