Various techniques, based on Formal Concept Analysis (FCA), for deriving conceptual structures from data have been investigated. Data is usually represented as a two-dimensional context of objects and fea tures. FCA discovers dependencies within the data based on the relation among objects and features. On the other hand, the probability logic represents and reasons with both statistical and propositional probabil ity among data. Both FCA and probability logic are useful tools for data analysis. We develop a novel approach for data analysis called SPICE -Symbiotic integration of Probability Inference and Concept Extraction. SPICE is expected to provide a more flexible and robust data analysis model as it integrates novel features of both FCA and probability logic.