Business and Hotel Management School

Despite the growing challenge of product returns in e-commerce, limited research explores real-time prediction of return intent. Existing studies typically rely on customer relationship management (CRM) data and require historical context, such as a user's return behavior the last n orders. However, many online shoppers lack this context, because they either browse as guests and can thus not be identified in realtime or are first-time visitors. This reduces the accuracy and coverage of existing return intent assessment methods, which would otherwise lay the groundwork for timely interventions. This paper explores the potential for return prediction based only on browsing behavior using Long Short-Term Memory (LSTM) models. We simulate real-world settings by training and testing on a rolling-window approach on logged browsing data. We find for our model to attain F1=0.68 and ROC AUC = 0.70 on average. Furthermore, our model demonstrates superior accuracy compared to methods relying on CRM data without historical user context. A subsequent analysis of the important features, based on the trained LSTM model, draws insights into which browsing behaviors may be early warning signals indicating return. For instance, having a high number of items in the shopping cart from a previous browsing session is strongly associated with high-value returns. Meanwhile, for desktop users, the use of filters appears to be a driving indicator for returns. In a hypothetical calculation, we illustrate the positive economic impact our approach enables to e-commerce companies. Our findings highlight the potential of utilizing browsing behavior for prediction of return intent, providing a foundation for developing real-time return intent assessment strategies.

As societies age, the number of individuals experiencing stroke increases, necessitating more effective rehabilitation strategies. Over half of stroke survivors suffer from upper limb impairments, making assessments of sensory-motor function crucial for both improving interventions and tracking progress. Ideally, such assessments could also be performed at home without requiring a therapist's presence. Advances in computer vision and human pose estimation allow for human movement analysis using consumer-grade cameras. This study investigates whether a single webcam, combined with human pose estimation and deep learning algorithms, can automatically detect compensatory movements in persons with stroke performing a drinking task. Twenty participants with stroke with mild to moderate upper limb impairment were recruited. Each participant performed multiple repetitions of the drinking task while being recorded by multiple cameras and an optical motion capture system (OMC) for kinematic ground truth. The videos were labeled by therapists to indicate the presence or absence of compensatory movements. Human poses were extracted from the videos using MediaPipe, and deep learning models were trained to predict these compensatory movements based on MediaPipe keypoints. Several factors affecting compensation detection accuracy were evaluated. Models trained on raw MediaPipe keypoints for inter-person compensation detection failed to generalize, achieving accuracy around 50%. Using custom features instead of raw keypoints improved the accuracy to 70%. In contrast, intraperson classification achieved high accuracy, typically exceeding 90%. Using OMC data significantly improved classification accuracy compared to using MediaPipe keypoints. Camera angle had an effect on accuracy, and convolutional neural networks outperformed long short-term memory networks. Generalizing models remain limited by (1) the measurement uncertainty of human pose estimation and (2) insufficient data representing the full spectrum of compensatory strategies (3) accurate compensation labels. The results demonstrate that deep learning approaches can differentiate between compensatory and non-compensatory movements when movement representations are sufficiently accurate. Future work should improve pose estimation and expand labeled datasets to better reflect the stroke population. While general models are limited in accuracy, personalized models using consumer cameras can support home-based rehabilitation. This digitalized assessment approach has the potential to quantify recovery progress throughout the continuum of care.

We introduce the Quantum Alarm System, a novel framework that combines the informational advantages of quantum majorization applied to tail pseudo-correlation matrices with the learning capabilities of a reinforced urn process, to predict financial turmoil and market crashes. This integration allows for a more nuanced analysis of the dependence structure in financial markets, particularly focusing on extreme events reflected in the tails of the distribution. Our model is tested using the daily log-returns of the 30 constituents of the Dow Jones Industrial Average, spanning from 2 January 1992 to 30 August 2024. The results are encouraging: in the validation set, the 12-month ahead probability of correct alarm is between 73% and 80%, while maintaining a low false alarm rate. Thanks to the application of quantum majorization, the alarm system effectively captures non-traditional and emerging risk sources, such as the financial impact of the COVID-19 pandemic—an area where traditional models often fall short.

