An Algorithmic Approach for Predicting Unknown Information in Incomplete Fuzzy Soft Set

This paper proposes a novel approach to estimate the missing or unknown information in incomplete fuzzy soft sets (FSSs). Incomplete information in fuzzy soft sets leads to more uncertainty and ambiguity in decision making. The need to represent unknown or missing information using the available knowledge is becoming increasingly important. The proposed method initially finds the mean value of each parameter exploiting the existing information. Then average distance of each parameter from the mean is computed. A pair of useful distance information is derived using the average distance and mean. Next we determine the unknown information using the probabilistic weight and distance information. In order to generalize the concept, we also extend the proposed approach for finding the missing or unknown information in the context of interval-valued fuzzy soft sets. Two illustrative examples are provided to show the effectiveness of the developed approaches. The result of the proposed method for FSS has been compared with the existing method using two well-known entropy measures, Kosko's (Inf Sci 40:165-174, 1986) entropy and De Luca and Termini's (Inf Control 20:301-312, 1972) entropy. The comparative analysis has shown that the proposed approach is preferable as it has less entropy, i.e., less degree of fuzziness than that of the existing approach.