Abstract
With the rapid development of advanced information technology in data collection and data analysis, an enterprise has more opportunities to analyze and synthesize customer behaviors and profiles to increase competitiveness, adjust product market position, and build customer loyalty. Thus, a customer-centric enterprise shifts its focus from simply getting data to obtaining meaningful knowledge. A contact center is an important part in Customer Relationship Management (CRM). A customer gets the first impression of an enterprise from contacting with the contact center. The performance of contact center may influence the loyalty of the customers, so an appropriate evaluation of its achievement and performance is necessary. We define the significant Key Performance Indicators (KPIs) of contact center operations, and generate the indicators of customer satisfaction and agent performance. The customer satisfaction and agent performance are measured using the weighted average of KPIs. The weights of the customer satisfaction KPIs are derived by neural network methodology. An enterprise can improve its contact center performance by comparing its KPIs values to the industry’s benchmarks values. This research uses data mining technology (such as clustering and neural network) to develop the contact center evaluation methods for the continuous improvement of customer service quality.