University of Twente Student Theses

Login

Missing data imputation based on probabilistic data

Kampen, Coen van (2019) Missing data imputation based on probabilistic data.

[img] PDF
432kB
Abstract:Missing data is a vast problem in data science. Thereare different reasons that data might be missing. An ex-ample would be when people take a survey, but want tokeep some information private. There exist several goodmethods that try to handle missing data. The most un-ambiguous method involves deleting the missing values orrecords containing missing values. However, this is of-ten not preferred as too much information might be lost.Therefore, missing data is usually handled by predictingthe missing values using an imputation method. Goodimputation techniques exist, but they often introduce abias into the data. This research attempts to develop animproved imputation method based on probabilistic data.This method will be compared to known methods by adeveloped evaluation framework. It is assumed this novelmethod will improve data quality.
Item Type:Essay (Bachelor)
Clients:
Unknown organization, Enschede, Nederland
Faculty:EEMCS: Electrical Engineering, Mathematics and Computer Science
Subject:54 computer science
Programme:Computer Science BSc (56964)
Link to this item:https://purl.utwente.nl/essays/79142
Export this item as:BibTeX
EndNote
HTML Citation
Reference Manager

 

Repository Staff Only: item control page