| CPC G06N 5/04 (2013.01) [G06F 16/36 (2019.01); G06N 20/00 (2019.01)] | 20 Claims |

|
1. A computer-implemented method, comprising operations for:
building a recommendation structure from features of data, wherein the recommendation structure comprises a plurality of rules, and wherein each rule of the plurality of rules is associated with a recommendation;
sending the recommendation structure to a model;
creating a feature set comprising a feature and one or more related features from the features; and
in response to determining that a feature worthiness score of the feature set exceeds a threshold,
inputting the feature set to the model;
receiving a rule of the plurality of rules from the model, wherein the rule includes the feature, the one or more related features, and the associated recommendation; and
in response to receiving a set of values for the feature and the one or more related features, applying the rule to the set of values to provide the recommendation.
|