Abstract: A contextual label compression framework is presented that uses trained sequence to sequence models. A set of training data including received queries and related content can be processed to generate sequences of semantic encodings. These sequences can be used to train the sequence to sequence models, in order to be able to predict queries for instances of content when the relevant information for those instances is processed by the model. When such information is received for an instance, that information can be processed to generate a semantic encoding sequence which can then be processed by the model. A resulting semantic sequence output by the model can be segmented and decoded to produce a set of relevant queries for the instance of content. This information can then be provided to an entity associated with the instance of content for purposes in managing aspects relating to that content.

Abstract: Large scale time series forecasting models are described that leverage deep learning. This can include the utilization of temporal convolution networks and long short-term memory (LTSM) units of recurrent neural networks (RNNS). The model architectures can handle very large data sets with a large number of time series. Diverse scaling is provided through use of a scale-free leveling network architecture, and sparse time-series data is managed using a gating approach. A deep temporally regularized matrix factorization approach to time-series forecasting is utilized that can leverage correlations between the time series during both training and prediction.

Abstract: Systems and methods presented herein create a graph of data within a data set, such as items within an electronic catalog. The nodes of the graph may represent data items, such as items within the electronic catalog. Links or edges can be created between nodes of the graph representative of a data-metric of interest. For example, links or edges can be created between nodes of the graph representative of co-access of items. A diversified page rank process can be performed with respect to a particular node in the graph. This process can use positive or negative bias toward specific attributes to dynamically re-weight edges before and/or during the walk.