1752 research outputs found
Sort by
Machine Learning-Methoden zur Vorhersage von Kundenabwanderungen im Bankensektor
No full textMit zunehmenden Wettbewerb wird die Kundenbindung zu einer der größten Herausforderungen für Kundendienstleister und insbesondere dem Bankensektor. Die stetige Weiterentwicklung von Machine Learning als Teilgebiet der künstlichen Intelligenz bietet heute die Möglichkeit, ein effektives, datengetriebenes Customer Relationship Management zu implementieren. Die Aufstellung eines Prognosemodells, welches abwanderungsgefährdete Kunden frühzeitig identifizieren kann, ist in diesem Zusammenhang ein vielversprechendes Werkzeug zur Verbesserung des Customer Churn Managements. Im Rahmen dieser Arbeit wird gezeigt, wie moderne Machine Learning-Methoden erfolgreich eingesetzt werden können, um zuverlässige Vorhersagemodelle von Kundenabwanderungen zu modellieren und evaluieren. In einem Praxisteil werden hierbei fiktive Kundendaten einer Bank mit der Open Source-Programmiersprache Python analysiert
Geschäftsprozessmanagement und Prozessorientierte Informationssysteme – Eine quantitative Evaluation von wissenschaftlichen Publikationen (Bibliometrische Analyse)
No full textZiel der vorliegenden wissenschaftlichen Arbeit ist es ein umfangreiches Bild der Forschungsaktivitäten der jüngsten Vergangenheit und Gegenwart in den Disziplinen Geschäftsprozessmanagement und Prozessorientierte Informationssysteme (engl. Process Aware Information Systems) aufzuzeigen und dieses zu evaluieren. Die Zielsetzung ist durch 5 Fragestellungen genauer beschrieben, die den Fokus auf die Entwicklung von Forschungsrelevanz, (großen) Forschungsfronten, Artikeln und Autoren, die einen wesentlichen Beitrag leisten, sowie den produktivsten Organisationen und deren Kooperationen richten.
Zum Beantworten der Fragestellungen wurde die Methodik der bibliometrischen Analyse verwendet und zur Unterstützung die bibliometrische Software NetCulator eingesetzt. Nach einer theoretischen Einführung in beide Disziplinen und der Methodik wurde für jede Disziplin ein Suchterm bestimmt, mittels dessen die für die Analyse notwendigen Daten aus der Zitationsdatenbank Web of Science gewonnen wurden. Der Untersuchungszeitraum wurde auf die Jahre 2000-2019 begrenzt. Die Datenbasis umfasste 5296 für NetCulator verwertbare Treffer für den Suchterm der Disziplin Geschäftsprozessmanagement und 3832 Treffer für den Suchterm der Disziplin Prozessorientierte Informationssysteme
The German Version of the Mobile App Rating Scale (MARS-G): Development and Validation Study
Full text linkBackground: The number of mobile health apps (MHAs), which are developed to promote healthy behaviors, prevent disease onset, manage and cure diseases, or assist with rehabilitation measures, has exploded. App store star ratings and descriptions usually provide insufficient or even false information about app quality, although they are popular among end users. A rigorous systematic approach to establish and evaluate the quality of MHAs is urgently needed. The Mobile App Rating Scale (MARS) is an assessment tool that facilitates the objective and systematic evaluation of the quality of MHAs. However, a German MARS is currently not available.
Objective: The aim of this study was to translate and validate a German version of the MARS (MARS-G).
Methods: The original 19-item MARS was forward and backward translated twice, and the MARS-G was created. App description items were extended, and 104 MHAs were rated twice by eight independent bilingual researchers, using the MARS-G and MARS. The internal consistency, validity, and reliability of both scales were assessed. Mokken scale analysis was used to investigate the scalability of the overall scores.
Results: The retranslated scale showed excellent alignment with the original MARS. Additionally, the properties of the MARS-G were comparable to those of the original MARS. The internal consistency was good for all subscales (ie, omega ranged from 0.72 to 0.91). The correlation coefficients (r) between the dimensions of the MARS-G and MARS ranged from 0.93 to 0.98. The scalability of the MARS (H=0.50) and MARS-G (H=0.48) were good.
