A Text-Based Predictive Maintenance Approach for Facility Management Requests Utilizing Association Rule Mining and Large Language Models
Introduction: Due to the lack of labeled data, applying predictive maintenance algorithms for facility management is cumbersome. Most companies are unwilling to share data or do not have time for annotation. In addition, most available facility management data are text data. Thus, there is a need fo...
| Main Author: | |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2024-01-01
|
| Series: | Machine Learning and Knowledge Extraction |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2504-4990/6/1/13 |
| _version_ | 1797240224014663680 |
|---|---|
| author | Maximilian Lowin |
| author_facet | Maximilian Lowin |
| author_sort | Maximilian Lowin |
| collection | DOAJ |
| description | Introduction: Due to the lack of labeled data, applying predictive maintenance algorithms for facility management is cumbersome. Most companies are unwilling to share data or do not have time for annotation. In addition, most available facility management data are text data. Thus, there is a need for an unsupervised predictive maintenance algorithm that is capable of handling textual data. Methodology: This paper proposes applying association rule mining on maintenance requests to identify upcoming needs in facility management. By coupling temporal association rule mining with the concept of semantic similarity derived from large language models, the proposed methodology can discover meaningful knowledge in the form of rules suitable for decision-making. Results: Relying on the large German language models works best for the presented case study. Introducing a temporal lift filter allows for reducing the created rules to the most important ones. Conclusions: Only a few maintenance requests are sufficient to mine association rules that show links between different infrastructural failures. Due to the unsupervised manner of the proposed algorithm, domain experts need to evaluate the relevance of the specific rules. Nevertheless, the algorithm enables companies to efficiently utilize their data stored in databases to create interpretable rules supporting decision-making. |
| first_indexed | 2024-04-24T18:04:02Z |
| format | Article |
| id | doaj.art-9aea359a7e4442b3bc8c4ec2bc674109 |
| institution | Directory Open Access Journal |
| issn | 2504-4990 |
| language | English |
| last_indexed | 2024-04-24T18:04:02Z |
| publishDate | 2024-01-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Machine Learning and Knowledge Extraction |
| spelling | doaj.art-9aea359a7e4442b3bc8c4ec2bc6741092024-03-27T13:52:04ZengMDPI AGMachine Learning and Knowledge Extraction2504-49902024-01-016123325810.3390/make6010013A Text-Based Predictive Maintenance Approach for Facility Management Requests Utilizing Association Rule Mining and Large Language ModelsMaximilian Lowin0Chair of Information Systems and Information Management, Goethe University Frankfurt, 60629 Frankfurt, GermanyIntroduction: Due to the lack of labeled data, applying predictive maintenance algorithms for facility management is cumbersome. Most companies are unwilling to share data or do not have time for annotation. In addition, most available facility management data are text data. Thus, there is a need for an unsupervised predictive maintenance algorithm that is capable of handling textual data. Methodology: This paper proposes applying association rule mining on maintenance requests to identify upcoming needs in facility management. By coupling temporal association rule mining with the concept of semantic similarity derived from large language models, the proposed methodology can discover meaningful knowledge in the form of rules suitable for decision-making. Results: Relying on the large German language models works best for the presented case study. Introducing a temporal lift filter allows for reducing the created rules to the most important ones. Conclusions: Only a few maintenance requests are sufficient to mine association rules that show links between different infrastructural failures. Due to the unsupervised manner of the proposed algorithm, domain experts need to evaluate the relevance of the specific rules. Nevertheless, the algorithm enables companies to efficiently utilize their data stored in databases to create interpretable rules supporting decision-making.https://www.mdpi.com/2504-4990/6/1/13predictive maintenancefacility managementtemporal association rule miningsentence transformersemantic similarity |
| spellingShingle | Maximilian Lowin A Text-Based Predictive Maintenance Approach for Facility Management Requests Utilizing Association Rule Mining and Large Language Models Machine Learning and Knowledge Extraction predictive maintenance facility management temporal association rule mining sentence transformer semantic similarity |
| title | A Text-Based Predictive Maintenance Approach for Facility Management Requests Utilizing Association Rule Mining and Large Language Models |
| title_full | A Text-Based Predictive Maintenance Approach for Facility Management Requests Utilizing Association Rule Mining and Large Language Models |
| title_fullStr | A Text-Based Predictive Maintenance Approach for Facility Management Requests Utilizing Association Rule Mining and Large Language Models |
| title_full_unstemmed | A Text-Based Predictive Maintenance Approach for Facility Management Requests Utilizing Association Rule Mining and Large Language Models |
| title_short | A Text-Based Predictive Maintenance Approach for Facility Management Requests Utilizing Association Rule Mining and Large Language Models |
| title_sort | text based predictive maintenance approach for facility management requests utilizing association rule mining and large language models |
| topic | predictive maintenance facility management temporal association rule mining sentence transformer semantic similarity |
| url | https://www.mdpi.com/2504-4990/6/1/13 |
| work_keys_str_mv | AT maximilianlowin atextbasedpredictivemaintenanceapproachforfacilitymanagementrequestsutilizingassociationruleminingandlargelanguagemodels AT maximilianlowin textbasedpredictivemaintenanceapproachforfacilitymanagementrequestsutilizingassociationruleminingandlargelanguagemodels |