Temporal Linguistic Summaries of Time Series Using Fuzzy Logic

We consider linguistic summaries of time series used for an analysis of the past performance of investment (mutual) funds to help make future investment decisions. We use results from psychology, cognitive sciences and human decision making, which indicate a crucial role of time in the sense that means and ends, like decisions and outcomes, have a varying relevance and impact depending on the time when they occur, notably that what occurs in a more immediate past is more relevant and meaningful that what has occurred earlier. We propose to take into account some of psychological findings related to the importance of time by using different protoforms of linguistic summaries, temporal linguistic summaries, a substantial extension of the protoforms employed in our previous works. We consider two types of temporal protoforms exemplified by “recently, among all segments, most are slowly increasing”, and exemplified by “initially, among all short segments, most are quickly decreasing”. We compare them with the traditional ones, and present examples of their use for the analyses of investment funds.keywordstime seriesfuzzy logicmutual fundfuture returnpast performancethese keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.