IBM时间序列模型下载量达5000万,现已登陆Confluent
ibm的时间序列模型下载量达5000万,现已在confluent上提供原生支持,用于实时预测和异常检测,为依赖及时数据分析的企业带来益处。
ibm and confluent have partnered to bring ibm's time-series foundation models closer to the data as it flows. these models, which have seen over 50 million downloads, can now run natively inside confluent in the cloud and on premises, using apache flink to apply forecasting, anomaly detection, and semantic intelligence to streaming data with sql. the models can support a range of use cases, including production line optimization, unusual store activity detection, and product-level planning. by integrating with confluent's data streaming platform, businesses can make timely decisions based on current data. the models run on cpus and can be fine-tuned or combined with other data and business logic.