Evaluating US Dollar Index Movements Using Markov Chains-Fuzzy States Approach

Uzun B., KIRAL E.

13th International Conference on Application of Fuzzy Systems and Soft Computing (ICAFS), Warszawa, Polonya, 27 - 28 Ağustos 2018, cilt.896, ss.386-391 identifier identifier

  • Cilt numarası: 896
  • Doi Numarası: 10.1007/978-3-030-04164-9_51
  • Basıldığı Şehir: Warszawa
  • Basıldığı Ülke: Polonya
  • Sayfa Sayıları: ss.386-391


The U.S. dollar (USD) is one of the most used currencies in the world and also the most commonly used currency in international payments. The U.S. dollar index (USDX) is a measure of the value of the USD relative to the value of a basket of currencies of the majority of the U.S.'s most significant trading partners. Therefore, dollar index gives to market players and regulators more valuable information about the dollar value rather than the regional value among the currencies. Since it can be counted as a key indicator for the direction of the USD, the Central Banks are also closely monitoring the USDX. In recent years, large fluctuations in dollar value have caused US price instability to increase. The aim of this study is to classify the USDX with triangular fuzzy sets and evaluate the USDX movements using Markov Chain of the Fuzzy States method. The data used in this study consist of the monthly changes rate of the USDX over the January 2003 to May 2018 period. The movements of the monthly USDX have been analysed with the probabilistic transition matrix of the fuzzy states, then the steady condition of the changes rate of the USDX has been presented. These outcomes give significant information to the decision makers about the USDX movements. With this model, we are able to evaluate USDX movements and estimate the expected USDX for long and short term without missing any movements between boundaries of the states.