Recommending Running Routes: Framework and Demonstrator

Loepp, B., & Ziegler, J. (2018). In Proceedings of the 2nd Second Workshop on Recommendation in Complex Scenarios (pp. 26–29).

Thesis by Marc Morgenbrod

Abstract

Recommending personalized running routes is a challenging task. When the runner’s specific background as well as needs, preferences and goals are taken into account, a recommender cannot only rely on e.g. a set of existing routes ran by others, but needs to individually generate each route while considering many different aspects that determine whether a suggestion will satisfy the runner in the end, e.g. height meters or areas passed. We describe a framework that summarizes these aspects, allowing to generate personalized running routes. Based on this framework, we present a prototypical smartphone app that we implemented to actually demonstrate how running routes can be recommended based on the different requirements a runner might have. A first small study where users had to try this app and ran some of the recommended routes underlines the general effectiveness of our approach.

Resources

Related publications

On User Awareness in Model-Based Collaborative Filtering Systems

Explaining Recommendations by Means of User Reviews

Sequential User-based Recurrent Neural Network Recommendations

VIEW MORE »

Focus areas