Effective forecasting of stock market price by using extreme learning machine optimized by PSO-based group oriented crow search algorithm

Abstract

Stock index price forecasting is the influential indicator for investors and financial investigators by which decision making capability to achieve maximum benefit with minimum risk can be improved. So, a robust engine with capability to administer useful information is desired to achieve the success. The forecasting effectiveness of stock market is improved in this paper by integrating a modified crow search algorithm (CSA) and extreme learning machine (ELM). The effectiveness of proposed modified CSA entitled as Particle Swarm Optimization (PSO)-based Group oriented CSA (PGCSA) to outperform other existing algorithms is observed by solving 12 benchmark problems. PGCSA algorithm is used to achieve relevant weights and biases of ELM to improve the effectiveness of conventional ELM. The impact of hybrid PGCSA ELM model to predict next day closing price of seven different stock indices is observed by using performance measures, technical indicators and hypothesis test (paired t -test). The seven stock indices are considered by incorporating data during COVID-19 outbreak. This model is tested by comparing with existing techniques proposed in published works. The simulation results provide that PGCSA ELM model can be considered as a suitable tool to predict next day closing price.

High-Accuracy Photovoltaic Power Prediction under Varying Meteorological Conditions: Enhanced and Improved Beluga Whale Optimization Extreme Learning Machine

“…ELM has been widely applied in multiple prediction research fields due to its unique advantages of fast learning speed and good generalization ability. In financial market analysis, ELM can be used to predict stock prices and market trends [27]. A predictive model for financial market system risk based on ELM was constructed and the stability of the model was verified through examples.…”

“…When there is a large number of samples in the training set, in order to reduce computational costs, the number of hidden-layer neurons is usually smaller than the number of samples in the training set. At this point, the network training error can approach an arbitrary value ε, as shown in Equation (27).…”

Daily tourism forecasting through a novel method based on principal component analysis, grey wolf optimizer, and extreme learning machine

“…However, most neural network-based forecast methods utilize gradient-based learning algorithms such as BPNN, which may suffer from overfitting and long calculational time (Shrivastava & Panigrahi, 2014). ELM is a faster learning algorithm than traditional gradient-based learning algorithm for SLFN (Das et al, 2020(Das et al, , 2022Huang et al, 2006;Zhu et al, 2005). ELM has been successfully applied in various fields, such as solar power generation forecast (Sahu et al, 2021), annual rainfall forecast (Wang et al, 2021), and currency exchange rate forecast (Das et al, 2020).…”

“…Overall, the key feature of ELM is its ability to outperform traditional learning algorithms in terms of speed, especially for SLFNs, without sacrificing learning accuracy. ELM has been widely used in various fields and achieved good results (Behera & Nayak, 2020; Das et al, 2022). Before ELM training, the predefined network architecture, that is, the number of neurons in the hidden layer, must be determined manually, which affects the training effect of the model.…”

Performance Prediction and Optimization of Single-Piston Free Piston Expander-Linear Generator Based on Machine Learning and Genetic Algorithm

“…Advances in machine learning have given new ideas and methods for design and performance improvement in the field of ORC and expander systems. Among them, artificial neural networks (ANN) have been widely used due to their advantages in self-adaption, self-learning, nonlinear mapping, and fault tolerance [39][40][41]. Yang et al [42] established an ANN prediction model for the diesel engine and ORC…”