Abstract: Systems and methods to implement a model operation application are provided. The method includes defining a plurality of artifacts of a model operation application, where each artifact has an abstract interface, and each artifact is invoked by a corresponding reference. The method also includes organizing references of data inputs and data sinks of the model operation application into a data channel, where the data channel includes one or more data channel artifacts of the plurality of artifacts. The method further includes combining a plurality of processing steps by reference into a scoring flow, wherein the scoring flow is configured to be managed as one or more scoring flow artifacts of the plurality of artifacts. The method further includes attaching the data channel to the scoring flow to form a scoring pipeline, wherein the scoring pipeline comprises one or more scoring pipeline artifacts of the plurality of artifacts.

Abstract: Systems and methods to screen a predictive model for risks of the predictive model are provided. The method includes obtaining a predictive model and metadata of the predictive model. The method also includes determining, based on a set of criteria for screening the predictive model, a risk of one or more negative consequences associated with the predictive model. The method further includes providing an analysis of the risk of one or more negative consequences.

Abstract: An algorithmic real-time learning engine comprising an algorithmic model generator configured to process a set of system variables from a big data source using at least one of a pattern recognition algorithm and a statistical test algorithm to identify patterns, relationships between variables, and important variables; and generate at least one of: a predictive model based on the identified patterns, relationships between variables, and important variables; statistical test model about correlations, differences between variables, or patterns in time across variables; and recurring clusters model of similar observations across variables. A data preprocessor can select system variables of interest, align the selected system variables based on time, and arrange the aligned variables into rows. The selected system variables can also be aggregated based on a pre-defined aggregate.