US 10,832,268 B2Granted

Modeling customer demand and updating pricing using customer behavior data

AssigneeInternational Business Machines Corporation

InventorsNorbert M. Binkiewicz, Junlei Chen, Elizabeth J. Chester, Prafulla N. Dawadi, Robert K. Parkin, Emrah Zarifoglu

Life of this patent

Estimating the term…

patentgrep

Loading patent…

Abstract

In an aspect of the invention, a computer-implemented method includes: receiving, by a computing device via computer network, a plurality of session data records indicating computer network browsing activity between a plurality of client devices and a merchant server hosting an online store; aggregating, by the computing device, a subset of the plurality of session data records for a single product, of a plurality of products, identified in the session data records and offered for purchase by the online store; extracting, by the computing device, features from the aggregated subset of session data records relating to customer demand for a the single product; modeling, by the computing device, customer demand for the single product based on the extracted features; optimizing, by the computing device, a price for the single product based on results of the modeling; and publishing, by the computing device, the optimized price.

Claims20

Dependent claims

A computer-implemented method comprising:

receiving, by a computing device via computer network, a plurality of session data records indicating computer network browsing activity between a plurality of client devices and a merchant server hosting an online store, the plurality of session data records being recorded based on occurrences of shopping-related events including accessing a webpage describing a single product of a plurality of products, adding the single product to an online shopping cart, and purchasing the single product from the online shopping cart, and wherein each of the plurality of session data records corresponds to a particular shopping-related event and identifies a price of the single product, a shipping speed of the single product, and a customer feedback rating of the particular product at a time of the particular shopping-related event;
aggregating, by the computing device, a subset of the plurality of session data records for the single product, of the plurality of products, identified in the session data records and offered for purchase by the online store, the aggregated subset of session data records identifying demand activity for the single product by time period, including views of the single product, cart additions of the single product, and purchases of the single product, and further identifying an average price of the single product, an average shipping speed of the single product, and an average customer feedback rating of the single product within a particular time period when the single product was viewed, within a particular time period when the single product was added to the online shopping cart, and within a particular time period when the single product was purchased from the online shopping cart;
preprocessing, by the computing device, the aggregated subset of session data records by interpolating missing data for at least one time period;
extracting, by the computing device, features from the aggregated subset of session data records relating to customer demand for the single product, the features including at least one from the group consisting of a centered average user rating and a log value of a quantity of items purchased;
modeling, by the computing device, customer demand for the single product based on the extracted features and using a regression of sales versus price;
determining, by the computing device, an optimized price for the single product based on results of the modeling and rules provided by an administrator;
and
publishing, by the computing device, the optimized price on the webpage describing the single product.

5 more elements

A computer program product for modeling customer demand based on a plurality of session data records and optimizing price, the computer program product comprising a non-transitory computer readable storage medium having program instructions embodied therewith, the program instructions executable by a computing device to cause the computing device to:

monitor computer network browsing activity between a plurality of client devices and a merchant server;
generate the plurality of session data records having details regarding the computer network browsing activity between the plurality of client devices and the merchant server hosting an online store, the plurality of session data records being generated based on occurrences of shopping-related events including accessing a webpage describing a single product of a plurality of products, adding the single product to an online shopping cart, and purchasing the single product from the online shopping cart, and wherein each of the plurality of session data records corresponds to a particular shopping-related event and identifies a price of the single product, a shipping speed of the single product, and a customer feedback rating of the particular product at a time of the particular shopping-related event;
aggregate a subset of the plurality of session data records for the single product, of the plurality of products, identified in the session data records and offered for purchase by the online store, the aggregated subset of session data records identifying demand activity for the single product by time period, including views of the single product, cart additions of the single product, and purchases of the single product, and further identifying an average price of the single product, an average shipping speed of the single product, and an average customer feedback rating of the single product within a particular time period when the single product was viewed, within a particular time period when the single product was added to the online shopping cart, and within a particular time period when the single product was purchased from the online shopping cart;
preprocess the aggregated subset of session data records by interpolating missing data for at least one time period;
extract features from the aggregated subset of session data records relating to customer demand for the single product, the features including at least one from the group consisting of a centered average user rating and a log value of a quantity of items purchased;
model customer demand for the single product based on the extracted features and using a regression of sales versus price;
a determine an optimized price for the single product based on results of the modeling and rules provided by an administrator;
and
publish the optimized price on the webpage describing the single product.

6 more elements

A system comprising:

a CPU, a computer readable memory and a non-transitory computer readable storage medium associated with a computing device;
program instructions to gather session level data from online customer retail activity, the session level data being gathered based on occurrences of shopping-related events including accessing a webpage describing a single product of a plurality of products, adding the single product to an online shopping cart, and purchasing the single product from the online shopping cart, and wherein the session level data corresponds to shopping-related events and identifies a price of the single product, a shipping speed of the single product, and a customer feedback rating of the particular product at a time of each of the shopping-related events;
program instructions to aggregate, for the single product, the session level data pertaining to the single product, the aggregated session level data identifying demand activity for the single product by time period, including views of the single product, cart additions of the single product, and purchases of the single product, and further identifying an average price of the single product, an average shipping speed of the single product, and an average customer feedback rating of the single product within a particular time period when the single product was viewed, within a particular time period when the single product was added to the online shopping cart, and within a particular time period when the single product was purchased from the online shopping cart;
program instructions to substitute values by interpolation as a replacement for missing data in the aggregated session level data to generate a complete data set;
program instructions to extract one or more features of online customer behavior based on an analysis of the complete data set, the features including at least one from the group consisting of a centered average user rating and a log value of a quantity of items purchased;
program instructions to determine a level of customer demand for the product based on the one or more features of online customer behavior and using a regression of sales versus price;
and
program instructions to determine a modified price of the product on the webpage describing the single product based on the level of customer demand and rules provided by an administrator,
wherein the program instructions are stored on the computer readable storage medium for execution by the CPU via the computer readable memory.

6 more elements

Dependencies are inferred from the claim text.

Facts

Application: 15/409,806Filed 19 Jan 2017
Published: US 2018/0204233 A119 Jul 2018
Granted: 10 Nov 2020
Term ends: Not estimatedThe source records don’t support an estimate.

Classification5 codes

G06Q 30/0206
Market modelling; Market analysis; Collecting market data: price or cost determination based on market factors
G06Q 30/0633
Electronic shopping [e-shopping]: managing shopping lists, e.g. compiling or processing purchase lists
H04L 67/566
Provisioning of proxy services: grouping or aggregating service requests, e.g. for unified processing
G06Q
Information and communication technology [ict] specially adapted for administrative, commercial, financial, managerial