Publicação
Churn Prediction in Digital Service Platforms
| datacite.subject.fos | Ciências Naturais::Ciências da Computação e da Informação | |
| datacite.subject.sdg | 08:Trabalho Digno e Crescimento Económico | |
| datacite.subject.sdg | 09:Indústria, Inovação e Infraestruturas | |
| dc.contributor.advisor | Castelli, Mauro | |
| dc.contributor.author | Simões, Mara Cordeiro | |
| dc.date.accessioned | 2026-06-29T12:57:47Z | |
| dc.date.available | 2026-06-29T12:57:47Z | |
| dc.date.issued | 2026-06-22 | |
| dc.description | Dissertation presented as the partial requirement for obtaining a Master's degree in Data Science and Advanced Analytics, specialization in Data Science | |
| dc.description.abstract | Customer churn prediction has become an important task for companies operating in competitive digital environments, particularly in non-contractual digital platforms where churn is not directly observable and must be inferred from patterns of user inactivity. This study develops and evaluates machine learning models to predict customer churn in a Portuguese digital service platform characterised by irregular and heterogeneous user activity patterns. Churn is defined using a 180-day inactivity threshold, supported by the distribution of inter-purchase intervals. The project follows the Cross-Industry Standard Process for Data Mining (CRISP-DM) and includes data preparation, feature engineering, and model comparison across several machine learning algorithms, including Logistic Regression, Random Forest, Gradient Boosting, XGBoost, LightGBM, Neural Networks, and a Stacking Ensemble. Special attention is given to class imbalance, as the dataset presents a reversed imbalance structure in which active users represent the minority class. The results show that models trained on the original imbalanced data achieve misleadingly strong performance by favouring the majority class, while the application of SMOTE leads to more balanced predictions across both classes. Among the evaluated models, LightGBM achieved the best overall performance, obtaining the highest F1-score while maintaining good generalisation and computational efficiency. The results also show the importance of handling class imbalance appropriately, selecting suitable evaluation metrics, and designing features that capture customer engagement patterns. In addition, engineered transactional features were shown to provide useful predictive information for churn prediction in non-contractual digital platforms. Overall, the study shows that machine learning models can effectively predict churn in environments characterised by irregular user activity patterns and non-standard class distributions. | eng |
| dc.identifier.uri | http://hdl.handle.net/10362/204153 | |
| dc.language.iso | eng | |
| dc.rights.uri | http://creativecommons.org/licenses/by/4.0/ | |
| dc.subject | Churn Prediction | |
| dc.subject | Machine Learning | |
| dc.subject | Digital Service Platforms | |
| dc.subject | Non-contractual Settings | |
| dc.subject | Class Imbalance | |
| dc.title | Churn Prediction in Digital Service Platforms | eng |
| dc.type | master thesis | |
| dspace.entity.type | Publication | |
| thesis.degree.name | Mestrado em Ciência de Dados e Métodos Analíticos Avançados, especialização em Data Science |