Web-aplikacija za polu-automatsko generiranje statističkih pokazatelja sportskih događaja

master's thesis

• Title (english): Web application for semi-automatic generation of sports event statistics
• Author: Luka Barišić
• Mentor: Igor Mekterović (mentor)
• Committee member: Igor Mekterović (predsjednik povjerenstva)
• Committee member: Ljiljana Brkić (član povjerenstva)
• Committee member: Boris Milašinović (član povjerenstva)
• Granter: University of Zagreb; Faculty of Electrical Engineering and Computing; Zagreb
• Defense date and country: 2023-02-24, Croatia
• Scientific / art field, discipline and subdiscipline: TECHNICAL SCIENCES; Computing

Abstract

Napredak tehnologije posljednjih godina je omogućio opsežno i relativno jednostavno prikupljanje podataka za različite sportske događaje. Ti podatci se onda koriste za različite analize od strane samih sportskih klubova, kao i trećih strana. Tijekom prijenosa sportskih događaja sportski komentatori tipično navode različite statistike koje čine prijenos zanimljivijim. Ti uvidi se mogu podijeliti u dvije kategorije: statistike prikupljene prije početka utakmice i statistike koje nastaju za vrijeme trajanja utakmice i, osim povijesnih, koriste podatke o tekućoj utakmici. Zadatak ovog diplomskog rada bio je razviti prototip sustava u vidu web-aplikacije koja će omogućiti polu-automatsko generiranje različitih statističkih pokazatelja u obje navedene kategorije. Prototip se oslanja na bazu podataka prethodnih sportskih događaja i priliv novih podataka o tekućim događajima. Od korisnika se očekuje da definira polazni skup podataka (koji sport i koji timovi su u pitanju, koliki historijat koristiti, itd.) te da pruža povratnu informaciju koliko je uspješna bila predložena statistika. Osim pred-definiranih statističkih pokazatelja (koji naravno ovise o vrsti sporta) prototip generira i ad-hoc pokazatelje (npr. u smislu detekcije odstupanja). U radu se razmatra i mogućnost različitih vizualizacija, donosi se ocjena ostvarenog pristupa te smjernice za budući razvoj.

Abstract (english)

Advances in technology in recent years have made it possible to collect data for various sporting events extensively and relatively easily. This data is then used for various analyses by the sports clubs themselves as well as by the third parties. During the broadcast of sporting events, sports commentators typically cite various statistics that make the broadcast more interesting. These insights can be divided into two categories: statistics collected before the start of the match and statistics generated during the match which, in addition to historical, use data on the current match. The task of this thesis was to develop a prototype system in the form of a web application that will allow the semi-automatic generation of various statistical indicators in both mentioned categories. The prototype relies on a database of previous sporting events and an influx of new data on current events. Users are expected to define a baseline data set (which sport and which teams are involved, how much history to use, etc.) and to provide feedback on how successful the proposed statistics were. In addition to pre-defined statistical indicators (which of course depend on the type of sport), the prototype generates ad-hoc indicators too (e.g. in terms of outlier detection). The paper also discusses the possibility of different visualisations, provides an assessment of the paper's results and guidelines for future developments.

• Keywords: web aplikacija; Python; Django; PostgreSQL; sportska statistika; automatsko generiranje; detekcija odstupajućih vrijednosti
• Keywords (english): web application; Python; Django; PostgreSQL; sports statistics; automatic generation; outlier detection
• Language: croatian
• URN:NBN: urn:nbn:hr:168:811296
• 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: 2023-07-13 09:54:56