Aydın Ulucan

A Multiple Criteria Energy Decision Support System

Abstract Multiple Criteria Decision Analysis (MCDA) techniques are particularly suitable for Energy and Environment (E&E) decisions due to multiple criteria nature of these types of problems and they have been widely applied in this area. Main points that can be taken into consideration when examining the MCDA literature related to E&E are the selection of appropriate method, selection of criteria to be used and the widely distributed application areas. The motivation behind this study is designing such a Decision Support System (DSS) that enables the energy decision makers to perform analysis using different methods of MCDA and different criteria from various application areas and test the applicability of the system through an application in Turkish Energy Sector. The system includes several methods of MCDA and common parameters from previous studies in order to provide different approaches of evaluating decision problems. With this feature, the system stands on the intersection of MCDA and E&E fields. ...

An analysis of mean-variance portfolio selection with varying holding periods

In this study, I investigate optimal holding period (investment horizon) for the classical mean-variance portfolio optimization problem. Optimal holding period ex-post is determined using Istanbul Stock Exchange ISE-100 index stocks and Athens Stock Exchange FTSE-40 index stocks data. I extend the approach to other downside risk criteria including expected loss and semi-variance. The analysis involves solving the portfolio optimization problem for a total of 648 cases – two stock exchanges, three different target return levels, three different risk measures and 36 different time periods with rolling data. I discuss the results from the view point of two neighbouring markets: one with an upward trend and the other with a downward trend. The results show that portfolio returns with varying holding periods have a convex structure with an optimal holding period.

A multiple criteria sorting methodology with multiple classifi cation criteria and an application to country risk evaluation

Abstract In this paper, we propose an extension of the standard UTADIS methodology, an approach that originates from multicriteria decision aid (MCDA) for sorting problems, such that it can handle more than one classification criteria simultaneously which possibly involves different predefined classes for alternatives. Moreover, we test the classification ability of the standard UTADIS methodology using the out-of-classification criterion approach, a new variant of the studies comprising out-of-time and out-of-sample testing methodologies. Results obtained in out-of-classification criterion testing are then compared with the classification ability of the Multiple Classification Criteria UTADIS (MCC UTADIS). Finally, an application to country risk evaluation is performed. In this application, classifications of two credit rating agencies, Standard & Poors and Moodys, are taken as two different classification criteria. Moreover, robustness of MCC UTADIS method is tested through using several data sets. Re...

Credit risk estimation using payment history data: a comparative study of Turkish retail stores

Our paper presents a comparative study applying logistic regression and multiple criteria decision analysis tools to the operations of wholesalers to assess the credit risk of their retailers using payment history data and to cluster the risky customers by ranking their risk levels. Our sample comprises approximately 6,000 retailer customers and 600.000 transactions of one of the major wholesalers of Turkey. Our findings emphasize the importance of using payment history and some non-financial factors data for predicting the creditworthiness of a firm.

The measurement of agricultural productivity change in OECD countries with Fuzzy data

In this paper, we aim to measure agricultural productivity change of 34 OECD countries between years 1990 and 2014. The methods employed are data envelopment analysis (DEA) and malmquist productivity index (MPI). DEA is a relative efficiency method in a production technology, whereas MPI is based on DEA to measure the changes in the production technology over time. Our challenge is the existence of missing data points over the years in the initial dataset, which correspond to approximately 9% of the data. Removing units, factors or years with missing data as commonly practiced in DEA, would cause loss of information and makes it very difficult to draw conclusions in such a macro-data. We present the idea of using averages of available data points for a given factor and average variations over the years in those data to produce intervals for the missing points and handle the problem without any dimension reduction in the available data. Fuzzy DEA approach is employed using the calculated factor-specific intervals followed by MPI calculations to conduct a productivity change analysis. We suggest and empirically illustrate that instead of narrowing down the scope of the analysis by excluding the points missing, applying fuzzy approaches is an option worth considering by which it can be possible to make the best out of the available information. The results of the analysis are interpreted with respect to years, countries, regions and economic size of the countries.

Ranking of Natural Gas Transmission Projects at the Southeastern Corridor: A Multi-Criteria Approach on the Countries of the Region

The southern energy corridor of Europe has been the subject of the main political developments and investment projects over the last decade. While Europe is focusing on energy needs and security, the energy-producing countries want to increase economic benefits by increasing their strategic importance. Turkey, which is placed between them, has a chance to become an energy terminal. In this study, Turkey’s available and potential gas transmission projects, including pipelines and LNG, are ranked by using a multi-criteria decision-making technique, namely ELECTRE. The method, which uses quantitative and qualitative variables such as investment cost, geopolitics, country risk, and trade volume, reveals that the Israel-Turkey offshore project is the most suitable one for securing natural gas demand of Europe. The same methodology also implies that the Israel-Turkey offshore project is the best also for Israel. Lastly, the sensitivity analysis, which is applied using parameters of different scenarios to reflect the uncertainties in the decision-making process shows that this project is a priority for both countries as the interests of the two countries overlap. Moreover, our work has also indicated that scenarios that would make the second priority project of the countries are not realistic.