Predicting Early Dropouts of an Active and Healthy Ageing App

TL;DR

This paper presents a machine learning approach to predict early dropouts in an active ageing app, demonstrating high accuracy and winning the IFMBE Scientific Challenge 2022.

Contribution

The study introduces effective machine learning models utilizing dynamic and static features, with oversampling techniques, to accurately predict user adherence in health apps.

Findings

Oversampling methods improved classification performance by 10%.

Dynamic features positively impacted prediction accuracy.

Our models achieved first place in the challenge.

Abstract

In this work, we present a machine learning approach for predicting early dropouts of an active and healthy ageing app. The presented algorithms have been submitted to the IFMBE Scientific Challenge 2022, part of IUPESM WC 2022. We have processed the given database and generated seven datasets. We used pre-processing techniques to construct classification models that predict the adherence of users using dynamic and static features. We submitted 11 official runs and our results show that machine learning algorithms can provide high-quality adherence predictions. Based on the results, the dynamic features positively influence a model's classification performance. Due to the imbalanced nature of the dataset, we employed oversampling methods such as SMOTE and ADASYN to improve the classification performance. The oversampling approaches led to a remarkable improvement of 10\%. Our methods won first place in the IFMBE Scientific Challenge 2022.