Extracting product drag effect from transaction records

Patent metadata

Field	Value
Publication number	US-11416877-B2
Application number	US-201715715529-A
Country	US
Kind code	B2
Filing date	Sep 26, 2017
Priority date	Sep 26, 2017
Publication date	Aug 16, 2022
Grant date	Aug 16, 2022

Abstract

A method, computer system, and a computer program product for computing a product drag effect is provided. The present invention may include receiving a plurality of transaction record data. The present invention may then include tuning a plurality of parameters based on the received transaction record data. The present invention may further include determining a product drag frequency based on the authorized parameter tuning and received transaction record data. The present invention may then include calculating a drag probability based on the determined product drag frequency. The present invention may then include deriving an observation from the calculated drag probability. The present invention may lastly include outputting the derived observation to a user.

First claim

What is claimed is:

1. A method implemented on a processing device configured to execute the method, the method automatically determining a temporary price drop of an item for purchase, the method comprising:
receiving, by the processing device, a plurality of transaction record data;
receiving tuning, by the processing device, of at least one of a plurality of parameters, from a user, based on the received transaction record data;
determining, by the processing device, a product drag frequency, indicating a number of the plurality of transactions in which both the item for purchase and a second item occur, based on the parameter tuning and received transaction record data, by constructing a complete directed graph which ranks a top-k list of leader products in decreasing order of out degrees, and a top-k list of follower products in decreasing order of in degrees;
calculating, by the processing device, a drag probability based on the determined product drag frequency;
receiving, by the processing device, a query from the user to obtain at least one observation relating to the item for purchase from the calculated drag probability, based on a user-specified analysis;
reducing, by the processing device, a price of the item for purchase based on the received user query; and
outputting, by the processing device, the reduced price of the item to the user.

2. The method of claim 1 , wherein the plurality of tuned parameters is selected from the group consisting of one or more physical product attributes, one or more physical parameters, and one or more analytic parameters.

3. The method of claim 1 , wherein the complete directed graph has a plurality of edges based on the plurality of transaction record data wherein a product rank is based on a sum of weights on incoming or outgoing arcs, or on a corresponding edge weight in a complete directed graph, and wherein a top portion of the complete directed graph depicts a leader product and a bottom portion of the complete directed graph depicts a follower product.

4. The method of claim 3 , wherein the drag probability is calculated by translating the determined product drag frequency, represented in a frequency matrix, into a corresponding probability, represented in a doubly stochastic probability matrix, such that the sum of every row and column in the probability matrix is equal to one.

5. The method of claim 4 , further comprising:
determining, by the processing device, a magnitude of pairwise drag effect based on the calculated drag probability.

6. The method of claim 1 , wherein the at least one observation from the calculated drag probability includes a leader and follower score, a top-k list of local leader products, a top-k list of local follower products, a top-k list of global leader products, and a top-k list of global follower products.

7. The method of claim 1 , wherein the output is customizable by the user.

8. A computer system for automatically determining a temporary price drop of an item for purchase, the method comprising:
one or more processors, one or more computer-readable memories, one or more computer-readable tangible storage medium, and program instructions stored on at least one of the one or more tangible storage medium for execution by at least one of the one or more processors via at least one of the one or more memories, wherein the computer system is capable of performing a method comprising:
receiving, by the one or more processors, a plurality of transaction record data;
receiving tuning, by the one or more processors, of at least one of a plurality of parameters, from a user, based on the received transaction record data;
determining, by the one or more processors, a product drag frequency, indicating a number of the plurality of transactions in which both the item for purchase and a second item occur, based on the parameter tuning and received transaction record data, by constructing a complete directed graph which ranks a top-k list of leader products in decreasing order of out degrees, and a top-k list of follower products in decreasing order of in degrees;
calculating, by the one or more processors, a drag probability based on the determined product drag frequency;
receiving, by the one or more processors, a query from the user to obtain at least one observation relating to the item for purchase from the calculated drag probability, based on a user-specified analysis;
reducing, by the one or more processors, a price of the item for purchase based on the received user query; and
outputting, by the one or more processors, the reduced price of the item to the user.

9. The computer system of claim 8 , wherein the plurality of tuned parameters is selected from the group consisting of one or more physical product attributes, one or more physical parameters, and one or more analytic parameters.

10. The computer system of claim 8 , wherein the complete directed graph has a plurality of edges based on the plurality of transaction record data wherein a product rank is based on a sum of weights on incoming or outgoing arcs, or on a corresponding edge weight in a complete directed graph, and wherein a top portion of the complete directed graph depicts a leader product and a bottom portion of the complete directed graph depicts a follower product.

11. The computer system of claim 10 , wherein the drag probability is calculated by translating the determined product drag frequency, represented in a frequency matrix, into a corresponding probability, represented in a doubly stochastic probability matrix, such that the sum of every row and column in the probability matrix is equal to one.

12. The computer system of claim 11 , further comprising:
determining, by the one or more processors, a magnitude of pairwise drag effect based on the calculated drag probability.

13. The computer system of claim 8 , wherein the at least one observation from the calculated drag probability includes a leader and follower score, a top-k list of local leader products, a top-k list of local follower products, a top-k list of global leader products, and a top-k list of global follower products.

14. The computer system of claim 8 , wherein the output is customizable by the user.

15. A computer program product for automatically determining a temporary price drop of an item for purchase, the method comprising:
one or more computer-readable storage media and program instructions stored on at least one of the one or more tangible storage media, the program instructions executable by a processor to cause the processor to perform a method comprising:
receiving, by the processor, a plurality of transaction record data;
receiving tuning, by the processor, of at least one of a plurality of parameters, from a user, based on the received transaction record data;
determining, by the processor, a product drag frequency, indicating a number of the plurality of transactions in which both the item for purchase and a second item occur, based on the parameter tuning and received transaction record data, by constructing a complete directed graph which ranks a top-k list of leader products in decreasing order of out degrees, and a top-k list of follower products in decreasing order of in degrees;
calculating, by the processor, a drag probability based on the determined product drag frequency;
receiving, by the processor, a query from the user to obtain at least one observation relating to the item for purchase from the calculated drag probability, based on a user-specified analysis;
reducing, by the processor, a price of the item for purchase based on the received user query

Assignees

• IBM

Inventors

• Basu Aditya
• Chong Jeanine C
• Garg Dinesh
• Jain Alankar
• Kannan Aswin
• Narayanam Ramasuri
• Squillante Mark S
• Toft-Nielsen Christian
• Yau Jessica Lee

Classifications

• G06Q40/12

  Accounting · CPC title

• G06Q30/0201 Primary

  Market modelling; Market analysis; Collecting market data · CPC title