Fraud detection for E-commerce
Tech stack
Bootstrap
Industry
Fintech
Collaboration
14 months Region
USA 
Client:
Under NDA
About the client:
We help our US-based client build patented technology that guards your company and workflow and minimizes duration wasted on mechanically revision operations and transactions. It’s easy to set up and it’s already used by more than 80 thousand merchants.
Solution
Our team created a non-linear, monitored machine learning model. The pattern identified fraud in real-time. We try to build a model for highly imbalanced data that are regular for this market. We used a mix of Classification methods like Random Forest, Bootstrap, Catboost, and LightGBM and implemented about 80 features.
Tasks we covered
- Cost of operation reduction by 24%
- Customer Satisfaction increase by 36%
- Analyzed around 140K transactions with 7% of fraudulent data items
You may also like
NDA
Data Accuracy & GDPR Compliance with AI Healthcare Document Automation
Unbench
How We Built a Flexible Vendor Management Platform Now Ready for White-Label Use
GetMeo
AI Agent for Efficient Project Knowledge Management
Tawkify
How Kitrum Simplified Tawkify’s Matchmaking Process
Franatech
Subsea Leak Detection Management Software For Franatech
Under NDA
Big Data Migration From Hadoop to Databricks
Under NDA
Recommendation Engine Solution With Embedding-Based Retrieval Approach
Quantium
Successful Migration and System Enhancement for Quantium
Under NDA
