Performance of machine learning algorithms for IT incident management

Mohammad Agus Prihandono, Ruki Harwahyu, Riri Fitri Sari

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

Incident Management is a part of managing IT services, improving services, and achieving organizational goals. IT incidents can be learned and predicted future incidents. This research compares the factors that cause incidents using initial machine learning techniques such as Random Forest, SVM, Multilayer perceptron, and the latest machine learning techniques such as RNN, LSTM, GRU, to predict IT incidents. Grid search is used to find the optimal parameter combination. 5-fold and 10-fold Cross-validation evaluates the model's optimal performance by dividing the dataset into training data and test data. The results show that the highest accuracy of 98.866% is produced by LSTM machine learning techniques at 5-fold and 10-fold cross-validation. SVM has the lowest accuracy of 97.837% made at 5-fold and 10-fold cross-validation.

Original languageEnglish
Title of host publication2020 11th International Conference on Awareness Science and Technology, iCAST 2020
PublisherInstitute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)9781728191195
DOIs
Publication statusPublished - 7 Dec 2020
Event11th International Conference on Awareness Science and Technology, iCAST 2020 - Qingdao, China
Duration: 7 Dec 20209 Dec 2020

Publication series

Name2020 11th International Conference on Awareness Science and Technology, iCAST 2020

Conference

Conference11th International Conference on Awareness Science and Technology, iCAST 2020
CountryChina
CityQingdao
Period7/12/209/12/20

Keywords

  • Deep learning
  • IT Incident
  • IT Service Management
  • Machine learning

Fingerprint Dive into the research topics of 'Performance of machine learning algorithms for IT incident management'. Together they form a unique fingerprint.

Cite this