Large-scale behavioral targeting for advertising over a network

A system, comprising a computer processor and a memory, for large-scale behavioral targeting, wherein the computer processor is configured to perform the steps of:

• receiving training data that is processed raw data of user behavior;
• generating selected features by performing feature selection on the training data;
• generating feature vectors from the selected features;
• initializing weights of a behavioral targeting model, wherein the behavioral targeting model is based on a Poisson regression, by:
• scanning the feature vectors once,
• allocating each of the weights as a normalized co-occurrence of a target and a feature,
• generating a weight matrix whose dimensionality is a total number of targets by a total number of features,
• generating a plurality of weight vectors for each of the selected features from the weight matrix;
• and
• updating the weight vectors of the behavioral targeting model by scanning iteratively the feature vectors using a multiplicative recurrence.

A non-transitory computer readable medium carrying one or more instructions for large-scale behavioral targeting, wherein the one or more instructions, when executed by one or more processors, cause the one or more processors to perform the steps of:

• receiving training data that is processed raw data of user behavior;
• generating selected features by performing feature selection on the training data;
• generating feature vectors from the selected features;
• initializing weights of a behavioral targeting model, wherein the behavioral targeting model is based on a Poisson regression, by:
• scanning the feature vectors once,
• allocating each of the weights as a normalized co-occurrence of a target and a feature,
• generating a weight matrix whose dimensionality is a total number of targets by a total number of features,
• generating a plurality of weight vectors for each of the selected features from the weight matrix;
• and
• updating the weight vectors of the behavioral targeting model by scanning iteratively the feature vectors using a multiplicative recurrence.