An Interval Type-2 Fuzzy Logic System for the Modeling and Prediction of Financial Applications

In the recent years, there has been growing interest in developing tools for the modeling and prediction of financial applications. The problem of financial applications is that there are huge data sets available which are sometimes incomplete, and almost always affected by noise and uncertainty. Some techniques used in financial applications employ black box models which do not allow the user to understand the behavior and dynamics of the given application. In this paper, we present a type-2 Fuzzy Logic System (FLS) for the modeling and prediction of financial applications. The proposed system avoids the drawbacks of the existing type-2 fuzzy classification systems where the proposed system is able to carry prediction based on a pre-specified rule base size even if the incoming input vector does not match any rules from the given rule base. We have performed several experiments based on the London Stock Exchange data which was successfully used to spot ahead of time arbitrage opportunities. The proposed type-2 FLS has outperformed the existing type-2 fuzzy logic based classification systems and the type-1 FLSs counterparts when using pre-specified rule bases.