Analytics Scoring

Analytics Scoring:

• Enables in-dataflow evaluation using predictive models defined in either QMML (Spectrum Miner's proprietary model format) or PMML (industry-standard Predictive Model Markup Language) formats. Dataflows can write and retrieve data from Miner datasets used by the Miner predictive analytics software. This approach to modeling enables data enrichment by adding predicted or scored output from models created by your data insight team with industry-standard data modeling tools. Examples include models that calculate churn risk for existing customers or credit scoring models to determine a consumer's credit rating.
• Allows Java scoring to support scoring a model's fit with Machine Learning.
• Score new data using an existing model in a production IT environment.