Random feature transformation forests for automatic feature engineering
AssigneeInternational Business Machines Corporation
InventorsSaket SATHE, Deepak S. TURAGA, Horst Cornelius SAMULOWITZ, Charu C. AGGARWAL
Life of this patent
Estimating the term…
Abstract
Embodiments for automated feature engineering by one or more processors are described. One or more selected transformations may be applied to a set of features in a dataset to create a set of transform features using random feature transformation forest (RFTF) classifiers. A transform feature may be selected from the set of transform features having a highest discriminative power as compared to other features of the set of transform features. At each node in a decision tree, store the selected feature, a split value, and the one or more selected transformations for the transform feature.
Claims20
A method, by one or more processors, for automated feature engineering, comprising:
- applying one or more selected transformations to a set of features in a dataset to create a set of transform features using random feature transformation forest (RFTF) classifiers;
- selecting a transform feature from the set of transform features having a highest discriminative power as compared to other features of the set of transform features;
- and
- storing at each node in a decision tree the selected transform feature, a split value, and the one or more selected transformations for the selected transform feature.
A system for automated feature engineering, comprising:
- one or more computers with executable instructions that when executed cause the system to:
- apply one or more selected transformations to a set of features in a dataset to create a set of transform features using random feature transformation forest (RFTF) classifiers;
- select a transform feature from the set of transform features having a highest discriminative power as compared to other features of the set of transform features;
- and
- store at each node in a decision tree the selected transform feature, a split value, and the one or more selected transformations for the selected transform feature.
A computer program product for feature engineering by one or more processors, the computer program product comprising a non-transitory computer-readable storage medium having computer-readable program code portions stored therein, the computer-readable program code portions comprising:
- an executable portion that applies one or more selected transformations to a set of features in a dataset to create a set of transform features using random feature transformation forest (RFTF) classifiers;
- an executable portion that selects a transform feature from the set of transform features having a highest discriminative power as compared to other features of the set of transform features;
- and
- an executable portion that stores at each node in a decision tree the selected transform feature, a split value, and the one or more selected transformations for the selected transform feature.
Dependencies are inferred from the claim text.