dc.contributor.author | Maknickienė, Nijolė | |
dc.contributor.author | Rutkauskas, Aleksandras Vytautas | |
dc.contributor.author | Maknickas, Algirdas | |
dc.date.accessioned | 2023-09-18T18:50:30Z | |
dc.date.available | 2023-09-18T18:50:30Z | |
dc.date.issued | 2011 | |
dc.identifier.issn | 2029-1035 | |
dc.identifier.other | (BIS)VGT02-000023631 | |
dc.identifier.uri | https://etalpykla.vilniustech.lt/handle/123456789/132534 | |
dc.description.abstract | Recurrent neural networks as fundamentally different neural network from feed-forward architectures was investigated for modelling of non linear behaviour of financial markets. Recurrent neural networks could be configured with the correct choice of parameters such as the number of neurons, the number of epochs, the amount of data and their relationship with the training data for predictions of financial markets. By exploring of learning and forecasting of the recurrent neural networks is observed the same effect: better learning, which often is described by the root mean square error does not guarantee a better prediction. There are such a recurrent neural networks settings where the best results of non linear time series forecasting could be obtained. New method of orthogonal input data was proposed, which improve process of EVOLINO RNN learning and forecasting. | eng |
dc.format.extent | p. 3-8 | |
dc.format.medium | tekstas / txt | |
dc.language.iso | eng | |
dc.source.uri | http://journal.kolegija.lt/iitsbe/journal/IITSBE-2011-2(11).pdf | |
dc.title | Investigation of financial market prediction by recurrent neural network | |
dc.type | Straipsnis kitame recenzuotame leidinyje / Article in other peer-reviewed source | |
dcterms.references | 15 | |
dc.type.pubtype | S4 - Straipsnis kitame recenzuotame leidinyje / Article in other peer-reviewed publication | |
dc.contributor.institution | Vilniaus Gedimino technikos universitetas | |
dc.contributor.faculty | Verslo vadybos fakultetas / Faculty of Business Management | |
dc.contributor.faculty | Fundamentinių mokslų fakultetas / Faculty of Fundamental Sciences | |
dc.subject.researchfield | S 004 - Ekonomika / Economics | |
dc.subject.en | Financial forecasting and simulation | |
dc.subject.en | Time-series models | |
dc.subject.en | Dynamic quantile regressions | |
dc.subject.en | Dynamic treatment models | |
dc.subject.en | Forecasting models | |
dc.subject.en | Simulation methods | |
dc.subject.en | Neural networks and related topics | |
dc.subject.en | Recurrent neural networks | |
dc.subject.en | EVOLINO learning algorithm | |
dc.subject.en | Non linear time series | |
dc.subject.en | Orthogonal inputs | |
dc.subject.en | Prediction of financial markets | |
dcterms.sourcetitle | Innovative technologies for science, business and education | |
dc.description.volume | vol. 2(11) | |
dc.publisher.name | Vilnius Business College | |
dc.publisher.city | Vilnius | |
dc.identifier.elaba | 3960506 | |