Amadeus S.a.s.

David Renaudie

Rodrigo Acuna Agost

Renaud Arnoux-Prost

Norbert Lataille

Alexandre Sbragia

Eric Bousquet

Alejandro Ricardo Mottini D'Oliveira

Jacques Bonaud

Mourad Boudia

Nicolas Hauviller

Vincent Boulineau

Benoit Lardeux

Francois Montegut

Eoin Thomas

Mohand Arezki Kessaci

Guillaume Deacken Owanssango

Ahmed Oulabas

Matthieu Gardeux

Giorgio Calandriello

Alessandro Pascali

Papa Birame Sane

Rodrigo Alejandro Acuna Agost

Maria Zuluaga

Alix Lheritier

A method of determining a primary storage location for a data record in a distributed system comprising a plurality of data stores physically located in corresponding geographic locations, includes initialising a machine learning mapping model using topology information of the distributed system, and determining a set of training feature vectors derived from metadata values associated with prior location requests. The model is trained using the training feature vectors and a corresponding set of target primary storage locations. A location request that includes a plurality of metadata values and is associated with a data record is received, and the metadata values are processed to determine a prediction feature vector comprising a plurality of prediction feature values. The model is executed using the prediction feature vector to identify one data store of the plurality of data stores as the primary storage location for the data record associated with the location request.

Machine learning systems and methods for data placement in distributed storage

Data is processed iteratively by a database system with a first cache storing key-value data which resulted from previous iterations of processing input data and a second cache storing aggregated data which resulted from previous iterations of processing key-value data stored in the first cache. In a current iteration, the database system receives further input data related to the input data of the previous iterations, transforms the further input data into further key-value data and stores the further key-value data in the first cache in addition to the stored key-value data which resulted from previous iterations. The database system further processes the further key-value data and the aggregated data stored in the second cache to form updated aggregated data, and stores the updated aggregated data in the second cache for usage in further iterations. The database system also provides the updated aggregated data to at least one client.

Iterative data processing

Computer-implemented methods of providing personalized recommendations to a user of items available in an online system, and related systems. First-level features including context features are computed based upon context data. A first-level machine learning model is then evaluated using the first-level features to generate predictions of user behavior in relation to a plurality of individual items available via the online system. A list of proposed item recommendations is constructed based upon the predictions. Second-level features are computed based upon the context data and list features based upon the list of proposed item recommendations and the corresponding predictions generated by the first-level machine learning model. A second-level machine learning model is evaluated using the second-level features to generate a prediction of user behavior in relation to the list of proposed item recommendations. A personalized list of item recommendations is provided based upon the prediction generated by the second-level machine learning model.

Recommender systems and methods using cascaded machine learning models

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. The selected machine learning model is deployed to a monitoring system that executes the deployed machine learning model to detect anomalies of the monitored system.

System and method for evaluating and deploying unsupervised or semi-supervised machine learning models

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.

Systems and methods for real-time online traveler segmentation using machine learning

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.

Machine learning methods and systems for predicting online user interactions

A computer-implemented reservation method and a corresponding system are utilized for controlling execution of a decision process to maintain data access efficiency upon receipt of a computation inquiry. The method comprises associating to a computer backend machine a configuration file containing at least a decision rule that drives the decision process and that is computed at least from a current value of a statistical indicator and a target value of the statistical indicator; periodically obtaining an updated value of the statistical indicator; upon detection that the updated value is differing from the target value, dynamically updating the configuration file and storing in real-time a recomputed decision rule in the configuration file.

System and method for load distribution in a network

A method, apparatus, and program product implement visual booking operations to search for travel products and/or present travel recommendations associated with travel products to users based upon visual elements in one or more digital images captured by a wearable or mobile device. Visual elements may be extracted and inferred to identify one or more travel destination locations that are geographically remote from a current location of a user, and the identified travel destination locations may be used to search a travel database to identify at least one travel product for travel from a travel origination location to a travel destination location.

Visual booking system

Computer-implemented reservation method and system. The method utilized for controlling the execution of a decision process by a computer backend machine of a computer network upon receipt of a computation inquiry includes associating to the computer backend machine a configuration file containing at least a decision rule that drives the decision process and that is computed at least from a current value of a statistical indicator and a target value of the statistical indicator; periodically obtaining an updated value of the statistical indicator; upon detection that the updated value is differing from the target value, dynamically updating the configuration file which further comprises re-computing the decision rule using the updated value as new current value, and storing in real-time the re-computed decision rule in the configuration file.

Computing system and method for controlling the execution of a decision process to maintain the data access efficiency upon receipt of an availability information inquiry

Growing community of inventors

Valbonne, France

David Renaudie