Christopher Blakey Full Stack Engineer
← All projects

Product case study / AI / Financial risk

FeedzaiAI-powered fraud and risk operations

Connect fraud detection, risk decisions, and investigations in a financial crime prevention platform.

Risk decisionsFraud detectionInvestigation

Relevant technical skills

  • Python
  • Event processing
  • Risk scoring
  • Data validation
  • Model evaluation
  • API security
  • Audit logging
  • Integration testing

These skills describe a proposed engineering approach. They are not a verified list of the company’s internal technologies.

01 / The problem

Context

Feedzai addresses a connected operational workflow: real-time fraud detection and financial crime workflows. Teams using this type of platform need consistent context as information moves between systems and people.

02 / The experience

A connected product workflow

This product study focuses on the path from receive event to investigate case. The central interface challenge is making the next action understandable while preserving the state and evidence behind it.

  1. 01Receive event
  2. 02Evaluate risk
  3. 03Review decision
  4. 04Investigate case

03 / Technical perspective

Engineering approach

Define clear decision boundaries between automated scoring and investigator review. Preserve event provenance and explainability without exposing sensitive financial data.

This section outlines a proposed approach, rather than the company’s verified internal implementation.

04 / Reliability

Testing priorities

Test duplicate transactions, delayed events, model drift, and review-queue escalation. Changes to a decision policy should be traceable to a version.

05 / Source & attribution

Explore the product

This independent study is based on the company’s public website. The gallery contains imagery sourced from the company’s official website and public product resources. Images belong to their respective owners. This study does not claim a personal role in building the product.

Visit Feedzai ↗