In the field of thermal engineering and commercial HVAC applications, heat exchanger is one of the most important equipment. For practical design of heat exchanger, it is important to study the heat transfer characteristics of pipe flow such as the identification of the flow regime and the prediction of the heat transfer performance. In recent years, Ghajar and his co-workers (1994, 1995 and 2006) successfully developed heat transfer correlations and flow regime maps for horizontal circular pipes under uniform wall heat flux boundary condition and three different inlet configurations (re-entrant, square-edged, bell-mouth). The heat transfer correlations and the boundary lines of the flow regime map were developed based on the traditional method such as least-squares method with specified functional form. Recently, Support Vector Machines (SVM) were widely successfully applied for regression problem and classification problem (Chen et al., 2006, Vong et al., 2006, Trafalis et al., 2005). Therefore, the SVM method is proposed for development of heat transfer correlation and flow regime maps for heated horizontal pipe. The results show that the new flow regime map can classify the forced and mixed convection experimental data of Ghajar and Tam (1994) into different flow regimes with good accuracy, and the new heat transfer correlation can predicted majority of the transitional forced and mixed convection experimental data of Ghajar and Tam (1994) within 5% deviation.