Description
Discover how Novacomp transformed the Machine Learning infrastructure of a major Fintech in the banking sector, solving visibility challenges for predictions in production and optimizing the model lifecycle. Through a microservices-based architecture, event-driven monitoring, and real-time experimentation frameworks, the organization standardized deployments and maximized the operational performance of its embedded lending system.
What will you discover in this document?
By reading this success story, you will learn about:
- The challenge of Machine Learning monitoring and deployment: The lack of visibility into prediction behavior in production environments, the absence of infrastructure to execute A/B testing, and the lack of standardization in deployment processes.
- The technical integration and collaboration approach: The incorporation of talent under a Staff Augmentation model in synergy with internal teams, actively participating in agile ceremonies and collaborating with Data Engineering and Analytics squads.
- The technological ecosystem and MLOps architecture: The implementation of an advanced stack composed of Python, FastAPI, Flask, Docker, Apache Pulsar, Split.io, and Weights & Biases, integrated with predictive modeling libraries such as XGBoost, CatBoost, and Scikit-learn.
- Operational results and technical autonomy: The development of a real-time event-driven monitoring system, significant latency reduction through asynchronous code, clear documentation for autonomous deployments, and the enablement of parallel A/B testing.