a Department of Physical Education and Sport Science, Faculty of Sport Sciences and Physical Education , University of A Coruña , A Coruña , Spain.
b School of Sports Science, Universidad Europea de Madrid , Madrid , Spain.
Eur J Sport Sci. 2019 Mar;19(2):217-224. doi: 10.1080/17461391.2018.1510036. Epub 2018 Aug 22.
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.
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.
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%.
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.
健身中心增加体育锻炼已使这些设施成为重要的积极生活方式促进者。然而,仅有 30%至 60%的会员在一年后仍与体育中心保持联系。本研究旨在设计一种预测健身中心会员流失的模型。
记录了西班牙三个体育中心的 14522 名会员在一年中的实际行为的每月数据。为了计算流失的可能性,对每个中心使用逻辑回归创建了预测模型。
可以根据用户的历史行为预测体育中心用户的流失,但为每个中心获得的预测模型并不完全一致。模型的有效性约为 70%。
分析健身中心用户的行为可以避免流失,从而避免放弃体育活动。根据流失的可能性对客户进行细分可能有助于提高忠诚度策略的有效性,并优化人力和物力资源的组织。