232451 research outputs found
Sort by
Prediction of cart abandonment using imbalanced clickstream data in online shopping
No full textNumerous AI-based solutions have been developed to predict online shopping behavior and cart abandonment, ranging from statistical and sequential data mining approaches to deep learning models. However, this task remains challenging due to the inherent class imbalance of online shopping data and the lack of transparency of most successful classifiers. In this paper, we investigate both issues in the context of cart abandonment prediction using imbalanced clickstream data in online shopping. As a first contribution, we study the effectiveness of addressing class imbalance via thresholding compared to other undersampling and oversampling in the context of clickstream data. Therefore the thresholding method is investigated that balances the decisions generated by deep neural networks by adjusting the probability threshold through binary search. The advantage of this strategy is that it neither discards any relevant data samples nor introduces synthetic ones. As a second contribution, we study the contribution of sequential and static features to the model's performance and investigate the extent to which oversampling techniques induce noise in the interpretability results. The numerical simulations show that our balancing strategy is slightly superior to undersampling and oversampling approaches without inducing a bias towards any of the decision classes. Moreover, we noticed that integrating static features alongside sequential data further boosts the performance of the recurrent neural network models, aligning with the results of previous research
The impact of self-stigma on empowerment in major depressive disorder:The mediating role of self-esteem and the moderating effects of socioeconomic and cultural context in an international multi-site study
No full textBackgroundMajor Depressive Disorder (MDD) is a prevalent mental health condition often accompanied by self-stigma, negatively impacting self-esteem and empowerment. This study examines the mediating role of self-esteem in the relationship between self-stigma and empowerment and explores the moderating influence of socioeconomic and cultural contexts in an international sample.MethodsThis cross-sectional study, part of the ASPEN/INDIGO-Depression project, included participants with a diagnosis of MDD from 34 countries. Self-stigma, self-esteem, and empowerment were assessed using, respectively, the Internalized Stigma of Mental Illness (ISMI) scale, the Boston University Empowerment Scale (BUES), and the Rosenberg Self-Esteem Scale (RSES). A mediation model examined self-esteem's role in the self-stigma–empowerment relationship, and a conditional mediation model examined the moderating effect of the Human Development Index (HDI). All effects were adjusted for socio-demographic and clinical covariates.ResultsA total of 1058 people participated. Mediation analysis confirmed that self-esteem significantly mediated the negative association between self-stigma and empowerment, suggesting that lower self-stigma leads to higher self-esteem, which in turn enhances empowerment. Moderation analysis revealed that the mediation effect varied across countries with different socioeconomic and cultural contexts. The indirect effect of self-stigma on self-esteem was stronger in countries with higher HDI, indicating that individuals in these settings experience greater vulnerability to the negative effects of self-stigma on self-esteem.ConclusionsSelf-esteem buffers the negative impact of self-stigma on empowerment in people with MDD. The strength of this effect varies by socioeconomic and cultural context, with stronger mediation in higher-HDI countries. These findings highlight the need for tailored interventions addressing self-stigma in specific contexts to enhance empowerment and recovery
