{"id":1873,"date":"2021-01-16T20:26:39","date_gmt":"2021-01-16T18:26:39","guid":{"rendered":"http:\/\/journals.khnu.km.ua\/vestnik\/?p=1873"},"modified":"2021-04-30T11:16:22","modified_gmt":"2021-04-30T08:16:22","slug":"%d0%bf%d1%80%d0%be%d0%b3%d0%bd%d0%be%d0%b7%d1%83%d0%b2%d0%b0%d0%bd%d0%bd%d1%8f-%d1%87%d0%b0%d1%81%d0%be%d0%b2%d0%b8%d1%85-%d1%80%d1%8f%d0%b4%d1%96%d0%b2-%d1%80%d0%be%d0%b7%d1%88%d0%b8%d1%80%d0%b5","status":"publish","type":"post","link":"https:\/\/journals.khnu.km.ua\/vestnik\/?p=1873","title":{"rendered":"\u041f\u0440\u043e\u0433\u043d\u043e\u0437\u0443\u0432\u0430\u043d\u043d\u044f \u0447\u0430\u0441\u043e\u0432\u0438\u0445 \u0440\u044f\u0434\u0456\u0432 \u0440\u043e\u0437\u0448\u0438\u0440\u0435\u043d\u043e\u044e \u0437\u0433\u043e\u0440\u0442\u043a\u043e\u0432\u043e\u044e \u043d\u0435\u0439\u0440\u043e\u043d\u043d\u043e\u044e \u043c\u0435\u0440\u0435\u0436\u0435\u044e"},"content":{"rendered":"

\u041f\u0420\u041e\u0413\u041d\u041e\u0417\u0423\u0412\u0410\u041d\u041d\u042f \u0427\u0410\u0421\u041e\u0412\u0418\u0425 \u0420\u042f\u0414\u0406\u0412 \u0420\u041e\u0417\u0428\u0418\u0420\u0415\u041d\u041e\u042e \u0417\u0413\u041e\u0420\u0422\u041a\u041e\u0412\u041e\u042e \u041d\u0415\u0419\u0420\u041e\u041d\u041d\u041e\u042e \u041c\u0415\u0420\u0415\u0416\u0415\u042e<\/p>\n

TIME SERIES PREDICTION WITH DILATED CONVOLUTIONAL NEURAL NETWORK<\/p>\n

<\/a> \u0421\u0442\u043e\u0440\u0456\u043d\u043a\u0438: 155-160. \u041d\u043e\u043c\u0435\u0440: \u21166, 2019 (279)<\/strong>
\n\u0410\u0432\u0442\u043e\u0440\u0438: <\/strong>
\n\u0410.\u0421. \u041a\u0410\u0428\u0422\u0410\u041b\u042c\u042f\u041d, \u041e.\u0412. \u041a\u0410\u0428\u0422\u0410\u041b\u042c\u042f\u041d
\n\u0425\u043c\u0435\u043b\u044c\u043d\u0438\u0446\u044c\u043a\u0438\u0439 \u043d\u0430\u0446\u0456\u043e\u043d\u0430\u043b\u044c\u043d\u0438\u0439 \u0443\u043d\u0456\u0432\u0435\u0440\u0441\u0438\u0442\u0435\u0442
\nA. KASHTALIAN, O. KASHTALIAN
\nKhmelnytskyi National University
\nDOI:<\/strong> https:\/\/www.doi.org\/10.31891\/2307-5732-2019-279-6-155-160<\/a>
\n\u0420\u0435\u0446\u0435\u043d\u0437\u0456\u044f\/Peer review :<\/strong> 18.12.2019 \u0440.
