Predikcija vremenskih zapisa u alatu za praćenje vremena

master's thesis

• Title (english): Time Entry Prediction for a Time Tracking Software
• Author: Stjepan Petruša
• Mentor: Tomislav Burić (mentor)
• Committee member: Tomislav Burić (predsjednik povjerenstva)
• Committee member: Mario Krnić (član povjerenstva)
• Committee member: Lana Horvat Dmitrović (član povjerenstva)
• Granter: University of Zagreb; Faculty of Electrical Engineering and Computing; Zagreb
• Defense date and country: 2019-07-08, Croatia
• Scientific / art field, discipline and subdiscipline: TECHNICAL SCIENCES; Computing

Abstract

Cilj ovog rada je bio dizajnirati i testirati novi mikroservis za postojeći alat za praćenje vremena koji će pružati predikcije za vremensko praćenje. Motivacija je bila poboljšanjem iskustva vremenskog praćenja ujedno i poboljšati kvalitetu vremenskih zabilješki i izvještajima o profitabilnosti. Odlučili smo koristiti alat Productive jer je kreiran s ciljem da poboljša profitabilnost tvrtke. Kreirali smo dva algoritma, jedan koji koristi heurističko pretraživanje i drugi koji koristi povratnu neuronsku mrežu. Oba algoritma imaju svoje pozitivne i negativne strane, i za najbolje rezultate hibrid oba algoritma bi se mogao koristiti.

Abstract (english)

The goal of this thesis was to design and test new microservice for an existing time-tracking tool which will provide suggestions for time tracking. Our motivation was that by improving time-tracking experience we could get sounder time entries and reliable profitability reports. We decided to use Productive as our time-tracking tool as it is built around making companies more profitable. We created two different algorithms, one using a heuristic search, and another with a recurrent neural network. Both algorithms had positive and negative sides, and for best performance, a hybrid method could be used.

• Keywords: praćenje vremena; predikcija uzoraka; neuronska mreža; pretraživanje heuristikom; alat Productive
• Keywords (english): time tracking; pattern prediction; neural network; heuristic search; Productive tool
• Language: english
• URN:NBN: urn:nbn:hr:168:162203
• 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: 2020-01-07 21:20:02