Fig. 3 shows an instance of how we use the Pin2Pin algorithm to generate key phrases for a Promoted Pin. First, we build a set of Pins which include Related Pins Related Pin 1, 2, and 3 that are corresponding to the input from the Promoted Pin. For each Promoted Pin and the set of identical Pins, we get its most engaged search queries. Specifically during this instance, we get “unique tacos” and two other Navboost queries of the Promoted Pin.
The “taco shell” query and five other Navboost queries appear on Related Pin 1. Next, for each of those queries, we compute a relevance score among the Promoted Pin and the query. In this example, we see “texas taco” from Related Pins 3, which has a relevance score of 0. 90 with the Promoted Pin. Finally, we filter the Navboost queries by the relevance score at a threshold and verify the set of key phrases for the Promoted Pin. As part of our Ads product life cycles, Targeting attribution is guilty for attributing ads impressions and beginning back to the advertisier’s targeting spec.
It is an important stage in our Advertising product since advertisers depend upon this suggestions to examine the performance of targeting profiles and plan for future commercials ideas. If an Ad is retrieved through probably the most Expanded Targeting techniques, we attribute the beginning to the generated key phrases or attention. The attribution signals also supply good comments signal for us to evaluate and improve the pleasant of our era pipelines.