\n\u041d\u0430\u0434\u0440\u0443\u043a\u043e\u0432\u0430\u043d\u0430\/Printed :<\/strong> 04.01.2020 \u0440.<\/p>\n

\u0410\u043d\u043e\u0442\u0430\u0446\u0456\u044f \u043c\u043e\u0432\u043e\u044e \u043e\u0440\u0438\u0433\u0456\u043d\u0430\u043b\u0443<\/strong><\/p>\n

\u0412 \u0441\u0442\u0430\u0442\u0442\u0456 \u0437\u0430\u043f\u0440\u043e\u043f\u043e\u043d\u043e\u0432\u0430\u043d\u043e \u043c\u0435\u0442\u043e\u0434 \u043f\u0440\u043e\u0433\u043d\u043e\u0437\u0443\u0432\u0430\u043d\u043d\u044f \u0447\u0430\u0441\u043e\u0432\u0438\u0445 \u0440\u044f\u0434\u0456\u0432 \u0430\u0434\u0430\u043f\u0442\u043e\u0432\u0430\u043d\u043e\u044e \u0440\u043e\u0437\u0448\u0438\u0440\u0435\u043d\u043e\u044e \u0437\u0433\u043e\u0440\u0442\u043a\u043e\u0432\u043e\u044e \u043d\u0435\u0439\u0440\u043e\u043d\u043d\u043e\u044e \u043c\u0435\u0440\u0435\u0436\u0435\u044e \u0437\u0430 \u0430\u0440\u0445\u0456\u0442\u0435\u043a\u0442\u0443\u0440\u043e\u044e, \u043f\u043e\u0434\u0456\u0431\u043d\u043e\u044e \u0434\u043e WaveNet. \u0412\u0438\u043a\u043e\u0440\u0438\u0441\u0442\u0430\u043d\u043d\u044f \u0440\u043e\u0437\u0448\u0438\u0440\u0435\u043d\u0438\u0445 \u043a\u0430\u0443\u0437\u0430\u043b\u044c\u043d\u0438\u0445 \u0437\u0433\u043e\u0440\u0442\u043a\u043e\u0432\u0438\u0445 \u0448\u0430\u0440\u0456\u0432 \u0434\u043e\u0437\u0432\u043e\u043b\u044f\u0454 \u0437\u0431\u0456\u043b\u044c\u0448\u0438\u0442\u0438 \u0440\u0435\u0446\u0435\u043f\u0442\u0438\u0432\u043d\u0435 \u043f\u043e\u043b\u0435 \u0442\u0430 \u0432\u0440\u0430\u0445\u0443\u0432\u0430\u0442\u0438 \u0434\u043e\u0432\u0433\u043e\u0441\u0442\u0440\u043e\u043a\u043e\u0432\u0456 \u0437\u0430\u043b\u0435\u0436\u043d\u043e\u0441\u0442\u0456 \u0432 \u0447\u0430\u0441\u043e\u0432\u0438\u0445 \u0440\u044f\u0434\u0430\u0445. \u041d\u0435\u0439\u0440\u043e\u043c\u0435\u0440\u0435\u0436\u0435\u0432\u0430 \u043c\u043e\u0434\u0435\u043b\u044c \u0454 \u043f\u043e\u0432\u043d\u0456\u0441\u0442\u044e \u0439\u043c\u043e\u0432\u0456\u0440\u043d\u0456\u0441\u043d\u043e\u044e \u0442\u0430 \u0430\u0432\u0442\u043e\u0440\u0435\u0433\u0440\u0435\u0441\u0438\u0432\u043d\u043e\u044e, \u0433\u0435\u043d\u0435\u0440\u0443\u0454 \u043d\u0430\u0441\u0442\u0443\u043f\u043d\u0435 \u0437\u043d\u0430\u0447\u0435\u043d\u043d\u044f \u0447\u0430\u0441\u043e\u0432\u043e\u0433\u043e \u0440\u044f\u0434\u0443 \u043d\u0430 \u043e\u0441\u043d\u043e\u0432\u0456 \u043f\u043e\u043f\u0435\u0440\u0435\u0434\u043d\u0456\u0445, \u0430 \u0442\u0430\u043a\u043e\u0436 \u043d\u0430 \u043e\u0441\u043d\u043e\u0432\u0456 \u0434\u043e\u0434\u0430\u0442\u043a\u043e\u0432\u043e\u0457 \u0456\u043d\u0444\u043e\u0440\u043c\u0430\u0446\u0456\u0457. \u0412 \u043d\u0435\u0439\u0440\u043e\u043c\u0435\u0440\u0435\u0436\u0435\u0432\u0456\u0439 \u0430\u0440\u0445\u0456\u0442\u0435\u043a\u0442\u0443\u0440\u0456 \u0432\u0438\u043a\u043e\u0440\u0438\u0441\u0442\u043e\u0432\u0443\u0454\u0442\u044c\u0441\u044f \u043c\u043e\u0434\u0435\u043b\u044e\u0432\u0430\u043d\u043d\u044f \u0441\u043f\u0456\u043b\u044c\u043d\u043e\u0433\u043e \u0440\u043e\u0437\u043f\u043e\u0434\u0456\u043b\u0443 \u0442\u043e\u0447\u043e\u043a \u044f\u043a \u0434\u043e\u0431\u0443\u0442\u043a\u0443 \u0443\u043c\u043e\u0432\u043d\u0438\u0445 \u0440\u043e\u0437\u043f\u043e\u0434\u0456\u043b\u0456\u0432. \u0422\u0430\u043a\u043e\u0433\u043e \u0442\u0438\u043f\u0443 \u0430\u0440\u0445\u0456\u0442\u0435\u043a\u0442\u0443\u0440\u0438 \u0437\u0434\u0430\u0442\u043d\u0456 \u043c\u043e\u0434\u0435\u043b\u044e\u0432\u0430\u0442\u0438 \u0440\u043e\u0437\u043f\u043e\u0434\u0456\u043b\u0438 \u0432\u0435\u043b\u0438\u043a\u043e\u0457 \u043a\u0456\u043b\u044c\u043a\u043e\u0441\u0442\u0456 \u0432\u0438\u043f\u0430\u0434\u043a\u043e\u0432\u0438\u0445 \u0432\u0435\u043b\u0438\u0447\u0438\u043d, \u0432 \u0442\u043e\u043c\u0443 \u0447\u0438\u0441\u043b\u0456 \u0447\u0430\u0441\u043e\u0432\u0456 \u0440\u044f\u0434\u0438. \u041e\u0441\u043d\u043e\u0432\u043d\u043e\u044e \u0441\u043a\u043b\u0430\u0434\u043e\u0432\u043e\u044e \u0437\u0433\u043e\u0440\u0442\u043a\u043e\u0432\u043e\u0457 \u043c\u0435\u0440\u0435\u0436\u0456 \u0434\u043b\u044f \u043f\u0440\u043e\u0433\u043d\u043e\u0437\u0443\u0432\u0430\u043d\u043d\u044f \u0447\u0430\u0441\u043e\u0432\u0438\u0445 \u0440\u044f\u0434\u0456\u0432 \u0454 \u043a\u0430\u0443\u0437\u0430\u043b\u044c\u043d\u0430 \u0437\u0433\u043e\u0440\u0442\u043a\u0430. \u041f\u043e\u0440\u044f\u0434\u043e\u043a \u043e\u0431\u0447\u0438\u0441\u043b\u0435\u043d\u043d\u044f \u0437\u0433\u043e\u0440\u0442\u043a\u0438 \u043f\u0435\u0440\u0435\u0434\u0431\u0430\u0447\u0430\u0454 \u0437\u0430\u043b\u0435\u0436\u043d\u0456\u0441\u0442\u044c \u043f\u043e\u0442\u043e\u0447\u043d\u043e\u0433\u043e \u0437\u043d\u0430\u0447\u0435\u043d\u043d\u044f \u0447\u0430\u0441\u043e\u0432\u043e\u0433\u043e \u0440\u044f\u0434\u0443 \u0442\u0456\u043b\u044c\u043a\u0438 \u0432\u0456\u0434 \u043f\u043e\u043f\u0435\u0440\u0435\u0434\u043d\u0456\u0445 \u0437\u043d\u0430\u0447\u0435\u043d\u044c, \u0449\u043e \u0434\u043b\u044f 1-D \u0437\u0433\u043e\u0440\u0442\u043a\u0438 \u0437\u0430\u0431\u0435\u0437\u043f\u0435\u0447\u0443\u0454\u0442\u044c\u0441\u044f \u0437\u0441\u0443\u0432\u043e\u043c \u0432\u0438\u0445\u043e\u0434\u0443 \u0437\u0432\u0438\u0447\u0430\u0439\u043d\u043e\u0457 \u0437\u0433\u043e\u0440\u0442\u043a\u0438 \u043d\u0430 \u0432\u0456\u0434\u043f\u043e\u0432\u0456\u0434\u043d\u0443 \u043a\u0456\u043b\u044c\u043a\u0456\u0441\u0442\u044c \u0442\u0430\u043a\u0442\u0456\u0432 \u0432\u043f\u0435\u0440\u0435\u0434. \u0422\u0430\u043a\u0438\u043c \u0447\u0438\u043d\u043e\u043c \u0432\u0438\u0445\u043e\u0434\u0438 \u0434\u043b\u044f \u0432\u0441\u0456\u0445 \u0442\u0430\u043a\u0442\u0456\u0432 \u0432 \u043f\u0440\u043e\u0446\u0435\u0441\u0456 \u043d\u0430\u0432\u0447\u0430\u043d\u043d\u044f \u0440\u043e\u0437\u0440\u0430\u0445\u043e\u0432\u0443\u044e\u0442\u044c\u0441\u044f \u043f\u0430\u0440\u0430\u043b\u0435\u043b\u044c\u043d\u043e. \u041f\u0440\u043e\u0446\u0435\u0441 \u0433\u0435\u043d\u0435\u0440\u0430\u0446\u0456\u0457 \u0437\u043d\u0430\u0447\u0435\u043d\u044c \u0447\u0430\u0441\u043e\u0432\u043e\u0433\u043e \u0440\u044f\u0434\u0443 \u0454 \u043f\u043e\u0441\u043b\u0456\u0434\u043e\u0432\u043d\u0438\u043c, \u0434\u043b\u044f \u043a\u043e\u0436\u043d\u043e\u0433\u043e \u0442\u0430\u043a\u0442\u0443 \u043f\u0440\u043e\u0433\u043d\u043e\u0437\u0443\u0454\u0442\u044c\u0441\u044f \u043d\u0430\u0441\u0442\u0443\u043f\u043d\u0435 \u0437\u043d\u0430\u0447\u0435\u043d\u043d\u044f, \u044f\u043a\u0435 \u0432\u0438\u043a\u043e\u0440\u0438\u0441\u0442\u043e\u0432\u0443\u0454\u0442\u044c\u0441\u044f \u0434\u043b\u044f \u043f\u043e\u0434\u0430\u043b\u044c\u0448\u043e\u0433\u043e \u043f\u0440\u043e\u0433\u043d\u043e\u0437\u0443\u0432\u0430\u043d\u043d\u044f. \u0414\u043b\u044f \u0437\u0431\u0456\u043b\u044c\u0448\u0435\u043d\u043d\u044f \u0432\u0435\u043b\u0438\u0447\u0438\u043d\u0438 \u0440\u0435\u0446\u0435\u043f\u0442\u0438\u0432\u043d\u043e\u0433\u043e \u043f\u043e\u043b\u044f \u0432\u0438\u043a\u043e\u0440\u0438\u0441\u0442\u043e\u0432\u0443\u0454\u0442\u044c\u0441\u044f \u0440\u043e\u0437\u0448\u0438\u0440\u0435\u043d\u0430 \u0437\u0433\u043e\u0440\u0442\u043a\u0430. \u0420\u043e\u0437\u0448\u0438\u0440\u0435\u043d\u0430 \u0437\u0433\u043e\u0440\u0442\u043a\u0430 \u043f\u0440\u0435\u0434\u0441\u0442\u0430\u0432\u043b\u044f\u0454 \u0441\u043e\u0431\u043e\u044e \u0437\u0433\u043e\u0440\u0442\u043a\u0443, \u0432 \u044f\u043a\u0456\u0439 \u0444\u0456\u043b\u044c\u0442\u0440 \u0437\u0430\u0441\u0442\u043e\u0441\u043e\u0432\u0443\u0454\u0442\u044c\u0441\u044f \u0434\u043e \u043f\u043b\u043e\u0449\u0456, \u0431\u0456\u043b\u044c\u0448\u043e\u0457 \u0437\u0430 \u0432\u0435\u043b\u0438\u0447\u0438\u043d\u0443 \u0444\u0456\u043b\u044c\u0442\u0440\u0430 \u0437\u0430 \u0440\u0430\u0445\u0443\u043d\u043e\u043a \u043f\u0440\u043e\u043f\u0443\u0441\u043a\u0443 \u0447\u0430\u0441\u0442\u0438\u043d\u0438 \u0432\u0445\u0456\u0434\u043d\u0438\u0445 \u0437\u043d\u0430\u0447\u0435\u043d\u044c \u0437 \u0432\u0438\u0437\u043d\u0430\u0447\u0435\u043d\u0438\u043c \u043a\u0440\u043e\u043a\u043e\u043c. \u0412 \u0437\u0430\u043f\u0440\u043e\u043f\u043e\u043d\u043e\u0432\u0430\u043d\u0456\u0439 \u043c\u0435\u0440\u0435\u0436\u0456 \u0440\u0435\u0446\u0435\u043f\u0442\u0438\u0432\u043d\u0435 \u043f\u043e\u043b\u0435 \u0435\u043a\u0441\u043f\u043e\u043d\u0435\u043d\u0446\u0456\u0439\u043d\u043e \u0437\u0440\u043e\u0441\u0442\u0430\u0454 \u0437\u0456 \u0437\u0431\u0456\u043b\u044c\u0448\u0435\u043d\u043d\u044f\u043c \u043a\u0456\u043b\u044c\u043a\u043e\u0441\u0442\u0456 \u0448\u0430\u0440\u0456\u0432. \u041e\u0446\u0456\u043d\u043a\u0430 \u0442\u043e\u0447\u043d\u043e\u0441\u0442\u0456 \u0440\u043e\u0437\u0433\u043b\u044f\u043d\u0443\u0442\u043e\u0457 \u043d\u0435\u0439\u0440\u043e\u043c\u0435\u0440\u0435\u0436\u0435\u0432\u043e\u0457 \u043c\u043e\u0434\u0435\u043b\u0456 \u043f\u0440\u043e\u0432\u043e\u0434\u0438\u043b\u0430\u0441\u044f \u0432 \u0437\u0430\u0441\u0442\u043e\u0441\u0443\u0432\u0430\u043d\u043d\u0456 \u0434\u043e \u043d\u0435\u043b\u0456\u043d\u0456\u0439\u043d\u0438\u0445 \u0447\u0430\u0441\u043e\u0432\u0438\u0445 \u0440\u044f\u0434\u0456\u0432, \u0430 \u0441\u0430\u043c\u0435 \u0434\u043e \u0446\u0456\u043d \u043d\u0430 \u0430\u043a\u0446\u0456\u0457. \u0411\u0443\u043b\u0438 \u043f\u0440\u043e\u0430\u043d\u0430\u043b\u0456\u0437\u043e\u0432\u0430\u043d\u0456 \u0434\u0430\u043d\u0456 \u0442\u0440\u044c\u043e\u0445 \u043a\u043e\u043c\u043f\u0430\u043d\u0456\u0439, \u043e\u0442\u0440\u0438\u043c\u0430\u043d\u0456 \u0437 \u0432\u0456\u0434\u043a\u0440\u0438\u0442\u0438\u0445 \u0434\u0436\u0435\u0440\u0435\u043b, \u0437 \u044f\u043a\u0438\u0445 \u0431\u0443\u043b\u0438 \u0441\u0444\u043e\u0440\u043c\u043e\u0432\u0430\u043d\u0456 \u043d\u0430\u0432\u0447\u0430\u043b\u044c\u043d\u0430 \u0442\u0430 \u0442\u0435\u0441\u0442\u043e\u0432\u0430 \u0432\u0438\u0431\u0456\u0440\u043a\u0438. \u0412 \u044f\u043a\u043e\u0441\u0442\u0456 \u043c\u0435\u0442\u0440\u0438\u043a \u0431\u0443\u043b\u043e \u0432\u0438\u043a\u043e\u0440\u0438\u0441\u0442\u0430\u043d\u043e \u0441\u0435\u0440\u0435\u0434\u043d\u044c\u043e\u043a\u0432\u0430\u0434\u0440\u0430\u0442\u0438\u0447\u043d\u0443 \u043f\u043e\u0445\u0438\u0431\u043a\u0443 \u0442\u0430 \u0441\u0435\u0440\u0435\u0434\u043d\u044e \u0430\u0431\u0441\u043e\u043b\u044e\u0442\u043d\u0443 \u043f\u043e\u0445\u0438\u0431\u043a\u0443 \u0443 \u0432\u0456\u0434\u0441\u043e\u0442\u043a\u0430\u0445. \u0420\u043e\u0437\u0448\u0438\u0440\u0435\u043d\u0430 \u043a\u0430\u0443\u0437\u0430\u043b\u044c\u043d\u0430 \u0437\u0433\u043e\u0440\u0442\u043a\u043e\u0432\u0430 \u043c\u043e\u0434\u0435\u043b\u044c \u043f\u043e\u043a\u0430\u0437\u0443\u0454 \u043a\u0440\u0430\u0449\u0456 \u0442\u043e\u0447\u043d\u0456\u0441\u043d\u0456 \u0440\u0435\u0437\u0443\u043b\u044c\u0442\u0430\u0442\u0438 \u0456 \u0432 \u043f\u043e\u0440\u0456\u0432\u043d\u044f\u043d\u043d\u0456 \u0437 \u0430\u0432\u0442\u043e\u0440\u0435\u0433\u0440\u0435\u0441\u0438\u0432\u043d\u043e\u044e \u043c\u043e\u0434\u0435\u043b\u043b\u044e, \u0456 \u0437 \u0440\u0435\u043a\u0443\u0440\u0435\u043d\u0442\u043d\u043e\u044e LSTM \u043c\u043e\u0434\u0435\u043b\u043b\u044e. \u041d\u0435\u0439\u0440\u043e\u043c\u0435\u0440\u0435\u0436\u0435\u0432\u0430 \u043c\u043e\u0434\u0435\u043b\u044c \u0437\u0456 \u0437\u0433\u043e\u0440\u0442\u043a\u043e\u0432\u0438\u043c\u0438 \u0448\u0430\u0440\u0430\u043c\u0438 \u043d\u0435 \u043c\u0430\u0454 \u0440\u0435\u043a\u0443\u0440\u0435\u043d\u0442\u043d\u0438\u0445 \u0437\u0432\u2019\u044f\u0437\u043a\u0456\u0432, \u0442\u043e\u043c\u0443 \u0437\u0430\u0431\u0435\u0437\u043f\u0435\u0447\u0443\u0454 \u0432\u0438\u0449\u0443 \u0448\u0432\u0438\u0434\u043a\u0456\u0441\u0442\u044c \u043d\u0430\u0432\u0447\u0430\u043d\u043d\u044f \u0443 \u043f\u043e\u0440\u0456\u0432\u043d\u044f\u043d\u043d\u0456 \u0437 \u0440\u0435\u043a\u0443\u0440\u0435\u043d\u0442\u043d\u0438\u043c\u0438 \u043c\u043e\u0434\u0435\u043b\u044f\u043c\u0438.
