Forecasting Exchange Rates: A Neuro-Fuzzy Approach
نویسندگان
چکیده
This paper presents an adaptive neuro-fuzzy inference system (ANFIS) for USD/JPY exchange rates forecasting. Previous work often used time series techniques and neural networks (NN). ANFIS can be used to better explain solutions to users than completely black-box models, such as NN. The proposed neurofuzzy rule based system applies some technical and fundamental indexes as input variables. In order to generate membership functions (MFs), we make use of fuzzy clustering of the output space. The neuro-fuzzy model is tested with 28 candidate input variables for both currencies. For the purpose of comparison, Sugeno-Yasukawa model, feedforward multi-layer neural network, and multiple regression are benchmarked. The comparison demonstrates that the presented algorithm shows its superiority in terms of prediction error minimization, robustness and flexibility. Keywords— ANFIS Network, Exchange Rates, Forecasting, Neuro-Fuzzy Systems, Nonlinear Identification.
منابع مشابه
Prediction of foreign exchange rates by neural network and fuzzy system based techniques
Forecasting currency exchange rates are an important financial problem that is receiving increasing attention especially because of its intrinsic difficulty and practical applications. This paper presents improved neural network and fuzzy models used for exchange rate prediction. Several approaches including multi-layer perceprtons, radial basis functions, dynamic neural networks and neuro-fuzz...
متن کاملLong-term Forecasting of Electrical Load using Gustafson-Kessel clustering algorithm on Takagi-Sugeno type MISO Neuro- Fuzzy network
1.1. Problem definition: Neuro-Fuzzy Approach in Electrical Load Forecasting Modeling and identification of electrical load processes are essential for the operation and also planning of a utility either for a company or for a country. Electrical load forecasting is needed because people intend to make important decision on generating power generators, load switching, purchasing strategy and al...
متن کاملFinancial Time Series Forecasting Using Neuro Fuzzy Approach for the Bucharest Stock Exchange
The motivation of this study is the research of an originally engineering field, but with important implications and applications for economics, in general and finance, in particular. Forecasting financial time series is the goal of many studies that combine concepts from various disciplines, in terms of classical theories or of the latest approaches, forming a point of great interest. Financia...
متن کاملForecasting Stock Exchange Market Using Hybrid Neuro Fuzzy Model
This paper proposes a hybrid approach based on neuro fuzzy model and emotional learning for prediction of stock exchange market. Neuro fuzzy models are powerful in modeling and forecasting highly nonlinear and complex time series. The emotional Learning, which is successfully used in bounded rational decision making, is introduced as an appropriate method to achieve particular goals in the pred...
متن کاملDaily irrigation water demand prediction using Adaptive Neuro- Fuzzy Inferences Systems (ANFIS)
One of the main problems in the management of large water supply and distribution systems is the forecasting of daily demand in order to schedule pumping effort and minimize costs. This paper examines a methodology for consumer demand modeling and prediction in a real-time environment of an irrigation water distribution system. The approach is based on Adaptive Neuro-Fuzzy Inferences System (AN...
متن کامل