Corruption measurement is particularly challenging, as it is difficult to observe and unlike other crimes, both actors obtain advantages and have no incentive to bring the illegal agreement to light. Classic methods for measuring corruption are based on subjective or objective indicators, but both suffer of some issues that may limit their overall applicability. More recent approaches that rely on red flag indicators – with the aim of highlighting anomalies and alerting the system to the possible risk of corruption – make it possible to leverage data from previously awarded public contracts to focus the fight against corruption where it is most likely to be present. Specifically, in this work we show an approach based on red flag indicators in public procurement. By exploiting data from the Italian Banca Data Nazionale dei Contratti Pubblici, a number of red flag indicators proposed by the international literature are computed at contracting body level and summarised into a synthetic indicator, in order to shed light on the most risky behaviours.

Download

Simone Del Sarto is post-doc researcher at the Department of Statistics, Computer science, Applications "Giuseppe Parenti" of the University of Florence. He earned the PhD in Statistics in 2015 at the University of Perugia. He is part of a team of research experts within the Italian Anti-Corruption Authority dealing with a project for constructing indicators for corruption prevention and transparency promotion. His main interests concern latent variable models (specifically, Item Response Theory, latent class and latent Markov models) and composite indicators construction in the field of education and corruption measurement.

Michela Gnaldi is Associate professor of Applied Statistics in the Department of Political Sciences of the University of Perugia, Italy, where she teaches Data science for the quality of institutions and Quantitative methods for social research. She is consultant of the Council of the Italian National Anti-Corruption Authority, as a senior statistician expert, and of other national and international agencies (i.e., UNHCR, United Nation Higher Commissioner for Refugees). She has been leading (with Prof. Ponti) the Italian project “Measuring and contrasting corruption. Direct and indirect methods to quantify corruption”. Since 2016 she leads a thematic area within the Italian Association for Quality of Life (AIQUAV) on “Contrast to corruption, social integrity and quality of life”.

Paolo Coppola is Associate Professor of Computer Science at the University of Udine where he teaches Computer Science and Law, Software Engineering, Digitization of Business and Public Administration. His research interests range from the study of linear logics, to the development of context-dependent mobile systems, to eGovernment and eDemocracy. He was an MP in the last legislature, chairman of the parliamentary inquiry committee on the level of digitalization of public administration and he is currently advisor to the Minister for technological innovation and digital transition.

He is Computer Scientist with a strong passion for data. He started his career working on public data as a Data Analyst in the Parliamentary Commission of inquiry of the Chamber of Deputies and as IT Consultant in the Digital Transformation Team of the The Presidency of the Council of Ministers. Today he is dealing with Big Data in Capgemini, a global leader in consulting, digital transformation, technology and engineering services.
His master's thesis entitled "Data analysis and construction of corruption risk indicators for the National Database of Public Contracts" was published as a working paper within the Scientific Series of the Italian National Anti-Corruption Authority.

The measurement of complex issues facing the world today, where great amounts of information and multiple aspects of very different nature are used, has lead to define the use of composite indicators as tools that allow aggregating all this information in an intuitive and easy to interpret way.

However, when aggregating single indicators in an overall composite indicator, special attention should be paid to the compensability degree among the indicators allowed by the aggregation procedure. In line with this concept, first, we present the Multiple Reference Point Weak-Strong Composite Indicator (MRP-WSCI), where two different aggregations are proposed: the weak indicator, allowing for full compensation among the single indicators, and the strong indicator, not allowing for any compensation.

On the other hand, we present the Multiple Reference Point Partially Compensatory Indicator (MRP-PCI), where a different compensation index can be established for each single indicator. In both approaches, the decision maker can establish any number of reference levels for each indicator, and the final outcome can be interpreted in terms of the position with respect to these levels. The approaches are illustrated using an example based on the EU-Regional Social Progress Index (EU-SPI). Finally, some reflections about the construction of composite indicators are provided.

Download

Samira El Gibari is a postodoctoral personnel training at the University of Malaga. Her doctoral thesis was designed to be an academic contribution to the evaluation of university performance using a recently developed methodology, based on the multicriteria reference point method and data envelopment analysis as a multi criteria decision tool. She holds an MA in economic and business analysis and a degree in Business and Management both from the University of Malaga. Her research has been supported by the Spanish Ministry of Science, Innovation and Universities.

Josè Manuel Cabello is an associated professor of Applied Economy at the University of Malaga, Spain. His research is focused on multi-objective programming methodologies, mainly in interactive methods and their applications to industry, development of composite indicators and portfolio selection. He has (co)authored more than 25 publications and has reviewed papers for 5 international journals. He has participated in more than 15 research projects, and he has held joint research activities with private companies.

Trinidad Gomez is a full professor of Quantitative Methods for Economy at the University of Malaga, Spain. Her current research is focused on Multi-objective Programming Techniques, Data Envelopment Analysis and their applications to public and private organizations. She has co-authored publications in different categories of journals as Operations Research and Management Science, Education and Educational Research, Forestry, and Environmental Sciences, among others.

Francisco Ruiz is a full professor of Quantitative Methods for Economy at the University of Malaga, Spain. His research is focused on multiobjective programming methodologies, mainly in interactive methods and their applications to industry, development of composite indicators and portfolio selection. He is a coordinator of the Spanish Group on Multiple Criteria
Decision Making (www.multicriterio.es). He has (co)authored more than 50 publications and has reviewed papers for 25 international journals. He has participated in more than 30 research projects, and he has held joint research activities with several Universities in Europe and North America, and with public and private companies.