\n\u041a\u043b\u044e\u0447\u043e\u0432\u0456 \u0441\u043b\u043e\u0432\u0430:<\/strong> \u0447\u0430\u0441\u043e\u0432\u0438\u0439 \u0440\u044f\u0434, \u0440\u043e\u0437\u0448\u0438\u0440\u0435\u043d\u0430 \u043a\u0430\u0443\u0437\u0430\u043b\u044c\u043d\u0430 \u0437\u0433\u043e\u0440\u0442\u043a\u0430, \u0440\u043e\u0437\u043f\u043e\u0434\u0456\u043b \u0439\u043c\u043e\u0432\u0456\u0440\u043d\u043e\u0441\u0442\u0435\u0439.<\/p>\n

\u0420\u043e\u0437\u0448\u0438\u0440\u0435\u043d\u0430 \u0430\u043d\u043e\u0442\u0430\u0446\u0456\u044f \u0430\u043d\u0433\u043b\u0456\u0439\u0441\u044c\u043a\u043e\u044e \u043c\u043e\u0432\u043e\u044e<\/strong><\/p>\n

The method of time series forecasting with the adapted dilated causal convolutional neural network model is proposed in the article. The model architecture is similar to WaveNet. The use of dilated causal convolutional layers allows to increase receptive field and to consider long-term dependencies in time series. The neural network model is full probabilistic and autoregressive, it generates the next time series value on the basis of previous ones and also on the basis of additional information. The modelling join distribution of points as a multiplication of conditional distributions is used. The such types of architectures is able to model distributions of a big number of random values, including time series. The main part of convolutional neural network for time series forecasting is causal convolution. The order of computation supposes the dependence of current value only from previous values. It provides by shifting output of usual convolution on certain number of time steps forward for 1-D convolution. Thus outputs for all time steps are computed in parallel in training process. The generation process is sequential, the next value is predicted for every time step, and this value is used for further prediction. A dilated convolution is used for increasing receptive field. Dilated convolution is convolution with a filter applied to area bigger than filter size for the account of skipping a part of input values with certain step. A receptive field increases exponentially with increasing layers number in considered network. The estimation of considered neural network model was carried out due to nonlinear time series, in particular to stock prices. The data of three companies was analysed. The data were obtained from open sources and create training and testing samples. Root mean squared error and mean absolute percentage error were used as metrics. The dilated causal convolutional model shows a better accuracy results in comparison both with autoregressive model and recurrent LSTM model. The neural network with convolutional layers does not have recurrent connections, so it provides higher training speed relatively to recurrent models.
