Retrieval of important concepts from generalized one-sided concept lattice

One of the approaches used in data analysis area is related to the theory of concept lattices. It is known as formal concept analysis (FCA), which is used for analysis of object-attribute input data models. The output of FCA is represented by concept lattice, which is the hierarchically organized structure of groups of objects with shared attributes (concepts). One of the main issues of FCA is a large number of concepts in generated concept lattice. In this paper, we present a solution based on information retrieval methods, where on the input is user query of what he/she wants to find in concept lattice and on the output we get concepts which best fits input query. Also, some interactive methods for visualization of best concepts are presented. Our approach is applied on concept lattice generated by the model of Generalized One-Side Concept Lattices (GOSCL), which against classical FCA models is suitable to work with different types of attributes used in input data tables. In order to work with this model, the modified Hamming distance was introduced for comparison of values of complex types of attributes.