Conclusions: The MARS-G is a reliable and valid tool for experts and stakeholders to assess the quality of health apps in German-speaking populations. The overall score is a reliable quality indicator. However, further studies are needed to assess the factorial structure of the MARS and MARS-G
Design of a solution for the communication between Microsoft’s ERP-solution and E-Commerce systems
No full textMicrosoft Dynamics 365 Finance and Microsoft Dynamics 365 Supply Chain Management are part of the ERP-solution provided by Microsoft. With Microsoft Dynamics 365 Commerce it is now also possible to define a channel in the ERP-system that represents an online store. Often, one or more third-party storefronts have to be used that require data about listings, saved in an ERP-system, in their own systems, and the stores also generate data that has to be transferred to the ERP-system. Incorrect synchronization results in either integrity problems or data that is difficult to maintain. Currently, there is no research on how to achieve such a synchronization with multiple shop platforms in Dynamics 365. This thesis evaluates possible implementations of such a synchronization between Dynamics 365 and third-party storefronts and suggests a most appropriate approach that can easily include multiple storefronts. The data transfer capabilities are evaluated for such an implementation, as well as technologies that can be used for best results, including Dynamics 365, Microsoft Azure, and Amazon Web Services. In the end, a combination of Business Events, Service Buses, Azure Functions and e-Commerce SDK was chosen to ensure successful bi-directional synchronization. The performance, scalability and extension aspect for multichannel was provided by the final implementation and resulted in a successful solution and synchronization
Mobile Health App Database - A Repository for Quality Ratings of mHealth Apps
Full text linkThe utilization of mobile technology in the field of medicine and healthcare has become a decisive aspect. The entire field is denoted as mobile health (mHealth). For mHealth, the development and use of mobile applications are crucial. The purposes and goals of mHealth apps, in turn, are manifold. As a consequence, a plethora of mHealth apps can be found in the app stores. Interestingly, for patients, users, and health care providers that consider to use mHealth apps one aspect has been less pursued so far: Systematic and standardized ways that help about the quality of an app or its medical evidence are mainly missing. The Mobile App Rating Scale (MARS) is a standardized instrument that aims at the systematic and comparable evaluation of the quality of mobile health apps as well as categorizing their goals and functions. It comprises 23 items, which are utilized to calculate a rating scale. Having MARS in mind, a database was developed that is called Mobile Health App Database (MHAD). The latter offers technical features to systematically utilize the MARS for researchers as well as clinicians and end-users that (i) want to evaluate apps as well as (ii) want an interactive and easy-to-use web interface that shows the results of the rating procedure. MHAD comprises a rating platform that supports the conduction of MARS ratings and their release process. With the information platform, a web application was developed that prepares the data stored in the rating platform for being freely viewed and studied by users, patients, and health care providers. The goal of MHAD constitutes to be an open science repository that encourages researchers to release their MARS ratings to a broader audience. Such repositories become more and more important in many fields, especially in the field of mHealth
Developing a medical software to enhance patient participation
Full text linkMental health disorder is a frequent issue among cancer patients. It is estimated that in about 30% of cancer patients, psychological issues are undetected. Psychooncology is a subdomain of psychology, which studies cancer related psychological issues and, hence, develop appropriate treatments. With the help of screening instruments like the Distress Thermometer, patients are rated according to their mental state. The result of the screening indicates, whether a patient needs psychological treatment or not. However, in most medical facilities this screening is processed using paper-based questionnaires, which complicates the treatment. This thesis aims for enhancing the screening process as well as the overall psychological treatment with a newly developed mobile application Feelback.