\nKey words:<\/strong> time series, dilated causal convolution, probability distribution.<\/p>\n

References<\/span><\/strong><\/p>\n

    \n
  1. Dev Shah, Haruna Isah, Farhana Zulkernine. Stock Market Analysis: A Review and Taxonomy of Prediction Techniques. International Journal of Financial Studies, 2019, 7, 26, P. 1\u201321.<\/li>\n
  2. Boussaada Z., Curea O., Remaci A., Camblong H., Bellaaj N.M. A nonlinear autoregressive exogenous (NARX) Neural Network Model for the Prediction of the Daily Direct Solar Radiation. Energies, 2018, Issue 11, P.\u00a0620\u2013641.<\/li>\n
  3. Kashtalian A. The features of feedforward neural network use for time series forecasting. Herald of Khmelnytskyi National University: Technical Science. Khmelnitsky: KhNU, 2016, Issue 6(243), P. 210\u2013215.<\/li>\n
  4. Wang J., Wang J., Fang W., Niu H. Financial Time Series Prediction Using Elman Recurrent Random Neural Networks. Computational Intelligence and Neuroscience, 2016, Issue 12, P. 1\u201314.<\/li>\n
  5. Petnehazi G. Recurrent Neural Networks for Time Series Forecasting. arXiv:1901.00069v1 [cs.LG] 1 Jan 2019. URL: https:\/\/arxiv.org\/pdf\/1901.00069.pdf<\/a>. Accessed 10 Sep 2019.<\/li>\n
  6. Borovykh A., Bohte S., Oosterlee C.W. Conditional time series forecasting with convolutional neural networks. arXiv:1703.04691v5 [stat.ML] 17 Sep 2018. URL: https:\/\/arxiv.org\/pdf\/1703.04691.pdf<\/a>. Accessed 10 Sep 2019.<\/li>\n
  7. Van den Oord A., Dieleman S., Zen H., Simonyan K., Vinyals O., Graves A., Kalchbrenner N., Senior A., Kavukcuoglu K. WaveNet: A Generative Model for Raw Audio. arXiv:1609.03499v2 [cs.SD] 19 Sep 2016. URL: https:\/\/arxiv.org\/pdf\/1609.03499.pdf<\/a>. Accessed 10 Sep 2019.<\/li>\n
  8. Aaron van den Oord, Kalchbrenner N., Kavukcuoglu K. Pixel recurrent neural networks. arXiv:1601.06759v3 [cs.CV] 19 Aug 2016. URL: https:\/\/arxiv.org\/pdf\/1601.06759.pdf<\/a>. Accessed 19 Sep 2019.<\/li>\n
  9. Van den Oord A., Kalchbrener N., Vinyals O., Espeholt L., Graves A., Kavukcuoglu K. Conditional Image Generation with PixelCNN Decoders. arXiv:1606.05328v2 [cs.CV] 18 Jun 2016. URL: https:\/\/arxiv.org\/pdf\/1606.05328.pdf<\/a>. Accessed 19 Sep 2019.<\/li>\n
  10. Arik S. O., Chrzanowski M., Coates A., Diamos G., Gibiansky A., Kang Y., Li X., Miller J., Ng A., Raiman J., Sengupta S., Shoeybi M. Deep Voice: Real-time Neural Text-to-Speech. arXiv:1702.07825v2 [cs.CL] 7 Mar 2017. URL: https:\/\/arxiv.org\/pdf\/1702.07825.pdf<\/a>. Accessed 19 Sep 2019.<\/li>\n
  11. Fisher T., Krauss C. Deep Learning with Long Short-Term Memory networks for financial market predictions. FAU Discussion papers in Economics, 2017, Issue 11, P. 961\u2013970.<\/li>\n<\/ol>\n","protected":false},"excerpt":{"rendered":"

