公开(公告)号：US20170140414A1

公开(公告)日：2017-05-18

申请号：US14942225

申请日：2015-11-16

Applicant: ORACLE INTERNATIONAL CORPORATION

Inventor： Maxime COHEN ,  Jeremy KALAS ,  Kiran PANCHAMGAM ,  Georgia PERAKIS

IPC: G06Q30/02

CPC classification number: G06Q30/0235

Abstract: Systems, methods, and other embodiments associated with determining a promotion price schedule for each item in a group are described. In one embodiment, a method includes computing an item coefficient that corresponds to a change in a value of an objective function when the item is priced at the promotion price. The objective function is based on a multiple product demand model. An item coefficient is computed for each item, each time period in the price schedule, and each promotion price in a price ladder for the item. An approximate objective function is formulated that includes products of item coefficients and binary decision variables. The item coefficients, the approximate objective function, and constraints are provided to an optimizer that determines values of the decision variables that maximize the approximate objective function. A promotion price schedule is created for each item based on values of the decision variables.

公开(公告)号：US20230096633A1

公开(公告)日：2023-03-30

申请号：US17449112

申请日：2021-09-28

Applicant: Oracle International Corporation ,  MASSACHUSETTS INSTITUTE OF TECHNOLOGY

Inventor： Leann THAYAPARAN ,  Kiran V. PANCHAMGAM ,  Setareh BORJIAN ,  Georgia PERAKIS

IPC: G06Q10/06 ,  G06N20/20 ,  G06K9/62 ,  G06Q10/08

Abstract: Embodiments generate an optimized demand model for a retail item. Embodiments train a tree ensemble machine learning model comprising a plurality of trees, the training comprising storing upper bounds for each of the trees, the trees comprising levels and branches that correspond to the demand features that influence demand for the item. Embodiments generate an objective function for the demand model. At a top split of each tree, embodiments determine optimal child nodes using the stored upper bounds and calculate a new feasible region for each tree. Using bounds on the new feasible region, embodiments move down each tree to a next level of splits and generate the optimized demand model when a leaf node of every tree has been reached.

公开(公告)号：US20240303577A1

公开(公告)日：2024-09-12

申请号：US18666037

申请日：2024-05-16

Applicant: Oracle International Corporation ,  MASSACHUSETTS INSTITUTE OF TECHNOLOGY

Inventor： Leann THAYAPARAN ,  Kiran V. PANCHAMGAM ,  Setareh BORJIAN ,  Georgia PERAKIS

IPC: G06Q10/067 ,  G06F18/214 ,  G06N20/20 ,  G06Q10/08 ,  G06Q10/087

CPC classification number: G06Q10/067 ,  G06F18/2148 ,  G06N20/20 ,  G06Q10/08 ,  G06Q10/087

Abstract: Embodiments generate and train an optimized demand model for predicting a demand of an item. Embodiments receive a plurality of trees, each of the plurality of trees including one or more levels of splits and a plurality of nodes, each of the plurality of nodes corresponding to a demand feature that influences demand for the item. Embodiments store a first bound as a current bound for each of the plurality of trees. Starting at a top split of each of the plurality of trees, embodiments select a first demand feature that a greatest number of the plurality of trees split on. Embodiments optimize the first demand feature using the stored current bound to generate a second bound. Embodiments store the second bound as the current bound for each of the plurality of trees and move down each of the plurality of trees to a next level of splits.

公开(公告)号：US20190066128A1

公开(公告)日：2019-02-28

申请号：US15685116

申请日：2017-08-24

Applicant: ORACLE INTERNATIONAL CORPORATION ,  MASSACHUSETTS INSTITUTE OF TECHNOLOGY

Inventor： Lennart BAARDMAN ,  Tamar COHEN ,  Setareh BORJIAN BOROUJENI ,  Kiran PANCHAMGAM ,  Georgia PERAKIS

IPC: G06Q30/02

Abstract: Systems, methods, and other embodiments associated with predicting customer behavior are described. The method can include identifying a group comprising customers who satisfy a defined criterion, and receiving input that identifies a factor that influences a decision by the customers to purchase a product. A likelihood that the factor will induce the customers in the group to purchase the product is generated. A customer influence on the generated likelihood is estimated independently of data expressly identifying relationships between the customers in the group. The likelihood is modified by combining the likelihood and the customer influence according to a predictive model, and one or more of the customers eligible for a promotional offer related to the product is identified based, at least in part, on the modified likelihood. Transmission of the promotional offer is controlled to transmit the promotional offer to the identified customers in the group.