Hyper Parameter Optimization for Continuously Learning ML Algorithms

Expert: Belgin Övet, Erva Marangoz, Aslıhan Uysal, Enver Özdemir

TAZI has developed AI/ML tools for its customer, especially in financial sectors to classify their users and users’ behavior. Their customer portfolio includes insurance, finance, retail, and telecoms. Their core business is AI, they don’t have adequate infrastructure and they are getting such service from public cloud companies. They frequently need hybrid systems for training data and performance testing of their platforms.

TAZI develops commercial software tools for anomaly detection, fraud detection, etc. and during implementation and testing of these tools, they require computational resources. They use synthetic data for the training phase and need computational resources to test and compare their products to other products available in the current market. As their ML platform needs to run on a scalable system to satisfy requirements such as response time, continuous service, and accurate outputs, using HPC resources will help them to accomplish their purposes.

Please click here to view the results of the case study carried out with TAZI.