Predviđanje vrijednosti dionice iz povijesnih vrijednosti i nedavnih vijesti

master's thesis

• Title (english): Predicting Stock Value From History Values and Recent News
• Author: Fran Jelenić
• Mentor: Marin Šilić (mentor)
• Committee member: Marin Šilić (predsjednik povjerenstva)
• Committee member: Siniša Srbljić (član povjerenstva)
• Committee member: Goran Delač (član povjerenstva)
• Granter: University of Zagreb; Faculty of Electrical Engineering and Computing; Zagreb
• Defense date and country: 2022-07-01, Croatia
• Scientific / art field, discipline and subdiscipline: TECHNICAL SCIENCES; Computing

Abstract

Rad se bavi sposobnošću dubokih modela da stvaraju reprezentacije različitih vrsta podataka i tako rješavaju složene probleme sastavljene od različitih tipova zadataka. Ta sposobnost se prezentira na problemu predviđanja cijena dionica na temelju prijašnjih cijena i nedavnih novinskih članaka. U tu svrhu je predložen model koji ujedinjuje metode analize vremenskih serija i obrade prirodnog jezika. Provedene su optimizacija i evaluacija modela, a rezultati su komentirani i na temelju njih su donošeni zaključci.

Abstract (english)

The thesis deals with the ability of deep models to create representations of different types of data and thus solve complex problems composed of different types of tasks. This ability is presented on the problem of predicting stock prices based on previous prices and recent newspaper articles. For that purpose, a model has been proposed combining methods of time series analysis and natural language processing. Model optimization and evaluation were performed, the results were commented on, and conclusions were drawn.

• Keywords: vremenska serija; obrada prirodnog jezika; duboko učenje; dionice; LSTM; BERT; pozornost
• Keywords (english): time series; natural language processing; deep learning; stock; LSTM; BERT; attention
• Language: croatian
• URN:NBN: urn:nbn:hr:168:614532
• Study programme: Title: Computing; Study programme type: university; Study level: graduate; Academic / professional title: magistar/magistra inženjer/inženjerka računarstva (magistar/magistra inženjer/inženjerka računarstva)
• Type of resource: Text
• File origin: Born digital
• Access conditions: Closed access
• Created on: 2023-01-14 08:59:02