Deep learning based it service desk ticket classifier using CNN
By: Paramesh, S. P
.
Contributor(s): Shreedhara, K. S.
Publisher: Chennai ICT Academy 2022Edition: Vol.13(1), Oct.Description: 2805-2812p.Subject(s): Computer EngineeringOnline resources: Click here
In:
ICTACT Journal on Soft Computing (IJSC)Summary: Assignment of problem tickets to a proper resolver group is an
important aspect and crucial step in any IT Service management tools
like IT Service desk systems. Manual categorization of tickets may lead
to dispatching of problem tickets to an inappropriate expert group,
reassignment of tickets, delays the response time and interrupts the
normal functioning of the business. Traditional supervised machine
learning approaches can be leveraged to train an automated service
desk ticket classifier by using the historical ticket data. Sparsity, non-
linearity, overfitting and handcrafting of features are some of the issues
concerning the traditional ticket classifiers. In this research work, a
deep neural network based on Convolution Neural Network (CNN) is
proposed for the automated classification of service desk tickets. CNN
automatically extracts the most salient features of the ticket
descriptions represented using word embeddings. The extracted
features are further used by the output classification layer for efficient
ticket category prediction. To corroborate the efficacy of the proposed
ticket classifier model, we empirically validated it using a real IT
infrastructure service desk data and compared the results with the
traditional classifier models like Support Vector machines, Naive
Bayes, Logistic Regression and K-nearest neighbour. The proposed
CNN model with proper hyperparameters tuning outperforms the
traditional classifiers in terms of overall model performance.
Assignment of tickets to the correct domain groups, speedy resolution,
improved productivity, increased customer satisfaction and
uninterrupted business are some of the benefits of the proposed
automated ticket classifier model.
| Item type | Current location | Call number | Status | Date due | Barcode | Item holds |
|---|---|---|---|---|---|---|
Articles Abstract Database
|
School of Engineering & Technology Archieval Section | Not for loan | 2023-0518 |
Assignment of problem tickets to a proper resolver group is an
important aspect and crucial step in any IT Service management tools
like IT Service desk systems. Manual categorization of tickets may lead
to dispatching of problem tickets to an inappropriate expert group,
reassignment of tickets, delays the response time and interrupts the
normal functioning of the business. Traditional supervised machine
learning approaches can be leveraged to train an automated service
desk ticket classifier by using the historical ticket data. Sparsity, non-
linearity, overfitting and handcrafting of features are some of the issues
concerning the traditional ticket classifiers. In this research work, a
deep neural network based on Convolution Neural Network (CNN) is
proposed for the automated classification of service desk tickets. CNN
automatically extracts the most salient features of the ticket
descriptions represented using word embeddings. The extracted
features are further used by the output classification layer for efficient
ticket category prediction. To corroborate the efficacy of the proposed
ticket classifier model, we empirically validated it using a real IT
infrastructure service desk data and compared the results with the
traditional classifier models like Support Vector machines, Naive
Bayes, Logistic Regression and K-nearest neighbour. The proposed
CNN model with proper hyperparameters tuning outperforms the
traditional classifiers in terms of overall model performance.
Assignment of tickets to the correct domain groups, speedy resolution,
improved productivity, increased customer satisfaction and
uninterrupted business are some of the benefits of the proposed
automated ticket classifier model.
Click on an image to view it in the image viewer
There are no comments for this item.