Video competition discovery and recommendation

A system of determining competition for search queries on a video hosting system on a computer network, the system comprising:

• a hardware processor that is configured to:
• identify first search queries directed to a first video and associated view durations that the first video was watched in response to the first search queries and second search queries directed to a second video and associated view durations that the second video was watched in response to the second search queries;
• generate a first vector for the first video based on the first search queries and associated view durations and a second vector for the second video based on the second search queries and associated view durations;
• calculate a competition score indicating an amount of competition between the first video and the second video for views of users of the video hosting system based on a degree of similarity between the first vector and the second vector;
• and
• modify at least one video in a set of videos that includes the first video and the second video based on the competition score.

A non-transitory computer-readable medium containing computer executable instructions that, when executed by a processor, cause the processor to perform a method of determining competition for search queries on a video hosting system on a computer network, the method comprising:

• identifying first search queries directed to a first video and associated view durations that the first video was watched in response to the first search queries and second search queries directed to a second video and associated view durations that the second video was watched in response to the second search queries;
• generating a first vector for the first video based on the first search queries and associated view durations and a second vector for the second video based on the second search queries and associated view durations;
• calculating a competition score indicating an amount of competition between the first video and the second video for views of users of the video hosting system based on a degree of similarity between the first vector and the second vector;
• and
• modifying at least one video in a set of videos that includes the first video and the second video based on the competition score.