Varying portfolio construction of stocks using genetic network programming with control nodes

Abstract

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.

EPSO-GHSOM Stock Selecting and Trading Strategy on Big Data

“…Recent research employs semi-structured and unstructured data from the Internet and social media. Table 1 identifies research concerning prediction and trading strategies [2,[6][7][8][9][10][11][14][15][16][17][18][19][20][21][22][23][24]. Table 1.…”

“…Previous research combines artificial intelligence and technical analysis in models to forecast market trends, trading rules, and buy-sell signals. Their methods included genetic programming [6], k-nearest neighbor algorithms [2], neural networks [7][8][9][10][11][12][13], genetic algorithms [14], and particle swarm optimization (PSO) [15] to construct trading models based on technical indicators.…”