(Español) Conferencia Profa. Gabriela Sicilia
7 June, 2017 | ||
12:00 pm |
19 May, 2017 | a | 20 May, 2017 |
11 April, 2017 | ||
12:30 pm |
Tittle: Combining metaheuristics with mathematical programming and machine learning
Speaker: El-Ghazali Talbi (University of Lille 1)
Date: 11/04/2017 12:30h
Location: Sala de Seminarios, Edificio Torretamarit
Abstract:
During the last years, interest on hybrid metaheuristics has risen considerably in the field of optimization and machine learning. The best results found for many optimization problems in science and industry are obtained by hybrid optimization algorithms. Combinations of optimization tools such as metaheuristics, mathematical programming, constraint programming and machine learning, have provided very efficient optimization algorithms. Four different types of combinations are considered in this talk: (i) Combining metaheuristics with complementary metaheuristics. (ii) Combining metaheuristics with exact methods from mathematical programming approaches which are mostly used in the operations research community. (iii) Combining metaheuristics with machine learning and data mining techniques.
10 November, 2016 | ||
11:00 am |
Title: Efficiency and productivity of Portuguese municipalities after local reforms
Speaker: José Manuel Cordero
Date: 10/11/2016 11:00 h
Location: Sala de Seminarios, Edificio Torretamarit
Abstract:
The aim of this work is to examine the effect of the reforms introduced in the structure of the Portuguese local administration after the bailout agreement in 2011 on the efficiency and productivity of municipalities. Specifically, we assess the performance of the 278 Portuguese mainland municipalities for the recent six-year period 2009-2014. Firstly, in order to determine a measure of productivity change we apply the global Malmquist productivity index developed by Pastor and Lovell (2005), which allows determining productivity change over time. Subsequently, since we are aware that the performance of local governments might be affected by their socio economic context, we apply the conditional frontier estimators developed by Daraio and Simar (2005) adapted to a dynamic framework by Mastromarco and Simar (2015). Furthermore, thie technique allows us to examine the effect of contextual and exogenous variables on municipal efficiency levels and technological change. The results reveal that the recent local reforms have had a positive effect on the productivity of municipalities, but only for small and medium-sized municipalities.
Brief Bio:
He is an Associate Professor in the Department of Economics in the University of Extremadura. He holds a degree and Ph.D. in Economics from the same university. His scientific production has been focused in the following fields of research: efficiency measurement in the public sector, economics of education and fiscal federalism, including local and regional governments. His research experience in the aforementioned fields has been reflected in multiple scientific articles published in referred journals as well as in several books and book chapters. He was a visiting scholar in Teachers College de Columbia University with the funds provided by the Spanish Ministry of Science and Education. He has participated as principal researcher or as a member of the research group in multiple research projects from different entities (Ministry of Economy and Competitiveness, Extremadura Government, Ramón Areces Foundation or the Institute for Fiscal Studies). Likewise, he has attended numerous conferences and congresses in Spain and worldwide related to his research interests. Previously he occupied a position as a technical advisor for the President of the Provincial Government in Badajoz and the President of the National Comission of Local Governments integrated in the Spanish Federation of Municipalities and Provinces.
10 November, 2016 | ||
10:00 am |
Title: Assessment of different approaches to incorporate contextual variables in efficiency measurement.
Speaker: Cristina Polo
Date: 10/11/2016 10:00h
Location: Sala de Seminarios, Edificio Torretamarit
Abstract:
Incorporating the effect of the exogenous variables into the estimation of efficiency measures is one of the issues that have received more attention in recent years within the operations research literature. The aim of this work is to assess the performance of two recently developed methodologies such as the nonparametric conditional model and the StoNEZD (Stochastic Nonparametric Envelopment on Z-variables Data) method, which combines both parametric and nonparametric techniques. To do this, we conduct a Monte Carlo experiment with various alternatives production functions. According to the results, StoNEZD methodology performs better, although the conditional DEA model also provides acceptable results in all the proposed scenarios, thus it can be considered as a valid alternative when the available data cannot be adapted to the specific framework of the StoNEZD model.
Brief Bio:
She has a degree in Physics by the University of Extremadura. He has a master’s degree in Social and Legal Sciences (specializing in Economics, Business and Labour). Her main research lines are focused on computational aspects related to efficiency measurement and its application in public services as diverse as education, health and municipal services. She has several publications in prestigious international journals and also she has participated as speaker at the most important meetings, nationals and internationals, which are related to efficiency and productivity measurement. Previously, she further developed research activities related to computational aspects in the Laboratory of Intelligent Sensory Systems (LSSI) of the UEx and the National Institute for Aerospace Technology (INTA) of the Ministry of Defense.