As we highlighted in a recent post, grad students Johan Nicander & Rikard Eriksson have worked with svexa’s guidance to develop a new automated system to help coaches and recreational athletes to more easily build high quality, individualized training plans. Their data model is now proven to successfully generate training programs for swimmers that closely match professional coaches. Recently Johan & Rikard were invited by International Society of Performance Analysis of Sport (ISPAS) and the International Association of Computer Science in Sport (IACSS) to present their training planning model at the prestigious 9th International Performance Analysis Workshop and Conference & 5th IACSS Conference (PACSS).
The crux of Johan & Rikard's work was demonstrating that their GERT system could accurately provide individualized training plans following the philosophy of a specific coach. As you can see from this chart, it does that very well.
About PACSS The PACSS is an online workshop and conference with a focus on interdisciplinary collaboration. The aim is to bridge the gap between theoretical computer science and practical performance analysis. The focus of the conference is on answering practical and contextual questions using the methods of computer science in the context of elite sport, which is perfectly aligned with svexa's work. Johan and Rikard's project is one of several current product developments svexa is pursuing, for automatic and adaptive training plans for every type of athlete in any sport and at every fitness level. As apparent from the results, it is possible to accurately create systems that provide individualized training plans following the philosophy of a specific coach.
Here's the conference poster with the details of the content Johan & Rikard presented:
If you'd like more information on how svexa can help your athletes and coaches optimize their individual performance, contact us on firstname.lastname@example.org
Abstract from their Thesis.
Optimal training planning is a combination of art and science, and a task that requires expert knowledge. This is a time-consuming task that is often exclusively available to top tier athletes. Many athletes outside the elite do not have access or cannot afford to hire a professional coach to help them create their training plans. In this study, we investigate if it is possible to use the historical training logs of elite swimmers to construct detailed weekly training plans similar to how a specific professional coach would have planned. We present a software system based on machine learning and genetic algorithms for generation of detailed weekly training plans based on desired volume, intensity, training frequency, and athlete characteristics. The system schedules training sessions from a library extracted from training plans written by a professional swimming coach. Results show that the proposed system is able to generate highly accurate training plans in terms of training load, types of sessions, and structure, compared to the human coach.