Search

User engagement (UE) is the quality of user experience that emphasizes any positive aspects of interaction with an application, and particularly the phenomena associated with being captivated by certain features included in it, thus being motivated to use it. In the context of mobile applications, measuring UE could provide insights to further explain usage behaviors, allowing developers, and product managers, to gain a better understanding of how users utilize their applications, and what drives their engagement with them. Numerous methods have been proposed in literature to measure UE in domains such as online services; however, not much had been done to model UE in the context of mobile applications. In response to this problem, our study proposes to measure UE with mobile applications by analyzing temporal changes in a defined set of usage metrics, yielding a general metric, a mobile application user engagement (MAUE) score, which is a linear combination of the UE time series metrics, accounting for the largest amount of the variance in usage data, and extracted by principal component analysis (PCA). Our proposed approach has been applied to the behavioral data of 40,004 unique users of The Weather Company mobile application. Our results indicate that time-dependent fluctuations of the MAUE score are characterized with a power-law decrease, in accordance with the power law of practice, suggesting different levels of UE stability for the different mobile platforms (i.e., IOS, Android). Additionally, the Multidimensional scaling distance between clusters of variables loadings, and among the variables loadings within each cluster with regards to the amount of usage days, could be used to map the UE motivations and thus provide product managers an improved understanding and prediction ability of the influence of different app updates and product interventions on UE.

A Cubist model for hospital Length of Stay (LOS) is proposed.The groups of cases covered by the Cubist rules differ in their characteristics.The LOS primarily depends on historical variables such as number of admissions.Applying CARMA algorithm allows discovery of important relations among variables.A method to separate the cases by their level of Cubist error. A model that accurately predicts, at the time of admission, the Length of Stay (LOS) for hospitalized patients could be an effective tool for healthcare providers. It could enable early interventions to prevent complications, enabling more efficient utilization of manpower and facilities in hospitals. In this study, we apply a regression tree (Cubist) model for predicting the LOS, based on static inputs, that is, values that are known at the time of admission and that do not change during patient's hospital stay. The model was trained and validated on de-identified administrative data from the Veterans Health Administration (VHA) hospitals in Pittsburgh, PA. We chose to use a Cubist model because it produced more accurate predictions than did alternative techniques. In addition, tree models enable us to examine the classification rules learned from the data, in order to better understand the factors that are most correlated with hospital LOS. Cubist recursively partitions the data set as it estimates linear regressions for each partition, and the error level differs for different partitions, so that it is possible to deduce what are the characteristics of patients whose LOS can be accurately predicted at admission, and what are the characteristics of patients for whom the LOS estimate at that point in time is more highly uncertain. For example, our model indicates that the prediction error is greater for patients who had more admissions in the recent past, and for those who had longer previous hospital stays. Our approach suggests that mapping the cases into a higher dimensional space, using a Radial Basis Function (RBF) kernel, helps to separate them by their level of Cubist error, using a Support Vector Machine (SVM).

A mixed-ensemble model for hospital readmission is proposed.The mixed-ensemble model enables controlling the tradeoff between reasoning transparency and predictive accuracy.The mixed-ensemble model increases the classification accuracy for positive readmission instances.An optimization approach for the mixed-ensemble model is proposed.The mixed-ensemble model has been implemented for predicting all-cause hospital readmissions of CHF patients. ObjectiveA hospital readmission is defined as an admission to a hospital within a certain time frame, typically thirty days, following a previous discharge, either to the same or to a different hospital. Because most patients are not readmitted, the readmission classification problem is highly imbalanced. Materials and methodsWe developed a hospital readmission predictive model, which enables controlling the tradeoff between reasoning transparency and predictive accuracy, by taking into account the unique characteristics of the learned database. A boosted C5.0 tree, as the base classifier, was ensembled with a support vector machine (SVM), as a secondary classifier. The models were induced and validated using anonymized administrative records of 20,321 inpatient admissions, of 4840 Congestive Heart Failure (CHF) patients, at the Veterans Health Administration (VHA) hospitals in Pittsburgh, from fiscal years (FY) 2006 through 2014. ResultsThe SVM predictions are characterized by greater sensitivity values (true positive rates) than are the C5.0 predictions, for a wider range of cut off values of the ROC curve, depending on a predefined confidence threshold for the base C5.0 classifier. The total accuracy for the ensemble ranges from 81% to 85%. Different predictors, including comorbidities, lab values, and vitals, play different roles in the two models. ConclusionsThe mixed-ensemble model enables easy and fast exploratory knowledge discovery of the database, and a control of the classification error for positive readmission instances. Implementation of this ensembling method for predicting all-cause hospital readmissions of CHF patients allows overcoming some of the limitations of the classifiers considered individually, and of other traditional ensembling methods. It also increases the classification accuracy for positive readmission instances, particularly when strong predictors are not available.