The chances of winning highly valued Information Technology (IT) service contracts are influenced by various factors. Identifying key factors driving the competition and the early prediction of the outcome (either winning or losing such sales opportunities) can have significant business benefits. Given the complexity of IT services, range of potential attributes, and scarcity of comparable data sets, the straightforward approach of developing predictive analytical models that works well in other industries, such as consumer products, tends to achieve lower accuracy in this context. In this paper, we develop an approach that uses business insights and domain knowledge in the classification of several of the attributes influencing the outcome. We show how using this approach in a naïve Bayes predictive analytics framework can vastly improve the prediction accuracy. Further, we discuss two applications of our model, early prioritization of newly validated sales opportunities and optimization of sales force allocation and planning.