Enhancing Public Procurement in the European Union Through Constructing and Exploiting an Integrated Knowledge Graph

Abstract

Public procurement is a large market affecting almost every organisation and individual. Governments need to ensure efficiency, transparency, and accountability, while creating healthy, competitive and vibrant economies. In this context, we built a platform, consisting of a set of modular APIs and ontologies to publish, curate, integrate, analyse, and visualise an EU-wide, cross-border, and cross-lingual procurement knowledge graph. We developed end-user tools on top of the knowledge graph, for anomaly detection and cross-lingual document search. This paper describes our experiences and challenges faced in creating such a platform and knowledge graph and demonstrates the usefulness of Semantic Web technologies for enhancing public procurement.

TheyBuyForYou platform and knowledge graph: Expanding horizons in public procurement with open linked data

“…Some of the other external vocabularies and ontologies used are W3C Organisation ontology, W3C Registered Organisation Vocabulary (RegOrg), 35 SKOS, Schema.org, and Asset Description Metadata Schema (ADMS). 36 The ontology, data sets and some examples are released as open source on GitHub. 37…”

“…To this end, in order to deal with the aforementioned challenges, we built a platform, called TheyBuyForYou [36], consisting of a set of modular REST APIs and ontologies, to publish, curate, integrate, analyse, and visualise an EU-wide, cross-border, and cross-lingual procurement knowledge graph (KG) [31,32,36,37]. The KG includes procurement and company data gathered from multiple disparate sources across the EU and integrated through a common ontology network using an extract, transform, load (ETL) approach [6].…”

SemML: Facilitating Development of ML Models for Condition Monitoring with Semantics

“…It would be extremely costly and time-consuming to develop different data analysis applications for each data source or format. A better solution is to systematically organise these data and integrate them in a uniform way [39]. The challenges here are to prepare these data, by renaming of the variables, unifying sampling rate of the time series, synchronising the starting time stamps of time series, etc, or for short, to integrate these data in an uniform format and store them in one data base so that they can be further processed by machine learning algorithms.…”

Data Quality Barriers for Transparency in Public Procurement

“…To this end, in this article, we present a case where we applied a number of anomaly detection techniques over a set of integrated open data sets including procurement, company, and spending data of Slovenia. This has been realised through a platform we developed, TheyBuyForYou [10,11], for integrating, curating, and publishing cross-border and cross-language procurement data and related data sets into a Knowledge Graph (KG). A KG is an interconnected semantic knowledge organisation structure [12], using the Semantic Web and linked data approach and technologies [13].…”

“…Linked data is a fundamental part of the Semantic Web, and it is concerned with the integration of large scale and interrelated data sets on the Web (https://www.w3.org/standards/semanticweb/ (accessed on 19 February 2022)). In addition to the anomaly detection case, we used the platform and resulting KG in several business scenarios including public and private stakeholders [11]. Based on our experience gained through the construction and use of the platform and KG, we elaborate on a set of guidelines for publishing high quality procurement data allowing advanced procurement analytics, since there are significant shortcomings in the quality of data being published.…”