The Proposed Mathematical Models for Decision-Making and Forecasting on Euro-Yen in Foreign Exchange Market

In this paper two approaches for trading and forecasting on Euro-Yen exchange rates are suggested. In the first approach three decision-making models are developed to maximize profit of trades during a specific period. Traders have three options to perform a trade at each market time that are: (a) Opening a buy trade, (b) Opening a sell trade and (c) Refusal of trading. These options are considered in the models by using related decision variables. Results of these models conform to qualitative contents in literature of foreign exchange market and present trading strategy on the basis of the indicators to maximize profit. The aim of second approach is forecasting the direction of exchange rate (increase or decrease) over a specific period on the basis of values of indicators in previous time period. In this approach two heuristic models are developed to minimize mean of errors of forecasting. Then mean of errors of developed models are compared with four major classification algorithms. Results show that the proposed model has higher accuracy in forecasting.