The Role of Automated Semiotic Classifications in Economic Domains

Over the years, scientists in intelligent technologies have adopted several approaches for the automated representation of the real world. An essential part of these attempts is the classification algorithms that give researchers an efficient way of acquiring and ordering data. This is particularly true in pattern recognition and related topics in the field of soft computing. This paper introduces a novel, more suitable way of handling classifications based on the elements of the semiotic process (signs, objects and meanings). This is, in several ways, more appropriate for the analysis of economic problems, where a thorough knowledge of the elements involved is required for sensible results. Because the core structure of real-world phenomena is essentially semiotic, an attempt to represent and handle real-world problems has to be based, at least in part, on semiotic procedures. The main difference between this and mainstream approaches to soft computing is the role that meaning plays in the classification process. Moreover, significance is a key element that can be used for further development of models with more economic content. A classification for a decision-making environment in finance using this automated semiotic approach is also presented.