The mentioned application uses patient participation principles by applying the latter. Patients shall feel more involved in the psychological treatment process. This results in patients that take a more active role in making decisions related to their treatment. Moreover, sophisticated gamification concepts guarantee long-term motivated users. From the medical facility’s point of view, screened patients are evaluated in an automated manner, which, in term, saves time and money. In addition, Feelback makes it easier to document psychological treatments. At the current state of development, further steps should focus on user acceptance testing, in order to verify, whether the mentioned concepts work as intended
Detecting Production Phases Based on Sensor Values using 1D-CNNs
Full text linkIn the context of Industry 4.0, the knowledge extraction from sensor information plays an important role. Often, information gathered from sensor values reveals meaningful insights for production levels, such as anomalies or machine states. In our use case, we identify production phases through the inspection of sensor values with the help of convolutional neural networks. The data set stems from a tempering furnace used for metal heat treating. Our supervised learning approach unveils a promising accuracy for the chosen neural network that was used for the detection of production phases. We consider solutions like shown in this work as salient pillars in the field of predictive maintenance
Entwicklung einer mobilen iOS-Anwendung zur Unterstützung von Schwangeren
No full textDas Ziel dieser Arbeit ist die Konzeption, sowie Realisation einer von iOS-Systemen unterstützten mobilen Anwendung, die durch eine individualisierte Geburtsvorsorge die Schwangere, während dieser prekären Zeit, optimal entlasten soll. Nachdem ein Fragebogen von der werdenden Mutter ausgefüllt wurde, kann dieser von der App evaluiert werden. Anhand des Resultats kann der Arzt ein persönliches Feedback erstellen. Dieses kann von der Mutter und dem behandelnden Gynäkologen eingesehen werden. Dadurch ergeben sich sowohl Vorteile für die Patientin, in Form einer umfangreicheren Behandlung, sowie für den Arzt, für den sich eine erhebliche zeitliche Entlastung ergibt, da die Notwendigkeit von direktem Kontakt und der Aufwand der Evaluierung, durch die Automatisierung, entfallen
Smartphone and Mobile Health Apps for Tinnitus: Systematic Identification, Analysis, and Assessment
No full textBackground: Modern smartphones contain sophisticated high-end hardware features, offering high computational capabilities at extremely manageable costs and have undoubtedly become an integral part in users' daily life. Additionally, smartphones offer a well-established ecosystem that is easily discoverable and accessible via the marketplaces of differing mobile platforms, thus encouraging the development of many smartphone apps. Such apps are not exclusively used for entertainment purposes but are also commonplace in health care and medical use. A variety of those health and medical apps exist within the context of tinnitus, a phantom sound perception in the absence of any physical external source. Objective: In this paper, we shed light on existing smartphone apps addressing tinnitus by providing an up-to-date overview. Methods: Based on PRISMA guidelines, we systematically searched and identified existing smartphone apps on the most prominent app markets, namely Google Play Store and Apple App Store. In addition, we applied the Mobile App Rating Scale (MARS) to evaluate and assess the apps in terms of their general quality and in-depth user experience. Results: Our systematic search and screening of smartphone apps yielded a total of 34 apps (34 Android apps, 26 iOS apps). The mean MARS scores (out of 5) ranged between 2.65-4.60. The Tinnitus Peace smartphone app had the lowest score (mean 2.65, SD 0.20), and Sanvello---Stress and Anxiety Help had the highest MARS score (mean 4.60, SD 0.10). The interrater agreement was substantial (Fleiss κ=0.74), the internal consistency was excellent (Cronbach α=.95), and the interrater reliability was found to be both high and excellent---Guttman λ6=0.94 and intraclass correlation, ICC(2,k) 0.94 (95% CI 0.91-0.97), respectively. Conclusions: This work demonstrated that there exists a plethora of smartphone apps for tinnitus. All of the apps received MARS scores higher than 2, suggesting that they all have some technical functional value. However, nearly all identified apps were lacking in terms of scientific evidence, suggesting the need for stringent clinical validation of smartphone apps in future. To the best of our knowledge, this work is the first to systematically identify and evaluate smartphone apps within the context of tinnitus
CONDA-PM: A Systematic Review and Framework for Concept Drift Analysis in Process Mining
Full text linkBusiness processes evolve over time to adapt to changing business environments.
This requires continuous monitoring of business processes to gain insights into whether they conform
to the intended design or deviate from it. The situation when a business process changes while
being analysed is denoted as Concept Drift. Its analysis is concerned with studying how a business
process changes, in terms of detecting and localising changes and studying the effects of the latter.
Concept drift analysis is crucial to enable early detection and management of changes, that is,
whether to promote a change to become part of an improved process, or to reject the change
and make decisions to mitigate its effects. Despite its importance, there exists no comprehensive
framework for analysing concept drift types, affected process perspectives, and granularity levels of a
business process. This article proposes the CONcept Drift Analysis in Process Mining (CONDA-PM)
framework describing phases and requirements of a concept drift analysis approach. CONDA-PM
was derived from a Systematic Literature Review (SLR) of current approaches analysing concept
drift. We apply the CONDA-PM framework on current approaches to concept drift analysis and
evaluate their maturity. Applying CONDA-PM framework highlights areas where research is needed
to complement existing efforts