User Related Challenges of Self-Service Business Intelligence

Lennerholt, Christian; Laere, Joeri van; Söderström, Eva

doi:10.24251/hicss.2020.024

Cited by 6 publications

(3 citation statements)

References 17 publications

(28 reference statements)

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Anhand der bereitgestellten Hinweise zur Durchführung und Interpretation der Analyseergebnisse ist es möglich ein solches System so zu gestalten, dass Anwender zudem durch eine intelligente Mensch-Software-Interaktion unter Bereitstellung spezifischer Hilfestellungen zur eigenständigen Analyse der logistischen Leistungsfähigkeit befähigt werden. Ein solches Self-Service-Business-Intelligence (SSBI) System erlaubt es Verantwortlichen der PPS, auch ohne Einbezug von Data Scientists, die richtigen Daten aus der Vielzahl möglicher Rohdaten sinnvoll auszuwählen und nutzerzentrierte Datenanalysen selbstständig durchzuführen (Lennerholt et al 2019). Abbildung 9 visualisiert die Grundidee eines solchen Systems.…”

Section: Technische Möglichkeiten Zur Integration In Ein It-basiertesunclassified

Datenbasierte Ursachenanalysen zur Verbesserung der logistischen Zielerrei-chung

Schmidt¹,

Maier²,

Härtel³

2020

Mensch-Technik-Interaktion in Der Digitalisierten Arbeitswelt

View full text Add to dashboard Cite

Section: Technische Möglichkeiten Zur Integration In Ein It-basiertesunclassified

Datenbasierte Ursachenanalysen zur Verbesserung der logistischen Zielerrei-chung

Schmidt¹,

Maier²,

Härtel³

2020

Mensch-Technik-Interaktion in Der Digitalisierten Arbeitswelt

View full text Add to dashboard Cite

“…The aspects of machine learning artifact deployment are manifold [5]: ranging from data access [6], scalability [5] and security [7] up to interface design [8]. However, one aspect needs to be incorporated into the very early design of the models: The phenomenon of changing data over time, usually referred to as concept drift [9].…”

Section: Introductionmentioning

confidence: 99%

Switching Scheme: A Novel Approach for Handling Incremental Concept Drift in Real-World Data Sets

Baier¹,

Kellner²,

Kühl³

et al. 2020

Preprint

View full text Add to dashboard Cite

Machine learning models nowadays play a crucial role for many applications in business and industry. However, models only start adding value as soon as they are deployed into production. One challenge of deployed models is the effect of changing data over time, which is often described with the term concept drift. Due to their nature, concept drifts can severely affect the prediction performance of a machine learning system.In this work, we analyze the effects of concept drift in the context of a real-world data set. For efficient concept drift handling, we introduce the switching scheme which combines the two principles of retraining and updating of a machine learning model. Furthermore, we systematically analyze existing regular adaptation as well as triggered adaptation strategies. The switching scheme is instantiated on New York City taxi data, which is heavily influenced by changing demand patterns over time. We can show that the switching scheme outperforms all other baselines and delivers promising prediction results.

show abstract

“…Apart from that, we want to incorporate a qualitative analyses of transcriptions of interviews into the future case studies. Finally, user experience (UX) in dashboards [26,86] is an interesting avenue for future work.…”

Section: Discussionmentioning

confidence: 99%

A Cross-Organizational Process Mining Framework

Aksu¹

View full text Add to dashboard Cite

Groups of people collaborate within organizations to deliver value to their customers. To establish such collaborations, which can lead to valuable outcomes for customers, a set of coordinated activities, events, and decision points are orchestrated in business processes. However, due to the diverse contexts of organizations, the meaning of terms used in business processes often differ from one organization to another. Moreover, the way a business process is executed may differ across organizations, in some branches of the same organization, or for certain products or services offered to customers, or even across organizational units. Those differences, furthermore, affect both the performance of business processes and the relevance of performance indicators used for measuring that performance. Therefore, when such points are not taken into account, efforts to enable organizations to learn from each other for performance improvement can lead to three main issues, namely unfairness, inaccuracy, and inadequacy.The aforementioned issues inspire the work in this thesis. In particular, the thesis focuses on providing relevant insights for organizations to improve their performance by learning from each other. With the theoretical Cross-Organizational Process Mining Framework that we developed, that learning becomes possible for organizations. The main contributions of this thesis are five approaches. The approach for automatically deriving Key Performance Indicators (KPIs) from Ontological Enterprise Models deals with the unfairness issue. Inaccuracy is the main focus of the approach for predicting relevant KPIs for organizations. Identifying the perspectives that can be adequate for organizations to learn from each other is the main focus of the two other approaches: the approach for the automated generation of engaging dashboards and the approach for interactive process performance dashboard generation. The last approach is devoted to building process benchmarks for performance improvement such that organizations can benefit from each others' best practices. Each approach is applied in a real-life setting to show its usefulness and practical value.Overall, the work presented in this thesis provides important contributions to perform crossorganizational process mining in a fair, accurate, and adequate fashion.

show abstract

User Related Challenges of Self-Service Business Intelligence

Cited by 6 publications

References 17 publications

Datenbasierte Ursachenanalysen zur Verbesserung der logistischen Zielerrei-chung

Datenbasierte Ursachenanalysen zur Verbesserung der logistischen Zielerrei-chung

Switching Scheme: A Novel Approach for Handling Incremental Concept Drift in Real-World Data Sets

A Cross-Organizational Process Mining Framework

Contact Info

Product

Resources

About