If you haven’t been paying attention, Pinterest is on the rise, with the platform seeing significant increases in overall users (now up to 416 million MAU) and engagement as it builds upon its product discovery focus and further refines its eCommerce tools.
That growth has been exacerbated by the COVID-19 lockdowns, with Pinterest becoming a replacement for the shopping mall in some respects. And regular Pinners are definitely coming to the platform in a buying mindset – according to Pinterest, some 90% of active Pinners use the platform to plan for or make purchases, while the app also sees far higher purchase intent than other social networks.
If you haven’t checked out what’s happening on Pinterest, it may well be worth a look. And late last week, Pinterest provided a few extra pointers for Pin marketers as part of an overview of how it’s improved its home feed ranking system.
In the post on the Pinterest Engineering blog, Pinterest outlines how it’s updated its system to show more relevant Pin results to each user.
As per Pinterest:
“Home feed is one of the most important surfaces at Pinterest that drives a significant portion of engagement from the more than 400+ million people who visit each month. From a business standpoint, the home feed is also a revenue driver, where most ads are shown to Pinners. Therefore, the way we surface personalized, engaging and inspiring recommendations in home feed is critical.”
In order to cater to this, Pinterest has revised its system to improve the relevance of its recommendations and listings, which has seen significant improvements in engagement.
The process involves taking into account more user actions, and building a system that’s capable of responding to variable inputs. That process has lead to various advances in feed display:
- We were able to show more relevant pins to users by improving the accuracy of our predictions.
- We improved engineering velocity by separating the model predictions from the ranking layer. We now can iterate on ranking functions by modifying utility terms and in parallel do model iterations.
- We helped the business by enabling stakeholders to quickly adjust ranking based on business needs.
That last point is particularly relevant for marketers – as Pinterest has evolved, it’s also sought to put increased focus on video content, with video now being the most engaging content type across all social platforms. Indeed, back in February, Pinterest reported that it saw 6x as many video views in 2019 as it did in 2018.
And that, at least in some part, is by design – as noted in the new ranking system overview:
“Video distribution was one of our main objectives in 2019 and achieving it via the old framework was difficult. In the MTL framework, we first defined a positive label for videos: was the video viewed for more than 10 seconds? We then added a new output node to MTL to predict this label. We then calibrated this node and added it into utility, including only video-specific actions: repins, close-ups and 10-second views. This increased our video distribution by 40% with increased engagement rates.”
So video Pins are not only more popular, they’re also being prioritized by Pinterest’s algorithm, which is an important note for marketers looking to make best use of the platform.
The full overview is fairly technical, but the key takeaway is that Pinterest’s system is getting better at recommending relevant content to each user, and that video content, in particular, should be a focus of your Pin efforts.
In addition to this, Pinterest also recently noted that ‘tags are the new hashtags’ in an outline of its updated post tagging process for video uploads.
As you can see, when you upload a video pin, you now select tags, based on a listing of product categories, as opposed to adding hashtags.
Another relevant note in your Pin process.
You can read the full overview of Pinterest’s updated feed algorithm process here.