Project background

In the world of logistics, fraudulent and dangerous packages are one of the industry's biggest challenges. That's why a major multinational logistics company turned to BigHub for help in implementing a system for early detection.

‍

Our approach

Our goal was to deploy a solution for real-time evaluation of shipments as they enter the transportation network. During the project, our team faced several challenges, such as scaling the REST API and managing the ML lifecycle. The REST API was connected to the client's network, where further operations would be carried out on the data. Based on the client's pilot solution, which had been developed and tested using historical data, BigHub improved the algorithms and deployed them in a production environment for real-time evaluation of shipments as they entered the transportation network.

For more details about the project, see our blog posts.

‍

Benefits of our approach

We were able to successfully deliver a solution that keeps the major international logistics firm one step ahead in the fight against bad actors.

Handling individual queries with a response time of less than 200 milliseconds and a high volume of queries (260 queries from 30 parallel resources per second) in real-time, ensuring it is ready for global deployment.

Managing the machine learning model lifecycle, including automated retraining, deployment of new versions into API, monitoring of quality and notifications, to ensure reliable long-term performance.

Enhancing the logistics company's operations

Through the REST API connected to the client's network

‍

Improving their warehouse management
Supply chain optimization
Transportation of thousands of packages globally on a daily basis.

Delivering complex solutions

The project has encompassed a variety of areas and modern data technologies

‍

Our approach includes data engineering
Real-time data processing
Cloud and machine learning-based applications
With use of Kubernetes, MLFlow, AirFlow, Teradata, Redis and Tableau