MLHub is a new module designed to bridge the gap between central data teams and operational experts. With MLHub, operational experts and data scientists are empowered to collaborate on a machine learning exercise. MLHub enables the creation, training, and deployment of machine learning models for deeper operational insights.<\/p>\n
\u00b7\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0Enhanced Machine Learning Capabilities<\/strong>: MLHub allows data scientists to import data from TrendHub and ContextHub views, validate hypotheses using Python code, and deploy machine learning models. These models become accessible to all software users as Machine Learning tags in TrendHub or notebook output tiles in DashHub.<\/p>\n \u00b7\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0New ML Environment<\/strong>: The release includes a new Jupyter notebooks ecosystem, kernel isolation and resource management for improved performance, and a full-proof security layer. Also, notebook output cells for easy visualization and Machine Learning Model tags based on PMML models are introduced.<\/p>\n \u00b7\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0Plotting Contextual Data<\/strong>: Multivariate scatterplots provide stronger visualization and allow process experts to classify the relationship between contextual events and their attributes. These plots help in extracting insights on correlations and distributions for further analysis.<\/p>\n \u00b7\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0Enhanced Operational Dashboards<\/strong>: Text tiles and notebook output tiles now appear on the dashboard, which allows operational experts to provide explanations and interpretations alongside visual data sources.<\/p>\n","protected":false},"author":105,"featured_media":126929,"template":"","meta":{"_acf_changed":false,"pgc_sgb_lightbox_settings":""},"categories":[104044],"tags":[],"class_list":{"2":"type-products"},"acf":[],"yoast_head":"\n