Please use this identifier to cite or link to this item:
Title: Predicting the number of bidders in public procurement
Authors: Görgün, Mustafa Kaan
Kutlu, Mücahid
Taş, Bedri Kamil Onur
Keywords: Competitiveness Prediction
European Union
Public Procurement
Issue Date: Sep-2020
Publisher: Institute of Electrical and Electronics Engineers Inc.
Source: Gorgun, M. K., Kutlu, M., and Taş, B. K. O. (2020, September). Predicting The Number of Bidders in Public Procurement. In 2020 5th International Conference on Computer Science and Engineering (UBMK) (pp. 360-365). IEEE.
Abstract: Public procurement constitutes an important part of economical activities. In order to effectively use public resources, increasing competition among firms participating in public procurement is essential. In this work, we investigate the impact of content information on the number of bidders in public procurement. We explore 6 different groups of features including n-grams, named entities, language of notices, country of the authority, description length, and CPV codes. In our experiments, we show that our proposed models outperform all baselines. In particular, k-nearest neighbor model with n-grams achieves the best prediction accuracy. Our model can be used by public procurement officials to automatically examine procurement notices and detect the ones causing low competition. Besides, participating firms can use our model to predict potential competition they will face, and make better decisions accordingly. © 2020 IEEE.
ISBN: 978-172817565-2
Appears in Collections:Bilgisayar Mühendisliği Bölümü / Department of Computer Engineering
İktisat Bölümü / Department of Economics
Malzeme Bilimi ve Nanoteknoloji Mühendisliği Bölümü / Department of Material Science & Nanotechnology Engineering
Scopus İndeksli Yayınlar Koleksiyonu / Scopus Indexed Publications Collection
WoS İndeksli Yayınlar Koleksiyonu / WoS Indexed Publications Collection

Show full item record

CORE Recommender


checked on Sep 23, 2022

Page view(s)

checked on Dec 26, 2022

Google ScholarTM



Items in GCRIS Repository are protected by copyright, with all rights reserved, unless otherwise indicated.