Abstract: A computer implemented method for controlling resources comprising is presented. The method comprises determining an evolution index for a second time period with respect to a first time period, determining a forecasting index for a first forecasting time period with respect to a starting forecasting time period by dividing the evolution index for the first forecasting time period with respect to the starting forecasting time period through the evolution index for a second forecasting time period with respect to the starting forecasting time period, determining at least one forecasting value of the requirement of the resources in a future time period by multiplying a starting value corresponding to the requirement for resources with the forecasting index for the future time period, and applying the at least one forecasting value to control the resources.

Abstract: Methods of evaluating and deploying machine learning models for anomaly detection of a monitored system and related systems. Candidate machine learning algorithms are configured for anomaly detection of the monitored system. For each combination of candidate machine learning algorithm with type of anomalous activity, training and cross-validation sets are drawn from a benchmarking dataset. Using each of the training and cross-validation sets, a machine-learning model is trained and validated using the cross-validation set with average precision as a performance metric. A mean average precision value is then computed across these average precision performance metrics. A ranking value is computed for each candidate machine learning algorithm, and a machine learning algorithm is selected from the candidate machine learning algorithms based upon the computed ranking values.

Abstract: Methods and computing apparatus for real-time online traveler segmentation. A machine learning classifier may be trained using computed feature vectors and associated tags corresponding with records in a training set. A machine learning classifier receives a feature vector comprising values of the plurality of features corresponding with an unidentified user in an online context. The machine learning classifier may determine an estimate of whether the unidentified user is a member or a non-member of a predetermined traveler category.

Abstract: Methods and computing apparatus for retrieving records relating to content placement events and records relating to user interaction events. A set of enriched training feature vectors is computed from raw feature values, and used with interaction event tags to train a machine learning model. Information is received relating to an online content placement slot and information is received relating to a user to whom content within the online content placement slot will be displayed. An enriched estimation feature vector is computed based upon a content item selected for placement within the online content placement slot, the information relating to the user, and the information relating to the online content placement slot. A machine learning model is executed to determine an estimate of likelihood of the user interacting with the selected content item, based upon the enriched estimation feature vector.

Abstract: Methods of evaluating and deploying machine learning models for anomaly detection of a monitored system and related systems. Candidate machine learning algorithms are configured for anomaly detection of the monitored system. For each combination of candidate machine learning algorithm with type of anomalous activity, training and cross-validation sets are drawn from a benchmarking dataset. Using each of the training and cross-validation sets, a machine-learning model is trained and validated using the cross-validation set with average precision as a performance metric. A mean average precision value is then computed across these average precision performance metrics. A ranking value is computed for each candidate machine learning algorithm, and a machine learning algorithm is selected from the candidate machine learning algorithms based upon the computed ranking values.

Abstract: Methods and computing apparatus for real-time online traveler segmentation. A machine learning classifier may be trained using computed feature vectors and associated tags corresponding with records in a training set. A machine learning classifier receives a feature vector comprising values of the plurality of features corresponding with an unidentified user in an online context. The machine learning classifier may determine an estimate of whether the unidentified user is a member or a non-member of a predetermined traveler category.

Abstract: Methods and computing apparatus for retrieving records relating to content placement events and records relating to user interaction events. A set of enriched training feature vectors is computed from raw feature values, and used with interaction event tags to train a machine learning model. Information is received relating to an online content placement slot and information is received relating to a user to whom content within the online content placement slot will be displayed. An enriched estimation feature vector is computed based upon a content item selected for placement within the online content placement slot, the information relating to the user, and the information relating to the online content placement slot. A machine learning model is executed to determine an estimate of likelihood of the user interacting with the selected content item, based upon the enriched estimation feature vector.

Abstract: Methods and computing apparatus for intelligent adaptive bidding in an automated online exchange network. A message comprising a bid request is received that includes site and user information relating to an available ad slot. A ranked list of offers is generated based at least in part on the site and user information. For each offer in the ranked list, an offer-level estimate of probability of user interaction with the offer is computed. For at least one combination of offers in the ranked list, an ad-level bid price is computed based on at least the computed offer-level estimates of probability of user interaction, corresponding offer-level interaction revenues, and an aggressiveness parameter that controls aggressiveness of bid pricing. Machine learning models for predicting behavior of online users are able to automatically determine estimates of probability of user interaction with online content elements based upon aggregated behavior of prior users in similar contexts.

Abstract: Methods, systems, and computer program products for optimizing schedules for a plurality of flights in a network of flights. the schedules for the flights may be received. In general, the schedules indicate, for each flight, a departure point, an arrival point, a departure time, and an arrival time. The schedules may be globally optimized to identify one or more schedule adjustments for one or more of the flights that results in an increase in a schedule connection value associated with the schedules, where the global optimization is based at least in part on one scheduling rule that constrains combinability of the flights in the network of flights.