Journal
JOURNAL ON DATA SEMANTICS
Volume 10, Issue 1-2, Pages 41-56Publisher
SPRINGER HEIDELBERG
DOI: 10.1007/s13740-021-00124-z
Keywords
Complaint management; Quality management; Process prediction; Machine learning; Deep learning
Categories
Funding
- Projekt DEAL
Ask authors/readers for more resources
This paper explores how available data can be used to automate support for complaint handling processes in medical technology companies. By designing a deep learning prototype, partial process automation was successfully achieved with promising results in practice.
Complaints about finished products are a major challenge for companies in the medical technology industry, where product quality is directly related to public health and therefore strictly regulated. In this paper, we examine how available data can be used to provide automated support to the complaint handling processes in the medical technology companies. We identify the automation potentials in the 8D reference process for complaint management and discuss their organizational and technical challenges. Using data from a large manufacturer of medical products, we show how partial process automation can be achieved in practice by designing, implementing, and evaluating a deep learning-based prototype for automatically suggesting a likely error code for future complaints, given their textual description. Our approach is able to assign the correct error code for more than 75% of all cases and outperforms the conventional classification approaches used as a baseline comparison. Our results show that partial automation of a complaint management process by means of deep learning can be achieved in practice.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available