Public Sector Corruption Analysis with Modified K-means Algorithm Using Perception Data

Corruption in public sectors has received increased attention over the last few decades due to its widespread presence all over the globe. We assert that public sector corruption must be properly analyzed and detected as soon as possible so that preventive and corrective measures can be taken. Thus,...

Full description

Saved in:
Bibliographic Details
Published in2020 11th International Conference on Electrical and Computer Engineering (ICECE) pp. 198 - 201
Main Authors Pramanik, Anik, Sarker, Amlan, Islam, Zabirul, Hashem, M.M.A.
Format Conference Proceeding
LanguageEnglish
Published IEEE 17.12.2020
Subjects
Analytical models
Attribute Weighting
Clustering Algorithm
Clustering algorithms
Corruption Analysis
Data models
Intelligent System
Organizations
Robustness
Sociology
Statistics
Online AccessGet full text

Cover

More Information
Summary:Corruption in public sectors has received increased attention over the last few decades due to its widespread presence all over the globe. We assert that public sector corruption must be properly analyzed and detected as soon as possible so that preventive and corrective measures can be taken. Thus, we developed a model that uses a modified K-means approach, based on K-means algorithm, on perception data, to analyze corruption within the public sector. The model was applied to analyze the corruption within public sectors of Bangladesh. The public sector organizations were segmented based on their different levels of corruption and resultant clustering showed an accuracy of 87.5% with official corruption data as reference. This paper also demonstrates the architecture of a cloud based web-application, developed based on this model that adds robustness and autonomy to the intelligent system.
DOI:10.1109/ICECE51571.2020.9393110