Using Case-Based Reasoning to Predict Marathon Performance and Recommend Tailored Training Plans

Training for the marathon, especially a first marathon, is always a challenge. Many runners struggle to find the right balance between their workouts and their recovery, often leading to sub-optimal performance on race-day or even injury during training. We describe and evaluate a novel case-based reasoning system to help marathon runners as they train in two ways. First, it uses a case-base of training/workouts and race histories to predict future marathon times for a target runner, throughout their training program, helping runners to calibrate their progress and, ultimately, plan their race-day pacing. Second, the system recommends tailored training plans to runners, adapted for their current goal-time target, and based on the training plans of similar runners who have achieved this time. We evaluate the system using a dataset of more than 21,000 unique runners and 1.5 million training/workout sessions.