University of Twente Student Theses
Improving the utilisation of AI Ops analyses by improving the quality of incident logging data
Idema, N.B. (2022) Improving the utilisation of AI Ops analyses by improving the quality of incident logging data.
|
PDF
1MB |
| Abstract: | This study focuses on improving the data quality of the incident registration process at Rabobank, so the Artificial Intelligence (AI) recovery of incidents in Rabobank’s Information Technology (IT) systems can be improved. The goal of the improved data quality is that a solution recommender can be built, which recommends solutions to operators, meaning that the time it takes an operator to solve a problem will be decreased. This in turn reduces the impact of the incident, meaning that the action problem of having more impactful incidents than preferred is remediated through the core problem: The quality of data of the incident registration process is insufficient to optimise AI recovery of incidents. This lack of data quality is expressed in two manners. First, measurements show that field ‘solution’ is too often filled in with a non-English language, or not filled in at all. Second, the user ratings required for a recommender system cannot be collected. The goal of this study is to find a way to collect the required user ratings from Artificial Intelligence for Operations (AIOps) using teams and to find a way to improve the quality of data filled in by all teams. The AIOps-using teams can test the non-AIOps-specific solutions. |
| Item Type: | Essay (Bachelor) |
| Faculty: | BMS: Behavioural, Management and Social Sciences |
| Subject: | 70 social sciences in general |
| Programme: | Industrial Engineering and Management BSc (56994) |
| Link to this item: | https://purl.utwente.nl/essays/92970 |
| Export this item as: | BibTeX EndNote HTML Citation Reference Manager |
Show download statistics for this publication
Show download statistics for this publicationRepository Staff Only: item control page