Search results for: degenerate cases
2 Mobile App versus Website: A Comparative Eye-Tracking Case Study of Topshop
Authors: Zofija Tupikovskaja-Omovie, David Tyler, Sam Dhanapala, Steve Hayes
Abstract:
The UK is leading in online retail and mobile adoption. However, there is a dearth of information relating to mobile apparel retail, and developing an understanding about consumer browsing and purchase behaviour in m-retail channel would provide apparel marketers, mobile website and app developers with the necessary understanding of consumers’ needs. Despite the rapid growth of mobile retail businesses, no published study has examined shopping behaviour on fashion mobile apps and websites. A mixed method approach helped to understand why fashion consumers prefer websites on smartphones, when diverse mobile apps are also available. The following research methods were employed: survey, eye-tracking experiments, observation, and interview with retrospective think aloud. The mobile gaze tracking device by SensoMotoric Instruments was used to understand frustrations in navigation and other issues facing consumers in mobile channel. This method helped to validate and compliment other traditional user-testing approaches in order to optimize user experience and enhance the development of mobile retail channel. The study involved eight participants - females aged 18 to 35 years old, who are existing mobile shoppers. The participants used the Topshop mobile app and website on a smart phone to complete a task according to a specified scenario leading to a purchase. The comparative study was based on: duration and time spent at different stages of the shopping journey, number of steps involved and product pages visited, search approaches used, layout and visual clues, as well as consumer perceptions and expectations. The results from the data analysis show significant differences in consumer behaviour when using a mobile app or website on a smart phone. Moreover, two types of problems were identified, namely technical issues and human errors. Having a mobile app does not guarantee success in satisfying mobile fashion consumers. The differences in the layout and visual clues seem to influence the overall shopping experience on a smart phone. The layout of search results on the website was different from the mobile app. Therefore, participants, in most cases, behaved differently on different platforms. The number of product pages visited on the mobile app was triple the number visited on the website due to a limited visibility of products in the search results. Although, the data on traffic trends held by retailers to date, including retail sector breakdowns for visits and views, data on device splits and duration, might seem a valuable source of information, it cannot explain why consumers visit many product pages, stay longer on the website or mobile app, or abandon the basket. A comprehensive list of pros and cons was developed by highlighting issues for website and mobile app, and recommendations provided. The findings suggest that fashion retailers need to be aware of actual consumers’ behaviour on the mobile channel and their expectations in order to offer a seamless shopping experience. Added to which is the challenge of retaining existing and acquiring new customers. There seem to be differences in the way fashion consumers search and shop on mobile, which need to be explored in further studies.Keywords: Consumer behaviour, eye-tracking technology, fashion retail, mobile app, m-retail, smart phones, Topshop, user experience, website.
Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 23551 Using Statistical Significance and Prediction to Test Long/Short Term Public Services and Patients Cohorts: A Case Study in Scotland
Authors: Sotirios Raptis
Abstract:
Health and Social care (HSc) services planning and scheduling are facing unprecedented challenges, due to the pandemic pressure and also suffer from unplanned spending that is negatively impacted by the global financial crisis. Data-driven approaches can help to improve policies, plan and design services provision schedules using algorithms that assist healthcare managers to face unexpected demands using fewer resources. The paper discusses services packing using statistical significance tests and machine learning (ML) to evaluate demands similarity and coupling. This is achieved by predicting the range of the demand (class) using ML methods such as Classification and Regression Trees (CART), Random Forests (RF), and Logistic Regression (LGR). The significance tests Chi-Squared and Student’s test are used on data over a 39 years span for which data exist for services delivered in Scotland. The demands are associated using probabilities and are parts of statistical hypotheses. These hypotheses, as their NULL part, assume that the target demand is statistically dependent on other services’ demands. This linking is checked using the data. In addition, ML methods are used to linearly predict the above target demands from the statistically found associations and extend the linear dependence of the target’s demand to independent demands forming, thus, groups of services. Statistical tests confirmed ML coupling and made the prediction statistically meaningful and proved that a target service can be matched reliably to other services while ML showed that such marked relationships can also be linear ones. Zero padding was used for missing years records and illustrated better such relationships both for limited years and for the entire span offering long-term data visualizations while limited years periods explained how well patients numbers can be related in short periods of time or that they can change over time as opposed to behaviours across more years. The prediction performance of the associations were measured using metrics such as Receiver Operating Characteristic (ROC), Area Under Curve (AUC) and Accuracy (ACC) as well as the statistical tests Chi-Squared and Student. Co-plots and comparison tables for the RF, CART, and LGR methods as well as the p-value from tests and Information Exchange (IE/MIE) measures are provided showing the relative performance of ML methods and of the statistical tests as well as the behaviour using different learning ratios. The impact of k-neighbours classification (k-NN), Cross-Correlation (CC) and C-Means (CM) first groupings was also studied over limited years and for the entire span. It was found that CART was generally behind RF and LGR but in some interesting cases, LGR reached an AUC = 0 falling below CART, while the ACC was as high as 0.912 showing that ML methods can be confused by zero-padding or by data’s irregularities or by the outliers. On average, 3 linear predictors were sufficient, LGR was found competing well RF and CART followed with the same performance at higher learning ratios. Services were packed only when a significance level (p-value) of their association coefficient was more than 0.05. Social factors relationships were observed between home care services and treatment of old people, low birth weights, alcoholism, drug abuse, and emergency admissions. The work found that different HSc services can be well packed as plans of limited duration, across various services sectors, learning configurations, as confirmed by using statistical hypotheses.
Keywords: Class, cohorts, data frames, grouping, prediction, probabilities, services.
Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 434