Stefan Kostić

Mr. Stefan Kostić

School of Electrical Engineering, University of Belgrade, Belgrade
orcid

Research Focus & Metrics

Academic Career Length

12Years (2015-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
9 July 2020 in Entropy
Verified
Journal Article
Open access
PDF file
SKStefan Kostić
Stefan Kostić
MSMirjana Simic
Mirjana Simic
MKMiroljub Kostic
Miroljub Kostic
Due to telecommunications market saturation, it is very important for telco operators to always have fresh insights into their customer’s dynamics. In that regard, social network analytics and its application with graph theory can be very useful. In this paper we analyze a social network that is represented by a large telco network graph and perform clustering of its nodes by studying a broad set of metrics, e.g., node in/out degree, first and second order influence, eigenvector, authority and hub values. This paper demonstrates that it is possible to identify some important nodes in our social network (graph) that are vital regarding churn prediction. We show that if such a node leaves a monitored telco operator, customers that frequently interact with that specific node will be more prone to leave the monitored telco operator network as well; thus, by analyzing existing churn and previous call patterns, we proactively predict new customers that will probably churn. The churn prediction results are quantified by using top decile lift metrics. The proposed method is general enough to be readily adopted in any field where homophilic or friendship connections can be assumed as a potential churn driver.

1 October 2015
Verified
Conference Paper
Closed access
JSJelena D. Sretenovic
Jelena D. Sretenovic
SKStefan Kostić
Stefan Kostić
MSMirjana I. Simic
Mirjana I. Simic
This paper presents an experimental analysis of WCWCL-RSSI (Weight-Compensated Weighted Centroid Localization algorithm based on Received Signal Strength Indicator (RSSI)) in an urban environment. In order to collect the data necessary for localization purposes, measurements were performed in the GSM (Global System for Mobile Communications) network in Belgrade (the central zones of city). The results of the work provide a valuable insight into performance of this method, compared to traditional CL (Centroid Localization) and WCL (Weighted Centroid Localization) methods in an urban environment.

1 November 2018
Verified
Conference Paper
Closed access
SKStefan Kostić
Stefan Kostić
MDMilos Duricic
Milos Duricic
MSMirjana I. Simic
Mirjana I. Simic
MKMiroljub V. Kostic
Miroljub V. Kostic
Banking industry is very competitive and the market itself has become very saturated in the recent years. Because of this, it is vital for every banking institution to use all available information in order to gain some sort of competitive advantage. In this paper we will demonstrate that it is possible to gain more insight about banking service clients by using data mining and analysis tools, more specifically by using K-Means clustering. Specifically, we will demonstrate that we can define a group of customers that are more prone to purchase housing loan.