July 2023 Summaries

The apply(risk) conference highlighted four key insights for developing machine learning systems in risk and fraud detection: investing in high-quality features and data is crucial, as well as expertise in handling unique data challenges such as drift and imbalance. Additionally, compliance and data governance can create technical challenges that require careful access control and management. Furthermore, it's essential to keep the business context in mind when evaluating trade-offs between model accuracy and performance, and to remember that a delicate balance must be struck between catching bad actors and maintaining a positive experience for legitimate users. The conference also emphasized the importance of using feature engines and ML observability tools to simplify data engineering and improve model health.

Tecton on Google Cloud is a feature platform that automates the steps involved in building and managing production-grade ML features. It enables data teams to easily define features as code using its declarative framework, which then orchestrates the physical data pipeline required to transform and materialize ML features. Tecton stores features in low-latency online and offline stores for real-time serving and training dataset generation. The platform is designed to meet enterprise scale and security requirements, supporting hundreds of thousands of queries per second with low latencies, while also enabling GDPR compliance. With Tecton on Google Cloud, customers can accelerate the development of ML applications, build state-of-the-art models, and get them to production quickly and reliably.

Tecton's feature platform has been integrated with Google Cloud Platform (GCP), enabling users to build and orchestrate the complete lifecycle of features from transformation to online serving for real-time machine learning. With this partnership, GCP users can seamlessly integrate a number of services with Tecton's feature platform, including BigQuery, Google Cloud Storage, and Pub/Sub. Tecton automates data connections, automatic orchestration, training dataset generation, and real-time feature retrieval, providing a fully managed way to build enterprise-grade feature platforms. The integration also enables users to utilize notebooks for development and testing, with tools like Vertex AI Workbench and Google Cloud Build facilitating the deployment of features-as-code. This partnership aims to help organizations deploy new ML applications faster, increase model accuracy, improve collaboration, and optimize costs.