Aplikacija za planiranje investicija korištenjem alata GPT-3

undergraduate thesis

• Title (english): Application for Investment Planning using GPT-3 Tool
• Author: Sven Barac
• Mentor: Ivica Botički (mentor)
• Committee member: Ivica Botički (predsjednik povjerenstva)
• Committee member: Mihael Kovač (član povjerenstva)
• Committee member: Kristijan Poje (član povjerenstva)
• Granter: University of Zagreb; Faculty of Electrical Engineering and Computing; Zagreb
• Defense date and country: 2023-07-04, Croatia
• Scientific / art field, discipline and subdiscipline: TECHNICAL SCIENCES; Computing

Abstract

U okviru ovog završnog rada se izradila web aplikacija koja koristi jezični model umjetne inteligencije GPT-3 za odabir portfelja dionica sukladno osobnim preferencijama korisnika. Korisniku se nudi mogućnost pregleda sadržaja i performansi generiranih portfelja dionica za njihovo međusobno uspoređivanje i analizu pristupa. Klijentski dio web aplikacije napisan je u programskom jeziku Javascript koristeći React, Axios i Bootstrap knjižnice. Poslužitelj je napisan u Javascript izvršnom okruženju, Node.js. Za generiranje portfelja dionica korišten je OpenAI API, a za njihovu analizu performansi i sadržaja Yahoo Finance! API pisan u programskom jeziku Python koristeći knjižnicu NumPy. Generirani portfelji dionica spremaju se u PostgreSQL bazu podataka.

Abstract (english)

As part of this final thesis, a web application was created that uses the language model of artificial intelligence GPT-3 to select a stock portfolio according to the user's personal preferences. The user is offered the possibility to review the content and performance of the generated stock portfolios for comparing them with each other and analyzing different investing approaches. The client part of the web application is written in Javascript programming language using React, Axios, and Bootstrap libraries. The server is written in the Javascript runtime environment, Node.js. OpenAI API was used to generate stock portfolios and Yahoo Finance! API, written in Python programming language using the NumPy library, was used to analyze their performance and extract relevent content. The generated stock portfolios are saved in the PostgreSQL database.

• Keywords: GPT-3; React; Javascript; PostgreSQL; umjetna inteligencija; investiranje; financije; web-aplikacija
• Keywords (english): GPT-3; React; Javascript; PostgreSQL; artificial intelligence; investing; finance; web-application
• Language: croatian
• URN:NBN: urn:nbn:hr:168:094218
• 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: 2023-10-11 08:21:55