Freshness and seasonality-based content determinations

Patent metadata

Field	Value
Publication number	US-10192253-B2
Application number	US-201514797924-A
Country	US
Kind code	B2
Filing date	Jul 13, 2015
Priority date	Sep 21, 2009
Publication date	Jan 29, 2019
Grant date	Jan 29, 2019

Abstract

The relevance or ranking of various dynamically-determined instances of content can be adjusted or otherwise improved based on aspects such as the freshness or seasonality of the content. In many conventional relevance or ranking algorithms, factors such as popularity, performance, and profit are used to determine which content to present to a user, as well as how to display the selected content. Such algorithms do not necessarily reflect domain-specific knowledge very well, and thus fail to accurately select content that is of differing levels appeal at various ages of the content and/or during various seasons of the year. Freshness and/or seasonality adjustment scores can be used to generate improved relevance, selection, or ranking determinations for various categories of content.

First claim

What is claimed is:

1. A system, comprising:
a processor; and
a non-transitory memory device including instructions that, when executed by the processor, cause the system to:
determine a plurality of items available for selection in an electronic inventory;
calculate a cycle score for each item of the plurality of items, the cycle score correlated to a demand cycle associated with at least one category of a respective item, wherein the cycle score is an output of at least one dynamic cyclical function of a plurality of cyclical functions and depends on the least one category of the respective item and an input of time elapsed from start of a repeating cycle;
calculate an age score for each item of the plurality of items, wherein the age score is an output of at least one age function of a plurality of age functions, and depends on an input of time elapsed from a time of first availability of a respective item;
compute a ranking score of each of the plurality of items based at least in part on user behavior associated with each of the plurality of items, the respective cycle score and the respective age score of each of the plurality of items, the user behavior correlated with each dynamic cyclical function and each age function;
generate a ranking of the plurality of items according to the ranking score of each of the plurality of items;
determine demand data for one or more items of the plurality of items;
derive an additive or multiplicative factor for each of the one or more items based on the demand data;
calculate an adjustment score for each of the one or more items, each adjustment score associated with at least one adjustment function of a plurality of adjustment functions and based on the respective additive or the multiplicative factor;
adjust the ranking score for each of the one or more items by an amount corresponding to the adjustment score to generate an adjusted ranking score for each of the one or more items;
determine an adjusted ranking of the plurality of items based at least in part on the adjusted ranking scores of the one or more items; and
generate a display of at least a portion of the plurality of items according to the adjusted ranking.

2. The system of claim 1 , wherein the memory device further includes instructions that, when executed by the processor, cause the system to:
compile a first set of purchase history data;
compile a second set of purchase history data;
determine that the first set of purchase history data differs from the second set of purchase history data by an amount corresponding to a temporal measure; and
time shift at least one age function corresponding to the first set of purchase history data to account for the temporal measure.

3. The system of claim 1 , wherein the memory device further includes instructions that, when executed by the processor, cause the system to:
increase the age score over a first time period, the first time period being measured from the time of first availability of the item; and
decrease the age score for a second time period, the second time period being subsequent to the first time period.

4. The system of claim 1 ,
wherein a first cyclical function of the plurality of cyclical functions is associated with a cycle length of one year, and a second cyclical function of the plurality of cyclical functions is associated with a cycle length of less than a year; and
wherein each of the plurality of cyclical functions is modeled as a set of discrete points, the set of discrete points including one or more of an inflection point, a discontinuity, and an end point.

5. The system of claim 1 , wherein at least a portion of the age functions and the cyclical functions correspond to different categories of items.

6. The system of claim 5 , wherein one or more of the age functions and the cyclical functions are associated with one or more of the items using one or more attributes of the items.

7. The system of claim 1 , wherein at least one of the plurality of cyclical functions and at least one of the age functions provides positive, negative, and zero values at different points in time.

8. The system of claim 1 , wherein the memory device further includes instructions that, when executed by the processor, cause the system to:
apply at least one default function to each item; and
tune the at least one default function for at least some of the items over time to produce at least one optimized function, the at least one optimized function applying to at least one of an item, a class of items, a type of items, a group of items, a category of items, or a sub-category of items, the optimized function further corresponding to an age function or a cyclical function.

9. A computer-implemented method, comprising:
determining a plurality of items available for purchase selection in an electronic inventory;
calculating a cycle score for each item of the plurality of items, the cycle score correlated to a demand cycle associated with at least one category of a respective item, wherein the cycle score is an output of at least one dynamic cyclical function of a plurality of cyclical functions and depends on the at least one category of the respective item and an input of time elapsed from start of a repeating cycle;
calculating an age score for each item of the plurality of items, wherein the age score is an output of at least one age function of a plurality of age functions and depends on the at least one category of the respective item and an input of time elapsed from a time of first availability of a respective item;
computing a ranking score of each of the plurality of items based at least in part on user behavior associated with the each of the plurality of items, the respective cycle score and the respective age score of each of the plurality of items, the user behavior correlated with each dynamic cyclical function and each age function;
computing a ranking of the plurality of items according to the ranking score of each of the plurality of items;
determining demand data for one or more items of the plurality of items;
deriving an additive or multiplicative factor for each of the one or more items based on the demand data;
calculating an adjustment score for each of the one or more items, the adjustment score associated with at least one adjustment function of a plurality of adjustment functions and based on the respective additive or the multiplicative factor;
adjusting the ranking score for each of the one or more items by an amount corresponding to the respective adjustment score to generate an adjusted ranking score for each of the one or more items;
determining an adjusted ranking of the plurality of items based at least in part on the adjusted ranking scores of the one or more items; and
generating a display of at least a portion of the plurality of items for display according to the adjusted ranking.

10. The computer-implemented method of claim 9 , further comprising:
increasing the age score over a first time period, the first time period being measured from the time of first availability of the item; and
decreasing the age score for a second time period, the second time period being subsequent to the first time period.

11. The computer-implemented method of claim 9 , further comprising:
compiling a first set of purchase history data;
compiling a second set of purchase history data;
determining that the first set of purchase history data differs from the second set of purchase history data by an amount corresponding to a temporal measure; and
time shifting at least one age function corresponding to the first set of purchase history data to account for the temporal measure.

Assignees

• A9 Com Inc

Inventors

• Huet Francois
• Sewani Anil A
• Rose Daniel E

Classifications

• G06F17/30876

  Physics · mapped topic

• G06F17/30598

  Physics · mapped topic

• G06F17/30386

  Physics · mapped topic

• G06F17/3053

  Physics · mapped topic

• G06Q10/067

  Enterprise or organisation modelling · CPC title