Using Information Technology Management with Artificial Intelligence Techniques

Objective: The priority ticket and request for charge are crucial services and activities in any organization that must be considered based on their significance. Theoretical Framework: Information technology management (ITM) is the process of supervising and controlling an organization's information technology systems, which includes software, hardware, and network, with the goal of improving the effectiveness of information systems. Method: This study utilized four Artificial Intelligence techniques: multilayer perceptron, decision tree, K closest neighbor, and random forest. Next, we utilized the dataset obtained from the Kaggle website that pertains to the ITM field. Results and Discussion: The findings indicated that the Random Forest (RF) and Decision Tree (DT) algorithms exhibited superior performance in the initial experiment, however all algorithms yielded identical results in the subsequent experiment. Research Implications: We proceed by addressing missing values, transforming feature types into appropriate formats, and standardizing the data. Additionally, we employed four assessment metrics to evaluate the performance of the algorithms: accuracy, f1-score, recall, and precision. Lastly, we conducted two experiments: the first one will include predicting priority tickets, while the second one will focus on anticipating requests for charges. Originality/Value: This paper applied four Artificial Intelligence techniques: random forest, decision tree, K nearest neighbor, and multilayer perceptron. Then, we obtained the dataset from the Kaggle website related to the ITM field and applied three preprocessing steps: filling in missing values, converting types of features from categorical features to numerical features, and scaling the data.