Abstract

The stock composite cost is utilized as a marker to tell the presentation of the recorded open organizations. The past stock costs in the financial exchange can be utilized for anticipating the future cost of the stock. Because of the snafu circumstances of the stock value, the best-performed forecast model remains a test. This investigation study predicts the stock composite cost by utilizing Nonlinear Autoregression with Exogenous Input (NARX). This technique is contrasted and the Neural Network model. In light of the examination, the NARX model outcome has moderately lower Mean Squared Error (MSE) esteem than the Neural Network model outcome. The little MSE of NARX model is 4.2, which is acquired by five deferrals and six neurons. Notwithstanding, the most reduced MSE of the NN model is 4.62 by utilizing ten neurons.

Original languageEnglish
Title of host publicationProceedings of 2019 International Conference on Information and Communication Technology and Systems, ICTS 2019
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages43-48
Number of pages6
ISBN (Electronic)9781728121338
DOIs
Publication statusPublished - Jul 2019
Event12th International Conference on Information and Communication Technology and Systems, ICTS 2019 - Surabaya, Indonesia
Duration: 18 Jul 2019 → …

Publication series

NameProceedings of 2019 International Conference on Information and Communication Technology and Systems, ICTS 2019

Conference

Conference12th International Conference on Information and Communication Technology and Systems, ICTS 2019
Country/TerritoryIndonesia
CitySurabaya
Period18/07/19 → …

Keywords

  • Bayesian regularization
  • Forecasting
  • NARX
  • Stock composite price

Fingerprint

Dive into the research topics of 'Stock composite prediction using nonlinear autoregression with exogenous input (NARX)'. Together they form a unique fingerprint.

Cite this