US 11,775,884 B2
Eligibility predictions for instant booking in an online marketplace
Yi Hou, Foster City, CA (US); Li Fan, Belmont, CA (US); Trunal Bhanse, Sunnyvale, CA (US); and Andrew Chen, San Francisco, CA (US)
Assigned to Airbnb, Inc., San Francisco, CA (US)
Filed by Airbnb, Inc., San Francisco, CA (US)
Filed on Oct. 25, 2022, as Appl. No. 17/973,166.
Application 17/973,166 is a continuation of application No. 16/169,172, filed on Oct. 24, 2018, granted, now 11,521,135.
Prior Publication US 2023/0052819 A1, Feb. 16, 2023
This patent is subject to a terminal disclaimer.
Int. Cl. G06Q 10/02 (2012.01); G06Q 30/02 (2023.01); H04W 4/02 (2018.01); G06N 20/00 (2019.01); G06Q 30/06 (2023.01); G06Q 30/0204 (2023.01); G06Q 30/0601 (2023.01)
CPC G06Q 10/02 (2013.01) [G06N 20/00 (2019.01); G06Q 30/0205 (2013.01); G06Q 30/0627 (2013.01); H04W 4/025 (2013.01)] 20 Claims
OG exemplary drawing
 
1. A method, comprising:
generating, by a computing system in an online marketplace, training data to train a machine learning model based on data captured via the online marketplace, the data associated with users of the online marketplace, suppliers of services in the online marketplace, and market dynamics in the online marketplace;
training, by the computing system in the online marketplace, the machine learning model using the training data to predict whether only services that can be instantly booked should be listed in response to a request for services in a given location or that both services that can be instantly booked and services that cannot be instantly booked should be provided in response to a request for services in a given location;
analyzing, by the computing system using the machine learning model, a set of features based on a request for service in a given location to generate a prediction value indicating whether only services that can be instantly booked should be provided in response to the request for services in the given location or that both services that can be instantly booked and services that cannot be instantly booked should be provided in response to the request for services in the given location;
based on determining that the prediction value output by the machine learning model indicates that only services that can be instantly booked should be provided in response to the request for services in the given location, performing operations comprising:
generating, by the computing system, a list of a subset of a plurality of services available in the given location comprising only services that can be instantly booked; and
causing, by the computing system, the list with only services that can be instantly booked to be provided to a client device in response to the request for services in the given location; and
based on determining that the prediction value output by the machine learning model indicates that both services that can be instantly booked and services that cannot be instantly booked should be provided in response to the request for services in the given location, performing operations comprising:
generating, by the computing system, a list of services that can be instantly booked and services that cannot be instantly booked; and
causing, by the computing system, the list of services that can be instantly booked and services that cannot be instantly booked to be provided to the client device in response to the request for services in the given location.