Industry: Travel & Leisure, Content
Presenting the right training session video that fits the users needs and activating not only the newest content in the platform.
Based on Raptors algoritms Nordic Hiit is able to present the most relevant training video to their users that matches training level and interest.
A Raptor Customer Case Study normally includes a commerce site where our recommendations are centered around products. But the Raptor recommendation engine is not only limited to product recommendations, which this case illustrates perfectly.
Nordic Hiit is an online training concept with online video workouts on demand.
The mission for Nordic Hiit has been clear from the beginning; it should be easy for everyone to live a healthy lifestyle in a busy everyday lifestyle.
Nordic Hiit has developed a platform which gives their users access to 1600 workout videos within categories like HIIT, Power Yoga, and Running. The videos can be accessed on their website and through their app.
Every user on Nordic Hiit’s platforms has chosen a specific training level, training goal, training days, and what equipment they have available in their home, on their profile – which means there are a lot of different preferences that have to be taken into consideration when creating recommendations for the users.
Whenever a user clicks on “next video”, a signal is sent to Raptor’s recommendation engine. The Raptor recommendation engine then starts the process of finding the most relevant video for the individual user on Nordic Hiit’s platforms.
The algorithm starts by separating the three different training levels that the individual user has chosen in their profile preference settings. This means that there are three different algorithm paths which are either beginner, intermediate, or advanced.
The recommendation engine then starts a data filtering process by looking at the individual user’s profile and based on the chosen equipment, training goal, and training days it will include and exclude videos from the video catalog containing 1600 videos. Likewise, the algorithm will make sure that the videos fit the current season, so the workout videos that fit into a winter environment do not get recommended in the summer months.
In the last step, the algorithm takes into consideration which workout videos you have watched recently. If you have just done a workout that trained your legs and abs, then the next video should not contain the same exercises.
No matter the idea or challenge, Raptor was able to solve it. When the “Proof of Concept” had been developed, tested and approved, Raptor were fast to implement the solution on Nordic Hiit’s website and app. Raptor’s personalization engine is very scalable both horizontal and vertical in the sense that when Nordic Hiit comes up with an idea for the recommendations, Raptor has no problem solving it. They have moved the recommendations from a stage where they only needed to pick the next video to a more advanced setup, that involves many complex algorithms.
Based on the above, the algorithm will find the most relevant video.
The algorithm starts this process every time a user clicks the “next video” button, to find the correct order of videos to show. All these steps in the algorithms happen within milliseconds, and therefore there won’t be any delay for the user.
We are proud of this case since it shows how custom our personalization engine can be. The results of the Nordic Hiit solution are a testament to the agility and customization of our solution. We emulate a personal trainer to find the most relevant workout videos, based on the user’s preferences. This will give the users the best training results based on their training level, goal, equipment, and previous workouts.
There is no plan to stop developing Nordic Hiit’s platforms regarding creating the most personalized online training experience in the market.
Raptor is a crucial part of Nordic Hiit’s present as well as future, which means that there are many projects yet to come where Raptor is involved.
Recently a ”favorite” button has been added to the videos, which users can use to save a workout they enjoyed.
The favorite button can be used to create lists of the user’s favorite workouts, but we can also use the data to recommend related videos that other users who have liked the same videos have seen. As we all know from Spotify, where they create playlists based on the music, we listen to, I imagine we can do the same for video workouts. If a user has watched a lot of workout videos about yoga or stretching, then we can create a playlist with more videos like the ones they have watched.
Trigger messaging is also a part of the future setup for Nordic Hiit’s platforms.
If a user has been at the same training level for a certain amount of time, we can use Raptor’s triggers both on our website, in the app and through email to send messages like “Is it time to take your training to the next level?” and hereby try to get users to watch new videos, which hopefully means that they will remain a member.
Based on all Nordic Hiit’s user’s behavior such as clicks, favorites, and profile settings, such as training level, goals, equipment, etc. the plan is to create a public playlist that is tailored towards the individual, which can create even more value for the user.
Raptor has helped Nordic Hiit take their home workout platform to the next level, offering a personalized and induvidual workout experience for their users. This case proves that the right personalization engine can be customized and tailored to any business and its goals.
- Nordic Hiit went from a static one-size-fits-all model to a dynamic 1:1 personalized workout experience
- Raptor’s personalization engine can be customized in order to fit any business
- The right personalization engine can be used to personalize any businesses customer journey
- Raptor is a part of Nordic Hiit’s further development of their platform, that includes features such as trigger messaging
Do you want to know more about this case?
A Raptor expert can share more about the product and answer any questions you have