The insurance industry of Iran has been experienced dramatic growth in the last decade. And insurance agents play a major role in transaction volume in this industry. Therefore, the selectionprocess of new agents is of vital importance. This study focuses on the characteristics of data warehousing and the appropriate data mining techniques to be used to support agent selection in the insurance industry. We examined three common data mining methods – discriminant analysis, decision trees and artificial neural networks – to predict the duration of service, sales premiums, and persistence indices of insurance agents. The results revealed that work experience, job position, age, marital status, previous occupation, past annual income, and insurance policies sold are the important factors influencing the length of stay for new insurance agents, the number of insurance policies sold, and the extension of insurance policies sold. This study specifically aimed to design and develop an intelligent decision support system, namely an ‘ Intelligent Agent Recruitment Assistant for Insurance’ companies, to help insurance managers to select quality agents.