Instacart Creates Real-Time Item Availability Architecture with ML and Event Processing

Instacart combined machine learning with event-based processing to create an architecture that provides customers with an indication of item availability in near real-time. The new solution helped to improve user satisfaction and retention by reducing order cancellations due to out-of-stock items. The team also created a multi-model experimentation framework to help enhance model quality.

ai apache flink apache kafka architecture architecture & design availability customers data warehousing development event event-driven-architecture experimentation framework instacart kinesis machine machine learning ml & data engineering mlops near postgres processing real-time retention s3 solution sql stock team