diplomsko delo
Abstract
Diplomsko delo opisuje celoten postopek izdelave namenskega priporočilnega sistema. Vsebuje predstavitev postopka vzpostavitve platforme PredictionIO, predprocesiranja podatkov iz dnevniških zapisov, vzpostavitve aplikacije ter testiranja uspešnosti sistema. Aplikacija deluje na podlagi analize ključnih besed, ki so bile pridobljene iz dnevniških zapisov gledanosti TV-vsebin za posameznega uporabnika, na podlagi česar sistem priporoči, kateri oglas je za posameznega uporabnika najprimernejši.
Keywords
priporočilni sistem;mera F;uporabniški vmesniki;oglasi;diplomske naloge;
Data
Language: |
Slovenian |
Year of publishing: |
2020 |
Typology: |
2.11 - Undergraduate Thesis |
Organization: |
UM FERI - Faculty of Electrical Engineering and Computer Science |
Publisher: |
[L. Abraham] |
UDC: |
004.775(043.2) |
COBISS: |
35504643
|
Views: |
1159 |
Downloads: |
33 |
Average score: |
0 (0 votes) |
Metadata: |
|
Other data
Secondary language: |
English |
Secondary title: |
Development of recommendation system for targeted TV advertising |
Secondary abstract: |
This thesis describes the entire process of making a domain-specific recommendation system. It includes the presentation of the PredictionIO platform, preprocessing log data, setting up an application, and testing the system’s performance. The application works based on keyword analysis. These keywords were obtained from the log records of TV content ratings for an individual user. Based on this, the system recommends which advertisement is the best for each user. |
Secondary keywords: |
recommendation system;measure F;user interface;advertisements; |
Type (COBISS): |
Bachelor thesis/paper |
Thesis comment: |
Univ. v Mariboru, Fak. za elektrotehniko, računalništvo in informatiko, Računalništvo in informacijske tehnologije |
Pages: |
XI, 44 f. |
ID: |
11977665 |