Both e-democracy and e-government face issues concerned with encouraging participation, avoiding manipulation through the malign use of technology and the need to avoid becoming functionally remote. In this philosophically based analysis, a combination of reflective equilibrium, most associated with John Rawls, and discourse ethics, most associated with Jürgen Habermas, is seen as offering answers to these issues by providing a framework and process for the electronic public forum, as also a method for moral justification in public decision making.

IntroductionClinical assessment of upper limb sensorimotor function post-stroke is often constrained by low sensitivity and limited information on movement quality. To address this gap, recent studies proposed a standardized instrumented drinking task, as a representative daily activity combining different components of functional arm use. Although kinematic movement quality measures for this task are well-established, and optical motion capture (OMC) has proven effective in their measurement, its clinical application remains limited. Inertial Measurement Units (IMUs) emerge as a promising low-cost and user-friendly alternative, yet their validity and clinical relevance compared to the gold standard OMC need investigation.MethodIn this study, we conducted a measurement system comparison between IMUs and OMC, analyzing 15 established movement quality measures in 15 mild and moderate stroke patients performing the drinking task, using five IMUs placed on each wrist, upper arm, and trunk.ResultsOur findings revealed strong agreement between the systems, with 12 out of 15 measures demonstrating clinical applicability, evidenced by Limits of Agreement (LoA) below the Minimum Clinically Important Differences (MCID) for each measure.DiscussionThese results are promising, suggesting the clinical applicability of IMUs in quantifying movement quality for mildly and moderately impaired stroke patients performing the drinking task.

Should family members work outside the family business before joining? Experts have long recommended that this is the best (and only!) way for the next generation to learn the skills and knowledge required for a job, develop vocational self-confidence, receive honest and objective feedback, and learn what "work" really means. And despite there being no empirical evidence to support this claim, many family

This venture targets giving a correspondence framework that can improve the legal framework execution and cooperation and furthermore make it simple to lead execution audits. This examination depicts restricted admittance to the right legitimate data just as admittance to courts and court administrations as the essential factors that limit admittance to equity. The basic target fundamental for accomplishing the point incorporates planning an online easy to understand data framework that would improve correspondence and association between legal professionals like legal advisors and disputants. The undertaking uses a subjective methodology that zeroed in on the substance investigation of essential information. Key members were court laborers like attorneys and agents, just as court clients like disputants. Pre-plan discoveries uncovered that current legitimate data frameworks – basically court sites – neglect to recognize their crowd by treating all court clients similarly comparative with the correspondence of lawful data. Likewise, the issue of admittance to equity includes the significant expense of equity also, restricted legal data that elevates admittance to equity. Post-plan discoveries from the online overview directed after the turn of events and execution of the IT curio uncovered a powerful and productive legitimate data framework. Exploration discoveries supported the advancement of an IT antiquity that records for huge shortcomings in current legal data frameworks, for example, their failure to pass on fitting legitimate data intelligently and productively. In outline, the investigation prescribes the reception of saw control to work fair and square of certainty of court clients and the differentiation between court clients to convey the right data to the right crowd.

The implementation of sustainability practices in the tourism system requires the participation of a variety of actors. While much research has focused on supply-side issues associated with sustainable tourism, there has been less focus on supply-side issues associated with consumer behaviour and business-related travel. This paper addresses the behaviours of this significant market segment. As behavioural change is seen as a key mechanism for achieving emission reduction, this paper focuses on behaviours of business travels from four countries: Canada, Switzerland, Russia and the U.S., using values-attitudes-behaviour (VAB) theory. We employ Principal Components Analysis to reduce the variables down to four factors and related factor scores. Stepwise multiple linear regression was then used to measure causal associations. The findings show how national cultures, demographics and values influence (although at different levels) the sustainable attitudes and behaviour of business travellers. These results have implications for future corporate travel policy. The recent impact of the COVID-19 global pandemic is also addressed.