Institutional Repository of Vilnius University
Išskirčių radimas prekybos centrų kvitų duomenyse /
Abstract
dc:descriptionDetecting outliers is a crucial task for all retail sellers to make as much profit as possible. Incorrect prices in their database can impact the results of their pricing models which can lead to huge losses in revenue. This paper reviews methods for detecting these outliers. Six methods will be tested, three methods will be from the traditional statistics — Z score, interquartile range and kernel density estimation and three machine learning methods will be used — isolation forest, local outlier factor and local distance-based outlier factor. In this work, it was observed that traditional statistical methods were superior to machine learning models. It also included a temporal analysis to check how often the cut-offs should be recalculated.
Degree
thesis:*- Grantor dc:publisher
- Institutional Repository of Vilnius University
- Year dc:date
- 2025
Author and committee
dc:creator, dc:contributor.*- Author dc:creator
-
- Varkalis, Aivaras,
Rights
dc:rights- Statement dc:rights
-
- info:eu-repo/semantics/openAccess
- Language dc:language
- lit
Identifiers
dc:identifier.*- Repository record dc:identifier
- https://repository.vu.lt/VU:ELABAETD239028891&prefLang=en_US