US 11,734,732 B2
Method, apparatus, and computer program product for determining closing metrics
Brian Mullins, Chicago, IL (US); Matt DeLand, San Francisco, CA (US); Zahra Ferdowsi, Chicago, IL (US); Stephen Lang, Chicago, IL (US); John Stokvis, Chicago, IL (US); Nolan Finn, Chicago, IL (US); and Shafiq Shariff, Chicago, IL (US)
Assigned to GROUPON, INC., Chicago, IL (US)
Filed by Groupon, Inc., Chicago, IL (US)
Filed on Jul. 14, 2021, as Appl. No. 17/375,428.
Application 17/375,428 is a continuation of application No. 15/667,666, filed on Aug. 3, 2017, granted, now 11,120,345.
Application 15/667,666 is a continuation of application No. 15/051,165, filed on Feb. 23, 2016, granted, now 10,558,922, issued on Feb. 11, 2020.
Application 15/051,165 is a continuation of application No. 13/826,757, filed on Mar. 14, 2013, granted, now 9,330,357, issued on May 3, 2016.
Claims priority of provisional application 61/730,046, filed on Nov. 26, 2012.
Claims priority of provisional application 61/709,623, filed on Oct. 4, 2012.
Prior Publication US 2021/0342721 A1, Nov. 4, 2021
This patent is subject to a terminal disclaimer.
Int. Cl. G06Q 30/0282 (2023.01); G06Q 30/0202 (2023.01); G06N 20/00 (2019.01); G06N 5/02 (2023.01); G06N 5/04 (2023.01); G06Q 10/0635 (2023.01); G06Q 10/0639 (2023.01); G06Q 10/067 (2023.01); G06Q 30/0601 (2023.01); G06Q 40/00 (2023.01); G06Q 10/0631 (2023.01); G06N 20/10 (2019.01); G06Q 30/0201 (2023.01)
CPC G06Q 30/0282 (2013.01) [G06N 5/02 (2013.01); G06N 5/04 (2013.01); G06N 20/00 (2019.01); G06N 20/10 (2019.01); G06Q 10/067 (2013.01); G06Q 10/0635 (2013.01); G06Q 10/0639 (2013.01); G06Q 10/06311 (2013.01); G06Q 10/06315 (2013.01); G06Q 10/06393 (2013.01); G06Q 30/0201 (2013.01); G06Q 30/0202 (2013.01); G06Q 30/0609 (2013.01); G06Q 40/00 (2013.01)] 20 Claims
OG exemplary drawing
 
1. An apparatus comprising at least one processor and at least one memory including computer program code, the at least one memory and the computer program code configured to, with the processor, cause the apparatus to at least:
automatically perform at least one of automated forward selection, automated backward elimination, or a combination thereof on a classifying model to select a set of determinative attributes from attributes comprising a provider, a geographic area in which the respective provider is located, a provider category, a lead source, and historical data relating to the one or more providers, wherein the determinative attributes are selected by at least the processor based on which attributes stabilize the classifying model;
train a set of classifying models to utilize the set of determinative attributes, wherein each classifying model indicates a probability of close with a particular provider within a respective time period;
supply the set of trained classifying models with a dataset, wherein the dataset comprises an indication of one or more providers in a given geographic area, a plurality of available attributes corresponding to the one or more providers, wherein the available attributes comprise at least one of a provider category, a lead source or historical data relating to the one or more providers; and
determine a probability of close with the particular provider for each of the respective time periods, wherein the probability of close indicates the probability that the particular provider will contract with a promotion service to offer a promotion within the respective time period, wherein the promotion is offered to a consumer for purchase from the promotion service in exchange for at least one of a discounted service or discounted product from the provider.