Predviđanje vrijednosti financijskih podataka temeljeno na rekurentnim neuronskim mrežama

undergraduate thesis

• Title (english): Prediction of Financial Data Values based on Recurrent Neural Networks
• Author: Matej Luburić
• Mentor: Alan Jović (mentor)
• Committee member: Alan Jović (predsjednik povjerenstva)
• Committee member: Nikolina Frid (član povjerenstva)
• Committee member: Igor Stančin (član povjerenstva)
• Granter: University of Zagreb; Faculty of Electrical Engineering and Computing; Zagreb
• Defense date and country: 2020-09-04, Croatia
• Scientific / art field, discipline and subdiscipline: TECHNICAL SCIENCES; Computing

Abstract

U ovom radu obrađena je analiza financijskih podataka pomoću neuronske mreže
koja koristi ćelije s dugom kratkoročnom memorijom (engl. long short-term memory,
LSTM). Detaljno su objašnjene tri vrste rekurentnih neuronskih mreža: osnovna rekurentna
neuronska mreža (RNN), LSTM i propusna povratna ćelija (engl. gated recurrent
unit, GRU). Objašnjena je prednost ćelija LSTM i GRU naspram jednostavne
RNN zbog rješavanja problema eksplodirajućeg i nestajućeg gradijenta. Prikazani su
dobiveni rezultati i njihova interpretacija pomoću srednje apsolutne postotne pogreške,
Pearsonovog koeficijenta i Theilovog koeficijenta U.

Abstract (english)

This paper deals with the processing of financial data using a long short-term memory
(LSTM). Three types of recurrent neural networks are explained in detail: the
simple recurrent neural network (RNN), LSTM and the gated recurrent unit (GRU).
The advantage of LSTM and GRU over simple RNN due to solving the problem of
exploding and vanishing gradient is explained. The obtained results and their interpretation
are presented using the mean absolute percentage error (MAPE), Pearson’s
coefficient and Theil’s U coefficient.

• Keywords: strojno učenje; rekurentne neuronske mreže; predviđanje; financije; LSTM; GRU
• Keywords (english): machine learning; recurrent neural network (RNN); prediction; finance; LSTM; GRU
• Language: croatian
• URN:NBN: urn:nbn:hr:168:345886
• Study programme: Title: Computing; Study programme type: university; Study level: undergraduate; Academic / professional title: sveučilišni/a prvostupnik/ prvostupnica (baccalaureus/baccalaurea) inženjer/inženjerka računarstva (sveučilišni/a prvostupnik/ prvostupnica (baccalaureus/baccalaurea) inženjer/inženjerka računarstva)
• Type of resource: Text
• File origin: Born digital
• Access conditions: Closed access
• Created on: 2023-01-14 09:18:48