In this paper, we propose a decision making method based on a nearest neighbor classifier for a market selection game. In the proposed method, market prices at the previous iteration of the game are handled as inputs to the decision making system. The output class (i.e., target) is the market from which the player can obtain the maximum profit at the current iteration. In computer simulations the performance of the proposed method is examined by competing with other decision making strategies.
展开▼
