Perspectives in business informatics research : 23rd International Conference on Business Informatics Research, BIR 2024, Prague, Czech Republic, September 11-13, 2024, proceedings / Václav Řepa, Raimundas Matulevičius, Emanuele Laurenzi, editors.
This book constitutes the proceedings of the 23rd International Conference on Perspectives in Business Informatics Research, BIR 2024, which took place in Prague, Czech Republic, in September 2024. The central theme of BIR 2024 was "Artificial Intelligence (AI) in Business Informatics: Opportun...
Saved in:
| Online Access: |
Full Text (via Springer) |
|---|---|
| Corporate Author: | |
| Other Authors: | , , |
| Other title: | BIR 2024 |
| Format: | Conference Proceeding eBook |
| Language: | English |
| Published: |
Cham :
Springer,
[2024]
|
| Series: | Lecture notes in business information processing ;
529. |
| Subjects: |
Table of Contents:
- Intro
- Preface
- Organization
- Keynotes
- Democratization of AI Tools: Bridging the Gap between Business Informatics and Accessible AI Innovation
- A Meaningful Road to Explanation
- Contents
- AI Opportunities and Challenges
- Business, Data and Analytics: Specifying AI Use Cases with the Help of Modeling Techniques
- 1 Introduction
- 2 Case Study Setting and Related Requirements
- 2.1 Case Study Setting
- 2.2 Case Study Requirements
- 3 Related Work and Choice of the Conceptual Model
- 3.1 Business View
- 3.2 Data and Analytics View
- 4 Application in a Real-World Case Study
- 4.1 Business View by Top-Down Strategy
- 4.2 Business View by User-Centric Strategy
- 4.3 Data View for the Prediction of Annual Construction Costs
- 4.4 Analytics View for the Prediction of Annual Construction Costs
- 5 Usefulness and Practical Application Tips
- 5.1 Usefulness of the Conceptual Models
- 5.2 Efficient Use of the Conceptual Model
- 6 Conclusion
- References
- Generative AI for BPMN Process Analysis: Experiments with Multi-modal Process Representations
- 1 Introduction
- 2 Large Language Models and the BPM Lifecycle
- 3 Related Works
- 4 Experimental Setup
- 5 Experimental Outcomes and Evaluation
- 5.1 RDF vs. XML Formats
- 5.2 RDF vs. Images (PNG)
- 5.3 Future Work: Serialization Generation
- 6 Conclusions
- References
- LLM-Assistance for Quality Control of LLM Output
- 1 Introduction
- 2 Theoretical Background
- 2.1 Large Language Models
- 2.2 LLM Support for Enterprise Modelling
- 3 Related Work
- 3.1 Quality Evaluation of LLM Output
- 3.2 Literature Analysis on LLM for Quality Control in EM
- 4 Quality Criteria for LLM Output in EM
- 4.1 Definition of Quality Criteria
- 4.2 Operationalization of the Defined Criteria
- 5 Experiments into LLM for Quality Control of LLM in EM
- 5.1 Experiments in Triangulation
- 5.2 Experiments in Inverse Mappings
- 6 Conclusion and Future Work
- References
- AI Applications and Use Cases in Business
- Unlocking Viewer Insights in Linear Television: A Machine Learning Approach
- 1 Introduction
- 2 Pipeline
- 2.1 Data Collection
- 2.2 Determining Viewer Time Slots
- 2.3 Content Genre Biases: Unveiling Viewer Preferences
- 2.4 Device Signature: Capturing Essential Features
- 2.5 Household Categorisation: Timing and Content
- 3 Data Analysis and Feature Selection
- 3.1 Classification Results
- 3.2 Feature Significance
- 4 Machine Learning Experiments and Results
- 4.1 Error Analysis: Confusion Matrices
- 4.2 Summary of Results
- 5 Related Works
- 6 Conclusions and Future Work
- References
- Comparison of AI-Based Document Classification Platforms
- 1 Introduction
- 2 Overview of the Field of Document Classification
- 3 Comparison Methodology
- 3.1 Description of the Dataset Used for the Study
- 3.2 Free Open Source Models Implementation