Related Experiment Video
Updated: Feb 6, 2026
Universal Screening for Prevention of Reading, Writing, and Math Disabilities in Spanish
Published on: July 18, 2020
Prediction of abandonment in Spanish fitness centres
Iván Clavel San Emeterio1, Jorge García-Unanue2, Eliseo Iglesias-Soler1
1a Department of Physical Education and Sport Science, Faculty of Sport Sciences and Physical Education , University of A Coruña , A Coruña , Spain.
Research Question:
The increase of physical exercise in fitness centres has turned these facilities in important active lifestyle promoters. However, only between 30% and 60% of subscribers still linked to the sports centre after a year. The aim of this study is to design a model to predict the drop out in fitness centres.
Research Methods:
Monthly data corresponding to the actual behaviour of 14,522 members of three sport centres in Spain were recorded over the course of one year. In order to calculate the likelihood of drop out, logistic regressions were used to create predictive models for each centre.
Results And Findings:
It was possible to predict abandonment of users of sport centres from their historical behaviour, although the predictive models obtained for each centre were not completely coincident. The effectiveness of the models was around 70%.
Implications:
The analysis of users' behaviour in a fitness centre can allow to avoid the drop out and therefore the abandonment of physical activity. Segmenting the customers based on the likelihood of drop out may be useful for improving the effectiveness of the strategies of loyalty and for optimizing the organization of human and material resources.
Related Concept Videos
01:13Induced-fit Model
Enzymes exhibit substrate specificity, meaning that they can only bind to certain substrates. This is mainly determined by the shape and chemical...
00:57Inclusive Fitness
01:16Goodness-of-Fit Test
02:27Predicting Molecular Geometry
01:03Prediction Intervals
However, the point estimate is most likely not the exact value of the population parameter, but close to it. After calculating point estimates, we construct interval estimates, called confidence intervals or prediction intervals. This prediction interval comprises a range of values unlike the point estimate and is a better predictor of the observed sample value, y.
01:19Expected Frequencies in Goodness-of-Fit Tests