A new evolutionary method named "Genetic Network Programming with Control Nodes, GNPcn" has been proposed and applied to determine the timing of buying and selling stocks. GNPcn represents its solution as a directed graph structure which has some useful features inherently. For example, GNPcn has the implicit memory function which memorizes the past action sequences of agents and GNPcn can re-use nodes repeatedly in the network flow, so highly compact graph structures can be made. GNPcn can improve the strategy of buying and selling stocks of multi issues. Its effectiveness is confirmed by some simulations.
Genetic Network Programming (GNP) has been proposed as a graph-based evolutionary algorithm. GNP works well especially in dynamic environments due to its graph structures. In addition, a stock trading model using GNP with Importance Index (GNP-IMX) has been proposed. IMX is one of the criterions for decision making. However, the values of IMXs must be determined by our experience/knowledge. Therefore in this paper, IMXs are adjusted appropriately during the stock trading in order to determine buying or selling stocks. Moreover, newly defined flag nodes are introduced to GNP, which can appropriately judge the current situation, and also contributes to the use of many kinds of nodes in GNP programs. In the stock trading simulations, the effectiveness of the proposed method is confirmed.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.