Improving IT Service Incident Resolution by Using an FAQ System

Abstract

As the enterprise computing becomes more and more complex, recently, the cost of IT system maintenance in enterprises has become a significant problem from the perspective of technology as well as business operations. One approach to managing the IT system maintenance cost is preparing and leveraging an FAQ (Frequently Asked Questions) system as a way of knowledge management and reuse. However, because the preparation of an FAQ system and data may take significant investment, a cost justification for such a system is essential. In an effort to analyze the cost and effect of the FAQ approach, in this paper, we observed a software maintenance project where 66 FAQs were prepared and monitored for a period of 15 months. We found that 67% of the practitioner's resolution time was saved with FAQ references. We also applied our novel Natural Language Processing techniques using conditional branches, sequential analysis and topic detection as domain independent methods. We found that the number of text segments has strong correlation with the time and cost savings. We designed an FAQ system based on these findings and observed that more than 70% of the practitioners who tested the system reported that it is useful and significantly improved their productivity.