Distributed scalable incrementally updated models in decisioning systems

摘要

In one embodiment, first weight information indicating a first set of delta values is obtained, where the first set of delta values includes a first delta value for each weight in a set of weights, the set of weights including a weight for each of a set of one or more parameters of a model. In addition, second weight information indicating a second set of delta values is obtained, where the second set of delta values includes a second delta value for each weight in the set of weights. Combined weight information including a combined set of delta values or a combined set of weights is generated based, at least in part, upon the first weight information and the second weight information.

主权项

1. A computer-implemented method of delivering targeted content to a user, the method comprising:
for a set of weights, each weight being applied to a feature of a set of features associated with the user, obtaining from a first decisioning component including a first processor a first weight information indicating a first set of delta values, the first set of delta values including a first delta value for each weight in a set of weights, the set of weights including a weight for each of a set of one or more parameters of a model, the first set of delta values generated by the first decisioning component by subtracting a prior set of local weights for the first decisioning component from a current set of local weights for the first decisioning component; obtaining from a second decisioning component including a second processor second weight information indicating a second set of delta values, the second set of delta values including a second delta value for each weight in the set of weights, the second set of delta values generated by the second decisioning component by subtracting a prior set of local weights for the second decisioning component from a current set of local weights for the second decisioning component; generating combined weight information including a combined set of delta values and a combined set of weights based, at least in part, upon the first weight information and the second weight information, wherein a single combined delta value for a particular weight is generated based on the first delta value for the particular weight and the second delta value for the particular weight; based on the model and the combined weight information generating a score for the user, where the score is determined by multiplying each weight in the combined weight information with a corresponding feature of the set of features and summing the results; based on the score, sending a content identification to a content management system; and based on the content identification, delivering targeted content to the user.