Finance
Kashif
Real-time detection of suspicious financial transactions
- XGBoost
- Kafka
- Docker
- Grafana
- Status
- Launched product
- Year
- 2,024
- votes
- 263
The problem it solves
Traditional rule-based detection lags behind new fraud patterns and produces a flood of false alarms that exhausts the review team.
The solution
A model that learns from shifting patterns and scores each transaction in under a hundred milliseconds, with a clear explanation for the score.
Impact
Reduced false alarms by close to 45% while maintaining the detection rate.
Awards & recognition
FinTech Innovation Award
The team
Talal Alharbi
A former safety technician with six years on construction sites, building vision systems that work in harsh field conditions rather than ideal labs.
- YOLO
- OpenCV
- Edge AI
- Python
Hessa Almutairi
A former accountant combining deep financial understanding with modern analytics tooling, leading an analytics team in risk management.
- SQL
- Power BI
- Python
- XGBoost
They were exactly where you are… look where they are now.
Membership is automatic for every graduate who completes a program — no application, no fee.