US 12,277,508 B2
Hierarchical tournament-based machine learning predictions
Gautham K. Kudva, Flower Mound, TX (US); Srinath goud Vanga, San Jose, CA (US); and Koustuv Chatterjee, Gilbert, AZ (US)
Assigned to o9 Solutions, Inc., Dallas, TX (US)
Filed by o9 Solutions, Inc., Dallas, TX (US)
Filed on Jun. 16, 2023, as Appl. No. 18/336,531.
Application 18/336,531 is a continuation of application No. 17/979,479, filed on Nov. 2, 2022, granted, now 11,748,640.
Application 17/979,479 is a continuation of application No. 17/449,350, filed on Sep. 29, 2021, abandoned.
Prior Publication US 2024/0028928 A1, Jan. 25, 2024
This patent is subject to a terminal disclaimer.
Int. Cl. G06N 5/04 (2023.01); G06N 5/022 (2023.01)
CPC G06N 5/04 (2013.01) [G06N 5/022 (2013.01)] 21 Claims
OG exemplary drawing
 
1. A system for hierarchical tournament-based machine learning predictions comprising:
at least one processor; and
memory including instructions that, when executed by the at least one processor, cause the at least one processor to perform operations to:
train a machine learning selection model with training data to calculate a probability that an algorithm and a model will provide output to obtain a metric;
select a set of evaluation component combinations using the machine learning selection model, wherein each evaluation component combination of the set of evaluation component combinations includes an algorithm, a hierarchical learning model corresponding to a level of a hierarchy, and a prediction model for a target prediction;
receive output results for the set of evaluation component combinations from a cluster of computing nodes;
evaluate the output results using a metric to determine a winning evaluation component combination; and
store the winning evaluation component combination in storage for use in calculating future predictions for the target prediction.