    \u041f\u0420\u041e\u0413\u041d\u041e\u0417\u0423\u0412\u0410\u041d\u041d\u042f \u0427\u0410\u0421\u041e\u0412\u0418\u0425 \u0420\u042f\u0414\u0406\u0412 \u0420\u041e\u0417\u0428\u0418\u0420\u0415\u041d\u041e\u042e \u0417\u0413\u041e\u0420\u0422\u041a\u041e\u0412\u041e\u042e \u041d\u0415\u0419\u0420\u041e\u041d\u041d\u041e\u042e \u041c\u0415\u0420\u0415\u0416\u0415\u042e TIME SERIES PREDICTION WITH DILATED CONVOLUTIONAL NEURAL NETWORK \u0421\u0442\u043e\u0440\u0456\u043d\u043a\u0438: 155-160. \u041d\u043e\u043c\u0435\u0440: \u21166, 2019 (279) \u0410\u0432\u0442\u043e\u0440\u0438: \u0410.\u0421. \u041a\u0410\u0428\u0422\u0410\u041b\u042c\u042f\u041d, \u041e.\u0412. \u041a\u0410\u0428\u0422\u0410\u041b\u042c\u042f\u041d \u0425\u043c\u0435\u043b\u044c\u043d\u0438\u0446\u044c\u043a\u0438\u0439 \u043d\u0430\u0446\u0456\u043e\u043d\u0430\u043b\u044c\u043d\u0438\u0439 \u0443\u043d\u0456\u0432\u0435\u0440\u0441\u0438\u0442\u0435\u0442 A. KASHTALIAN, O. KASHTALIAN Khmelnytskyi National University DOI: https:\/\/www.doi.org\/10.31891\/2307-5732-2019-279-6-155-160 \u0420\u0435\u0446\u0435\u043d\u0437\u0456\u044f\/Peer review : 18.12.2019 \u0440. \u041d\u0430\u0434\u0440\u0443\u043a\u043e\u0432\u0430\u043d\u0430\/Printed : 04.01.2020 \u0440. \u0410\u043d\u043e\u0442\u0430\u0446\u0456\u044f \u043c\u043e\u0432\u043e\u044e \u043e\u0440\u0438\u0433\u0456\u043d\u0430\u043b\u0443 \u0412 \u0441\u0442\u0430\u0442\u0442\u0456 \u0437\u0430\u043f\u0440\u043e\u043f\u043e\u043d\u043e\u0432\u0430\u043d\u043e \u043c\u0435\u0442\u043e\u0434 \u043f\u0440\u043e\u0433\u043d\u043e\u0437\u0443\u0432\u0430\u043d\u043d\u044f […]<\/p>\n","protected":false},"author":1,"featured_media":0,"comment_status":"closed","ping_status":"closed","sticky":false,"template":"","format":"standard","meta":[],"categories":[19],"tags":[],"_links":{"self":[{"href":"https:\/\/journals.khnu.km.ua\/vestnik\/index.php?rest_route=\/wp\/v2\/posts\/1873"}],"collection":[{"href":"https:\/\/journals.khnu.km.ua\/vestnik\/index.php?rest_route=\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/journals.khnu.km.ua\/vestnik\/index.php?rest_route=\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/journals.khnu.km.ua\/vestnik\/index.php?rest_route=\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/journals.khnu.km.ua\/vestnik\/index.php?rest_route=%2Fwp%2Fv2%2Fcomments&post=1873"}],"version-history":[{"count":3,"href":"https:\/\/journals.khnu.km.ua\/vestnik\/index.php?rest_route=\/wp\/v2\/posts\/1873\/revisions"}],"predecessor-version":[{"id":6120,"href":"https:\/\/journals.khnu.km.ua\/vestnik\/index.php?rest_route=\/wp\/v2\/posts\/1873\/revisions\/6120"}],"wp:attachment":[{"href":"https:\/\/journals.khnu.km.ua\/vestnik\/index.php?rest_route=%2Fwp%2Fv2%2Fmedia&parent=1873"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/journals.khnu.km.ua\/vestnik\/index.php?rest_route=%2Fwp%2Fv2%2Fcategories&post=1873"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/journals.khnu.km.ua\/vestnik\/index.php?rest_route=%2Fwp%2Fv2%2Ftags&post=1873"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}