Brain-inspired genetic complementary learning for stock market prediction

Traditional technical analysis for stock market prediction is error-prone, especially for multiyear trend prediction. Hence, computational intelligence provides an attractive alternative. Among the plethora of methods, statistics and artificial neural network are the most popular. However, they are black boxes that are not interpretable. Genetic complementary learning (GCL) fuzzy neural network is therefore proposed. GCL is a brain-inspired learning algorithm that is a confluence of genetic algorithm (GA) and hippocampal complementary learning. Since GA has the potential of finding optimal solution, and complementary learning is one of the mechanisms underlying human recognition, GCL may offer superior performance. The experimental results have demonstrated that GCL is a competent stock market prediction system.