IBM Brings Real-Time Forecasting to Streaming Data with Granite Models

IBM and Confluent have launched IBM Granite Time Series models in Early Access on Confluent Cloud, bringing forecasting and anomaly detection to streaming data. This integration pairs IBM's time-series foundation models with Confluent's data streaming platform.

The four complementary time-series foundation models - PatchTST-FM-r1, FlowState-r1.1, TTM-r3, and TSPulse - are designed to support different needs across forecasting, anomaly detection, scale, accuracy, and other time-series tasks.

These models can be applied to various use cases, including forecasting and planning, anomaly detection in financial services, production optimization in manufacturing environments, and semantic intelligence for answering practical questions.