BACKGROUND: The valuation of tea depends on the sensory assessments made by the Brokers and Buyers (Tea Tasters) to a large extent, though the market conditions and the requirements of a particular Buyer play an important role in determining the basic prices of teas. Again, there are several biochemical quality parameters in tea on which the quality of a particular tea depends. It is not straightforward to establish the reflection of biochemical quality characteristics in tea on the Taster's sensory assessments and price because of the complex dynamics within chemical properties and the inherent subjectivity of quality evaluation through the Taster's scores. It is, however, important to judge the market valuation of teas from quality assessments and biochemical properties. This paper describes the advantages of using statistical data-mining techniques to explore the association of biochemical quality parameters in teas with the Taster's sensory assessments, and the application of a nonparametric statistical technique, multivariate adaptive regression splines (MARSplines), to establish the predictability of the realised prices of teas from sensory assessments.