Parallel classification and optimization of telco trouble ticket dataset

Yayah, Fauzy Bin Che; Ghauth, Khairil Imran; Ting, Choo-Yee

doi:10.12928/telkomnika.v19i3.18159

Cited by 3 publications

(6 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In both tables, we have categorized the details of the automated model as implemented in the literature. Among the ML classifiers, Support Vector Machine (SVM) is the most popular [3,4,5,17,18,19,20,21,22,25,28,29,30,31], followed by Naive Bayes (NB) [1,3,4,5,17,19,22,28,29,30,31,33], Decision Tree (DT) [1,2,3,5,17,19,25,26,28,34], K-Nearest Neighbour (KNN), [3,5,19,28,31] Logistic Regression (LR) [1,5,22,27,29], and Random Forest (RF) [2,33]. Most ITSM models adopted the SVM algorithm as a classifier due to SVM's faster processing speed when dealing with large datasets.…”

Section: Resultsmentioning

confidence: 99%

“…In terms of the feature engineering, TF-IDF is the most preferred approach [4,17,18,19,21,22,23,29,30,31,33,34] followed by the more conventional Count Vectorizer [3,28]. The other feature analysis tools and techniques adopted in the literature are linguistic feature [5], parts of speech tagging (PoS) [20], Jira ticketing system [25] used TF-IDF , Hadoop [26] to countvectorizer , and Weka tool [31] for word embeddings.…”

Section: Resultsmentioning

confidence: 99%

“…Another major hurdle is the cost associated with the implementation of AI-based solutions. Organizations are required to significantly upgrade their IT infrastructure and potentially handle the extensive data migration and/or curation processes, which may be challenging and indeed off putting for organizations as there may be initial investment required in terms of new IT infrastructure as well as time involved in bring domain experts, IT staff and AI experts together to understand challenges and curate data [15,26].…”

Section: Discussion and Challengesmentioning

confidence: 99%

“…The vocabulary generated during tokenization will be predominantly from the majority class compared to the minority class. This has an adverse effect on the performance of real-time IT incidents as indicated by Yayah et al [26]. Although complex, Zaidi et al [15] demonstrated the capability of BERT (i.e., a deep transfer learning algorithm, as mentioned earlier) to handle the skewed distribution of classes without applying any re-sampling technique, which would be suitable for IT incidents dataset.…”

Section: Discussion and Challengesmentioning

confidence: 99%

See 3 more Smart Citations

AI for Information Technology Operation (AIOps): A Review of IT Incident Risk Prediction

Ahmed¹,

Singh²,

Doherty³

et al. 2022

2022 9th International Conference on Soft Computing &Amp; Machine Intelligence (ISCMI)

View full text Add to dashboard Cite

The advancement of Artificial Intelligence has led to a surge in its application in Information Technology (IT) Operations, often termed Artificial Intelligence for IT Operations (AIOPS). One of the most challenging problems in AIOPS is IT Service Management (ITSM), which deals with incidents and anomalies of users, often referred to as tickets. These tickets are resolved by the IT firm support system, which plays a significant role in the company's user experiences, productivity, and profit. Recent advances have been made to automate the prediction of IT incidents and resolve them in a minimal time, utilizing AI models. In this paper, we take stock of the work in this domain and review the challenges. We also highlight the open topics that require further investigation for the advancement of the field.

show abstract

Section: Resultsmentioning

confidence: 99%

Section: Resultsmentioning

confidence: 99%

Section: Discussion and Challengesmentioning

confidence: 99%

Section: Discussion and Challengesmentioning

confidence: 99%

See 2 more Smart Citations

AI for Information Technology Operation (AIOps): A Review of IT Incident Risk Prediction

Ahmed¹,

Singh²,

Doherty³

et al. 2022

2022 9th International Conference on Soft Computing &Amp; Machine Intelligence (ISCMI)

View full text Add to dashboard Cite

show abstract

“… In addition, big data analytics can be used to analyze real-time SDN network traffic. For example, Spark Streaming is designed to effectively process and analyze streaming data received from multiple sources in a high-speed parallel manner across the available cluster nodes [39]. Using such systems, each switch load is monitored in real-time.…”

Section: B Big Data Assists Sdn In Traffic Monitoringmentioning

confidence: 99%

A Review on Utilizing Big Data Techniques for Performance Improvement in Software Defined Networking

2023

IJCCCE

View full text Add to dashboard Cite

Traditional network abilities have a drastic shortage in the current networking world. Software-Defined Networking (SDN) is a revival development in the networking domain that provides separation of control and data planes, enlarges the data plane granularity, and simplifies the network devices. All these factors accelerate and automate the evolution of new services. However, when the SDN network topology becomes large, it poses new challenges in security, traffic management, and scalability due to the vast amounts of traffic data generated and the need for additional controllers to manage the significant number of networking devices. On the other hand, big data has become an attractive trend that can enhance network performance in general, specifically SDN. Both SDN and big data have gained great attraction from industry and academia. Traditionally, these two subjects have been studied separately in most of the preceding works. However, big data can impact the design and implementation of SDN thoroughly. This paper presents how big data can support SDN in various aspects, including intrusion detection, traffic monitoring, and controller scalability and resiliency. We suggest several approaches toward deeper cooperation between big data and SDN. Index Term – SDN, big data, Spark, graph database, traffic engineering, intrusion detection.

show abstract

An Empirical Analysis of State-of-Art Classification Models in an IT Incident Severity Prediction Framework

et al. 2023

View full text Add to dashboard Cite

Large-scale companies across various sectors maintain substantial IT infrastructure to support their operations and provide quality services for their customers and employees. These IT operations are managed by teams who deal directly with incident reports (i.e., those generated automatically through autonomous systems or human operators). (1) Background: Early identification of major incidents can provide a significant advantage for reducing the disruption to normal business operations, especially for preventing catastrophic disruptions, such as a complete system shutdown. (2) Methods: This study conducted an empirical analysis of eleven (11) state-of-the-art models to predict the severity of these incidents using an industry-led use-case composed of 500,000 records collected over one year. (3) Results: The datasets were generated from three stakeholders (i.e., agency, customer, and employee). Separately, the bidirectional encoder representations from transformers (BERT), the robustly optimized BERT pre-training approach (RoBERTa), the enhanced representation through knowledge integration (ERNIE 2.0), and the extreme gradient boosting (XGBoost) methods performed the best for the agency records (93% AUC), while the convolutional neural network (CNN) was the best model for the rest (employee records at 95% AUC and customer records at 74% AUC, respectively). The average prediction horizon was approximately 150 min, which was significant for real-time deployment. (4) Conclusions: The study provided a comprehensive analysis that supported the deployment of artificial intelligence for IT operations (AIOps), specifically for incident management within large-scale organizations.

show abstract

Parallel classification and optimization of telco trouble ticket dataset

Cited by 3 publications

References 22 publications

AI for Information Technology Operation (AIOps): A Review of IT Incident Risk Prediction

AI for Information Technology Operation (AIOps): A Review of IT Incident Risk Prediction

A Review on Utilizing Big Data Techniques for Performance Improvement in Software Defined Networking

An Empirical Analysis of State-of-Art Classification Models in an IT Incident Severity Prediction Framework

Contact Info

Product

Resources

About