Fraud detection software

Software increased the number of detected fraudulent transactions by a 96% accuracy and simplifying the client’s manual transaction review process.

Client

Payment platform specializing in handling transactions for companies in travel industry.

Objective

Identify fraudulent transactions and reduce fraud related losses.

Solution

Achievion data science experts analyzed the client’s data lake that aggregated financial data coming from multiple sources. The team has also reviewed the existing transaction validation engine to better understand the nature of the fraudulent activities.

Once the analysis phase was completed, we developed and trained the Machine Learning model to detect suspicious transactions within several seconds after posting. The continuous monitoring and improvement process was put in place to keep the model up to date going forward.

Our engineering team built the API on top of the model and integrated the software with client’s payment processing engine.

Result

Our software elevated the detection rate of fraudulent transactions, achieving a 96% accuracy rate. This streamlined the client’s manual transaction review process, resulting in significant cost savings for the company.

Improved fraud detection: the software increased the number of detected fraudulent transactions by 87%.
High accuracy achievement: achieved a 96% accuracy in identifying fraudulent transactions.
Cost savings: the client’s manual transaction review process was simplified, resulting in substantial cost savings.