Stock market prediction using Altruistic Dragonfly Algorithm

Abstract

Stock market prediction is the process of determining the value of a company’s shares and other financial assets in the future. This paper proposes a new model where Altruistic Dragonfly Algorithm (ADA) is combined with Least Squares Support Vector Machine (LS-SVM) for stock market prediction. ADA is a meta-heuristic algorithm which optimizes the parameters of LS-SVM to avoid local minima and overfitting, resulting in better prediction performance. Experiments have been performed on 12 datasets and the obtained results are compared with other popular meta-heuristic algorithms. The results show that the proposed model provides a better predictive ability and demonstrate the effectiveness of ADA in optimizing the parameters of LS-SVM.

A New Medical Analytical Framework for Automated Detection of MRI Brain Tumor Using Evolutionary Quantum Inspired Level Set Technique

“…When it comes to optimization, these two swarming techniques rely on the usage of metaheuristics for both exploitation and exploration [68]. Figure 13 illustrates the flowchart of the Dragonfly algorithm [21,69,70]. Separation (S i ), alignment (A i ), cohesion (C i ) attraction to food sources (F i ), and distraction from enemies (E i ), are the five operators of dragonfly swarms [21].…”

“…The ith dragonfly's primary survival goal is to collect food, but it is diverted from this goal by enemies, as reflected by the final two operators, F i and E i . To show the survival behaviors of dragonfly swarms, each operator is weighted appropriately [70].…”

“…Both the inertia weight and the Lévy flight equation have their origins in Newtonian mechanical concepts, which place limits on the kinds of searching that may be performed by an individual. Any given dragonfly has a high degree of difficulty altering its preexisting searching direction in response to DA because of the so-called inertia constraint; any dragonfly without an adjacent neighbor must use the Lévy flight equation and may not modify the fly rules while in Lévy flight due to the Lévy flight constraint [69][70][71].…”