Amazon.com

About: Amazon.com is a company organization based out in Seattle, Washington, United States. It is known for research contribution in the topics: Service (business) & Service provider. The organization has 13363 authors who have published 17317 publications receiving 266589 citations.

Probabilistic demand forecasting at scale

Abstract: We present a platform built on large-scale, data-centric machine learning (ML) approaches, whose particular focus is demand forecasting in retail. At its core, this platform enables the training and application of probabilistic demand forecasting models, and provides convenient abstractions and support functionality for forecasting problems. The platform comprises of a complex end-to-end machine learning system built on Apache Spark, which includes data preprocessing, feature engineering, distributed learning, as well as evaluation, experimentation and ensembling. Furthermore, it meets the demands of a production system and scales to large catalogues containing millions of items.We describe the challenges of building such a platform and discuss our design decisions. We detail aspects on several levels of the system, such as a set of general distributed learning schemes, our machinery for ensembling predictions, and a high-level dataflow abstraction for modeling complex ML pipelines. To the best of our knowledge, we are not aware of prior work on real-world demand forecasting systems which rivals our approach in terms of scalability.

ETA Prediction with Graph Neural Networks in Google Maps

Abstract: Travel-time prediction constitutes a task of high importance in transportation networks, with web mapping services like Google Maps regularly serving vast quantities of travel time queries from users and enterprises alike. Further, such a task requires accounting for complex spatiotemporal interactions (modelling both the topological properties of the road network and anticipating events---such as rush hours---that may occur in the future). Hence, it is an ideal target for graph representation learning at scale. Here we present a graph neural network estimator for estimated time of arrival (ETA) which we have deployed in production at Google Maps. While our main architecture consists of standard GNN building blocks, we further detail the usage of training schedule methods such as MetaGradients in order to make our model robust and production-ready. We also provide prescriptive studies: ablating on various architectural decisions and training regimes, and qualitative analyses on real-world situations where our model provides a competitive edge. Our GNN proved powerful when deployed, significantly reducing negative ETA outcomes in several regions compared to the previous production baseline (40+% in cities like Sydney).

Using qualifications of users to facilitate user performance of tasks

Abstract: A method, system, and computer-readable medium is described for facilitating interactions between task requesters who have tasks that are available to be performed and task performers who are available to perform tasks. In some situations, the tasks to be performed are human performance tasks that use cognitive and other mental skills of human task performers, such as to employ judgment, perception and/or reasoning skills of the human task performers. In addition, in some situations the performance of tasks is facilitated by using information about qualifications of task performers that are related to performance of tasks Various types of qualifications about task performers can be specified, and qualification information can be specified and used in various ways, such as to limit task performance and/or access to other functionality to users having appropriate qualifications.

Amalgamated display comprising dissimilar display devices

Abstract: A reflective display, such as an electrophoretic display (EPD), and an emissive display, such as a backlit liquid crystal display, may be combined to form an amalgamated display. This combination may include layering one display atop the other, alternating reflective and emissive display elements, or otherwise interspersing reflective and emissive display elements with one another. Images on the amalgamated display may be presented using either reflective or emissive modes or a combination of the two, depending upon factors such as refresh rate, power consumption, presence of color and/or video, and so forth.

Electronic device with haptic feedback

Abstract: Haptic feedback may be provided to a user of an electronic device, such as an electronic book reader device, to confirm receipt of user input or otherwise convey information to the user. The haptic feedback may be provided more quickly than a display update time of a display of the electronic device. Different patterns, durations, and/or intensities of haptic feedback may be used in response to different events.