Ellida case study: AI-driven individualized and adaptive training programs

Following on our recent successful pilot program with RaceID, and additional testing with individual athletes, we have further developed the capability of our Ellida product. This will enable athletes of all levels to easily generate optimized, individualized training programs and help them achieve their goals. Our latest case study describes this work:

The Challenge: Most recreational athletes do not have access to any type of coaching. This results in the use of ad-hoc or generic training programs that are neither personalized or adaptive over time. This approach on average leads to sub-optimal training, underperformance and even injury.

The Solution: To address this need, we combined several of our products to create the training planning system Ellida*, which combines training logs, subjective measures (fitness level, goals, and commitment) and coaching domain expertise to produce then iterate on personalized training plans. In partnership with RaceID, we tested this with a pilot project focused on runners of different fitness levels, who trained for 8 weeks to run a 10km race.

Results: success! The participants were happy and motivated by the program, felt that it was tailored well to their personal goal and situation, and that the levels/recommendations of the training sessions were appropriate - even the hard sessions.

Each of the runners completed their target race, 10 of the 12 runners finished within 1 minute of their target time or better and most set new PBs. Ellida's predictions proved very accurate - race time had an average error of just 3.8%, and the average race HR was predicted with an average error of just 2.8 BPM!

Following this initial pilot, we have tested Ellida in a number of separate athlete training situations. Results were similarly impressive, with each athlete achieving very close to Ellida's predicted time.

Head engineer and international middle distance runner Johan Rogestedt has been further testing Ellida with his amateur athlete friends - as he says "Recently we used Ellida to make a prediction of 49.58 @ 180bpm for a friend's all-out 10k run. In reality, he ran 49.14 @ 176 bpm, so our prediction was super close and further validated as the course was slightly downhill!"

We will continue to develop our Ellida capability for use by all athletes, first working to expand the capability to trail running, cycling, swimming, triathlon, and swimrun. If you'd like to hear how we can help your athletes perform better, don't hesitate to get in touch at