| CPC G06N 5/01 (2023.01) [G06F 17/18 (2013.01); G06F 18/22 (2023.01); G06F 18/2413 (2023.01); G06N 7/01 (2023.01)] | 20 Claims |
|
1. A computer-implemented method comprising:
obtaining, by one or more processors, respective target values of a plurality of attributes of a target entity, the plurality of attributes being used for prediction in a decision tree;
constructing, by the one or more processors, representations of a plurality of leaf nodes of the decision tree, wherein each of the representations indicate respective statistic values of a plurality of attributes of historical entities that have reached each leaf node of the plurality of leaf nodes in a historical traversal and a statistic prediction result determined from historical prediction results output at a respective one of the plurality of leaf nodes for the historical entities;
subsequently storing each representation of each leaf node constructed;
subsequently accessing and distributing each representation of each leaf node constructed to a respective execution unit;
subsequently determining, by running each respective execution unit in parallel, respective distance measures between the target entity and the plurality of leaf nodes based on the target values and the statistic values indicated by the representations; and
subsequently determining, by the one or more processors, a target prediction result for the target entity based on the respective distance measures and the statistic prediction results of the historical entities.
|