Your browser doesn't support javascript.
Effective forecasting of stock market price by using extreme learning machine optimized by PSO-based group oriented crow search algorithm.
Das, Sudeepa; Sahu, Tirath Prasad; Janghel, Rekh Ram; Sahu, Binod Kumar.
  • Das S; Department of Information Technology, National Institute of Technology, Raipur, Chhattisgarh India.
  • Sahu TP; Department of Information Technology, National Institute of Technology, Raipur, Chhattisgarh India.
  • Janghel RR; Department of Information Technology, National Institute of Technology, Raipur, Chhattisgarh India.
  • Sahu BK; Department of Electrical Engineering, ITER, Siksha 'O' Anusandhan University, Bhubaneswar, Odisha India.
Neural Comput Appl ; 34(1): 555-591, 2022.
Article in English | MEDLINE | ID: covidwho-1626526
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.
Keywords

Full text: Available Collection: International databases Database: MEDLINE Type of study: Experimental Studies / Prognostic study Language: English Journal: Neural Comput Appl Year: 2022 Document Type: Article

Similar

MEDLINE

...
LILACS

LIS


Full text: Available Collection: International databases Database: MEDLINE Type of study: Experimental Studies / Prognostic study Language: English Journal: Neural Comput Appl Year: 2022 Document Type: Article