Leon R Cho, 50Ponte Vedra, FL

2018021, Aug 2, 2018

Feb 1, 2017

15/421438

- Menlo Park CA, US
Robert Oliver Burns Zeldin - Los Altos CA, US
Sushma Nagesh Bannur - Cupertino CA, US
Rami Mahdi - San Mateo CA, US
Rubinder Singh Sethi - San Francisco CA, US
Shyamsundar Rajaram - San Francisco CA, US
Leon R. Cho - Santa Clara CA, US

G06N 99/00
G06Q 30/02
G06N 5/04

An online system receives content items, for example, from content providers and sends the content items to users. The online system uses machine-learning models for predicting whether a user is likely to interact with a content item. The online system uses stored user interactions to measure the model performance to determine whether the model can be used online. The online system determines a baseline model using stored user interactions. The online system determines whether the machine-learning model performs better than the baseline model or worse for each content provider. The online system determines whether to approve the model for online use based on an aggregate normalized performance metric, for example, a metric representing the fraction of content providers for which the model performs better than the baseline. If the online system determines to reject the model, the online system retrains the model.

2017018, Jun 29, 2017

Dec 29, 2015

14/983432

- Menlo Park CA, US
Leon R. Cho - Santa Clara CA, US
Yuval Israel Oren - Pacifica CA, US
Ying Qin - Saratoga CA, US

G06Q 30/02

An online advertising system evaluates advertising opportunities for online advertising publishers. The online advertising system tracks online users via various tracking methods to receive advertising data and user information for the online users. The online advertising system identifies and segments the online users based on segmenting criteria that are associated with some interest topics (e.g., demographical information). The system calculates projected advertising revenue for each audience segment and generates an inventory optimization dashboard based on the calculated revenue. The inventory optimization dashboard helps the advertising publishers better understand the online advertising traffic and better optimize their advertising inventory. For example, the advertising publishers may advertise to specific audience segments which tend to purchase the advertised products or services.

2016030, Oct 13, 2016

Apr 7, 2015

14/681061

- Menlo Park CA, US
Peng Fan - Castro Valley CA, US
Zhimin Chen - Santa Clara CA, US
Leon R. Cho - Santa Clara CA, US

G06Q 30/02

An online system receives information describing a target group of online system users from a third party system that includes one or more user properties, which may identify actions to be performed by an online system user for inclusion in the target group. Additionally, information describing the target group includes metadata associated with the user properties identifying access to the user properties by additional third party systems. If an additional third party system requests access to the target group or to the user properties describing the target group, the online system determines whether the additional third party system is authorized to access the target group or the user properties based on the metadata. Further, the online system determines an amount of compensation the third party system is to receive if the additional third party system is authorized to access the target group or the user properties based on the metadata.

2016023, Aug 11, 2016

Feb 6, 2015

14/616543

- Menlo Park CA, US
Sue Ann Hong - San Francisco CA, US
Leon R. Cho - Santa Clara CA, US

G06Q 30/02
G06Q 50/00

A social networking system receives an advertisement request including multiple sets of targeting criteria. To increase the number of users eligible to be presented with the advertisement request, the social networking system generates a cluster group associated with each set of targeting criteria. A cluster group associated with a set of targeting criteria includes users satisfying the targeting criteria and additional users that do not satisfy the targeting criteria. The social networking system determines an amount of overlap between the cluster groups. If the amount of overlap equals or exceeds a threshold value, the social networking system combines the cluster groups to generate an overall group associated with the advertisement request.

2016003, Feb 4, 2016

Jul 29, 2014

14/446176

- Menlo Park CA, US
Weiwei Ding - Fremont CA, US
Xingyao Ye - Mountain View CA, US
Leon Cho - Menlo Park CA, US

G06Q 30/02

An online system allows content items to be targeted based on interests associated with users. When the online system receives a request to specify targeting criteria associated with a content item, the online system provides an interface to specify targeting criteria. As the online system receives input specifying an interest for inclusion in targeting criteria, the online system retrieves stored interests associated with online system users. Each interest stored by the online system is associated with a type. For example, a type associated with a stored interest indicates whether the interest is from a set of user-generated keywords, from a set of semantic topics mapped from the keywords, or from a set of manually curated broad categories. To avoid confusion from overlap in the types of interests, the online system applies rules to stored interests matching at least a portion of the input to select a set of interests.