Year: 2024
Type: dissertation
Abstract: Recent advances in artificial intelligence (AI) offer new opportunities for companies to streamline operations and gain a competitive edge. This thesis explores the potential of AI to improve customer support operations within a specific unit of a case company. The study addresses three research questions: (1) What AI solutions are currently possible for different types of requests? (2) What is the most relevant data for training the AI model? (3) What key factors should future research address to improve AI solutions? To answer these questions, the research analyzed customer support tickets from a three-month period, categorizing them into two groups based on their resolution methods. Group 1 consisted of cases that are straightforward to resolve, typically requiring only order-specific data from the company’s enterprise resource planning (ERP) system provided by SAP. Group 2 included more complex cases that required additional investigation, often involving internal documentation or collaboration with engineers. The analysis found that tasks in Group 1, due to the dynamic nature of order-specific data, were not ideal for direct AI model training. However, an AI-powered chatbot could assist specialists by providing guidance on case resolution and navigating the SAP ERP system. In contrast, tasks in Group 2, which involve more stable data such as technical documentation, are more suitable for AI integration. AI models trained on this data could improve information retrieval efficiency. To test these findings, a pilot implementation was conducted using a subset of Group 2 cases. The pilot showed promising results, demonstrating the potential for further AI integration. However, limitations were also identified, including challenges with data processing and handling complex queries. This study provided a solid framework for future research and AI implementations within the case company. Moving forward, enhancing AI models through improved data preprocessing and broader training datasets is crucial. Further investment in advanced AI technologies and their integration to support ticket system can significantly improve customer support capabilities. Collaboration with IT specialists and engagement with other ongoing AI projects within the company are recommended to optimize resources and maximize benefits.
Source: Osuva (University of Vaasa)
Author: Olli, Petteri
Language: English
Topic: AI in Service Interactions
Subfield: Marketing
Domain: Social Sciences
Open Access status: green
OpenAlex ID: W7053722893