Napovedovanje stopnje interakcij z oglasi

diplomsko delo

Juš Hladnik (Author), Igor Kononenko (Mentor), Domen Košir (Co-mentor)

Abstract

V spletnem oglaševanju je stopnja interakcij z oglasom (angl. click-through rate oz. CTR) ena izmed bolj pomembnih metrik o uspešnosti posameznega oglasa. V diplomskem delu se ukvarjamo z napovedjo CTR oglasov na posameznih spletnih straneh za novo kreirane oglase, ki v preteklosti še niso bili prikazani, in z ocenjevanjem atributov oglasov. Podatke o oglasih in klikih na oglase podjetja Celtra d.o.o. pripravimo na več različnih načinov in na njih preizkusimo več regresijskih metod strojnega učenja - naključni gozd, k-najbližjih sosedov in matrično faktorizacijo. Atribute ocenjujemo z RReliefF-om in razliko variance. Ugotovimo, da na CTR najbolj vpliva spletna stran in velikost oglasa. Na podlagi napovedi stopenj interakcij se lahko podjetje odloči, na katere spletne strani želi objaviti oglas in s tem povečati število klikov nanj.

Keywords

peptidi;naključni gozd;k-najbližjih sosedov;matrična faktorizacija;RReliefF;spletno oglaševanje;računalništvo;računalništvo in informatika;računalništvo in matematika;interdisciplinarni študij;univerzitetni študij;diplomske naloge;

Data

Language:	Slovenian
Year of publishing:	2020
Typology:	2.11 - Undergraduate Thesis
Organization:	UL FRI - Faculty of Computer and Information Science
Publisher:	[J. Hladnik]
UDC:	004(043.2)
COBISS:	1538517955
Views:	1053
Downloads:	222
Average score:	0 (0 votes)
Metadata:

Other data

Secondary language:	English
Secondary title:	Prediction of degree of interaction with creatives
Secondary abstract:	Click-through rate (CTR) is one of the most important measurements in online advertising that tells us how successful a certain ad is. In this thesis we work on CTR prediction of ads on individual websites for newly created ads that have not been published on any website in the past. We also work on evaluation of attributes that describe these ads. We use data about ads and ad clicks from Celtra d.o.o. and process it in different ways. Then we apply different machine learning methods - random forest, k-nearest neighbors, and matrix factorization. For attribute evaluation we use RReliefF and the difference of variance. We find out that the website, on which an ad is published, and the size of an ad influence CTR the most. Based on our predictions of CTR, a company can decide on which websites they should publish the ad thus enlarge the number of clicks on the ad.
Secondary keywords:	random forest;k-nearest neighbors;matrix factorization;RReliefF;online advertising;computer science;computer and information science;computer science and mathematics;interdisciplinary studies;diploma;
Type (COBISS):	Bachelor thesis/paper
Study programme:	1000407
Embargo end date (OpenAIRE):	1970-01-01
Thesis comment:	Univ. v Ljubljani, Fak. za računalništvo in informatiko
Pages:	46 str.
ID:	11386553