Amazon Technologies, Inc.

Zhihao Cen

Balakrishnan Narayanaswamy

Jeffrey B Maurer

Deepak Bhatia

Ali Sadighian

Jingchen Wu

Kari E J Torkkola

Jingqiao Zhang

Wen-Yu Hua

Alexander Matthew Lamb

Ru He

Techniques described herein include a method and system for item demand forecasting that utilizes machine learning techniques to generate a set of quantiles. In some embodiments, several item features may be identified as being relevant to an item forecast and may be provided as inputs to a regression module, which may calculate a set of quantiles for each item. A set of quantiles may comprise a number of confidence levels or probabilities associated with calculated demand values for an item. In some embodiments, costs associated with the item may be used to select an appropriate quantile associated (e.g., based on a corresponding confidence level). In some embodiments, an item demand forecast may be generated based on the calculated demand value associated with the selected quantile. In some embodiments, one or more of the item may be automatically ordered based on that item demand forecast.

Demand forecasting via direct quantile loss optimization

Techniques for computing a feature based on variables may be provided. For example, historical realizations associated with a first variable may be accessed. The first variable may be associated with an item. Realizations of the first variable may be based on one or more factors associated with the item. Historical realization of a second variable associated with the item may also be accessed. The historical realizations of the first and second variables may be analyzed to generate an expected realization of the first variable as a function of the second variable. The feature may be computed based on the generated function.

Efficiently computing a feature based on a plurality of variables

Growing community of inventors

Bellevue, WA, United States of America

Zhihao Cen