July 2024 Summaries

Recent updates from the engineering team include several enhancements to the Chalk platform, notably the introduction of a gRPC engine for improved performance, and the ability to use SQL in offline queries for more efficient data retrieval. Role-based access control has been expanded, allowing for more granular permissions at the data source and feature levels. Users can now track incremental resolver statuses via CLI, and deployment tags have been introduced for better environment management. Heartbeat monitoring now detects and marks long-running queries as failed if they hang, while new integrations with Trino and Spanner, improved search and filtering in the feature catalog, and enhancements to SQL resolvers and error reporting contribute to a more robust and user-friendly experience.

Machine learning plays a critical role in fraud detection across various industries, with feature stores being pivotal in enhancing this capability. Feature stores serve as a bridge between raw data sources and machine learning models, facilitating the extraction, transformation, and storage of real-time and historical features necessary for model training and compliance. Within a machine learning platform, feature stores are structured with a registry defining feature names and types, an ETL process for data ingestion, and online and offline storage for low-latency queries and bulk data handling, respectively. Monitoring and observability systems are integrated to detect issues like feature drift, ensuring data quality. For fraud detection, feature stores can integrate with streaming and batch data sources, such as Kafka for real-time transaction data and Snowflake for historical data, to compute features like risk scores and transaction statistics. By enabling efficient querying and computing of feature values, feature stores support real-time inference and model training, thus aiding in the development and deployment of sophisticated fraud risk models. The use of feature stores not only enhances model accuracy and efficiency but also promotes collaboration and scalability in machine learning applications.

Chalk has opened a new office in New York City's Flatiron district, close to Madison Square Park, to strengthen its presence on the East Coast and access the region's pool of talent to enhance its machine learning solutions. This expansion aims to merge the expertise of Chalk's Bay Area team with the engineering and go-to-market skills available in the Northeast, furthering its mission to support machine learning and data teams. By establishing a hub in New York, Chalk seeks to contribute to the growing AI and MLOps community and expand its go-to-market and engineering teams. The company is actively seeking talented professionals to join its dynamic workforce and shape its culture across different regions.