Abstract:
A method is provided for building a user interest profile, including the following method operations: identifying features of each of a plurality of articles; for a given user, logging views of one or more of the plurality of articles; for each view, measuring a corresponding dwell time for the view by the given user; applying a weight to each view based on the corresponding measured dwell time; determining user interest scores for features of the one or more of the plurality of articles based on the weighted views; generating a user interest profile for the given user based on the user interest scores.
Abstract:
A method for online advertising includes: receiving a request for a content stream from a client device; embedding an advertisement in the content stream, and transmitting the content stream to the client device; determining a scroll dwell time of the advertisement when the content stream is presented on the client device; determining a level of performance of a guaranteed presentation amount associated with the advertisement, the level of performance based on the scroll dwell time of the advertisement. In another embodiment, candidate advertisements are identified for presentation in the content stream; for each candidate, an expected cost per time unit (eCPTU) of exposure is determined; one of the candidate advertisements is selected for inclusion in the content stream based on the eCPTU's; the content stream is transmitted to the client device.
Abstract:
Method, system, and programs for identifying a target metric. In one example, at least one first type of metric computed based on a first period associated with a first length of time is measured for each of a plurality of users. At least one second type of metric computed based on a second period associated with a second length of time is measured for each of the plurality of users. The second length of time is larger than the first length of time. Correlations between each of the at least one first type of metric and each of the at least one second type of metrics are computed with respect to the plurality of users. A target metric is identified from the at least one first type of metric based on the correlations. The target metric is correlated with the at least one second type of metric.
Abstract:
One or more systems and/or methods of generating a query-goal-mission structure for a set of queries are provided. A set of queries may be evaluated to identify query information for the queries within the set of queries. The queries may be evaluated as query pairs to determine common goal probabilities (e.g., likelihood two queries correspond to a particular goal, such as to identify vacation planning information) for the query pairs. Responsive to the common goal probabilities for the query pairs exceeding a goal probability threshold, the query pairs may be grouped into goal clusters. The goal clusters may be evaluated as goal cluster pairs to determine common mission probabilities. Responsive to the common mission probabilities for the goal cluster pairs exceeding a mission probability threshold, the goal clusters may be grouped into mission clusters. The mission clusters and the goal clusters may be utilized to generate a query-goal-mission structure.
Abstract:
Methods, systems and programming for targeting users with engaging content. In one example, a metric with respect to a piece of content is measured for each of a plurality of users. A first set of users is identified from the plurality of users based on the measured metrics and a threshold. User profiles of the first set of users are obtained. A second set of users is then identified based on the user profiles of the first set of users. The piece of content is provided to the second set of users.
Abstract:
A method for online advertising, is provided, including: receiving a request for a web page from a client device; in response to the request, selecting an advertisement for presentation on the web page, and transmitting the web page to the client device; determining a duration of exposure of the advertisement when the web page is presented on the client device; determining a level of performance of a guaranteed presentation amount associated with the advertisement, the level of performance based on the duration of exposure of the advertisement. In another embodiment, a plurality of candidate advertisements are identified for presentation on a requested web page; for each candidate, an expected cost per time unit (eCPTU) of exposure is determined; one candidate advertisement is selected for presentation on the web page based on the eCPTU's; the web page is transmitted to a client device.
Abstract:
A method for online advertising includes: receiving a request for a content stream from a client device; embedding an advertisement in the content stream, and transmitting the content stream to the client device; determining a scroll dwell time of the advertisement when the content stream is presented on the client device; determining a level of performance of a guaranteed presentation amount associated with the advertisement, the level of performance based on the scroll dwell time of the advertisement. In another embodiment, candidate advertisements are identified for presentation in the content stream; for each candidate, an expected cost per time unit (eCPTU) of exposure is determined; one of the candidate advertisements is selected for inclusion in the content stream based on the eCPTU's; the content stream is transmitted to the client device.
Abstract:
One or more client devices, systems, and/or methods of improving mobile searches are provided. A feature (e.g., “snow boots”), generated on a client device, is identified. The feature is evaluated to identify a goal (e.g., finding snow boots) associated with the feature. A mission (e.g., finding outdoor apparel), associated with the goal, is identified. A query (e.g., “outdoor stores near Akron”) associated with a second goal (e.g., find outdoor apparel store) associated with the mission is identified using a model generated utilizing a machine learning method trained using a query-goal-mission structure. A query recommendation (e.g., “outdoor apparel store”) comprising the query is presented to the user. A user satisfaction metric, associated with the query, the query recommendation, a result generated by the query recommendation, etc. is determined based upon user interaction with the query recommendation and the result. The model may be tuned based upon the user satisfaction metric.
Abstract:
A method for determining a display time of a page is provided, including the following method operations: receiving a request for page data from a client; in response to the request, sending the page data to the client, the page data defining a page when rendered by the client, the rendered page including a page event module configured to detect and log events in a beacon for transmission, the events being selected from a group comprising a page unhide event, a page hide event, and a page unload event; receiving the beacon from the client; reading events logged in the beacon; and determining a display time of the page based on the events logged in the beacon.
Abstract:
A system for adjusting reserve price for impressions of non-guaranteed delivery (“NDG”) advertising auctions includes a processor configured to retrieve a reserve price set by a publisher for an impression that is fillable by eligible advertisements to be streamed to users in a display content stream; and to retrieve user engagement information for users that engage the eligible advertisements. A statistical analyzer applies a statistical function to the user engagement information of an identified advertisement of the eligible advertisements, to generate a user engagement statistic for the identified advertisement related to a user engagement level. A reserve price adjuster dynamically adjusts the reserve price for the identified advertisement responsive to a value of the user engagement statistic, where the adjusted reserve price for the identified advertisement is different than the reserve price for at least another of the eligible advertisements based on different user engagement levels for each.