Guvenir H.A.,Bilkent University |
Cakir M.,Central Bank of the Republic of Turkey
Expert Systems with Applications | Year: 2010
Voting features based classifiers, shortly VFC, have been shown to perform well on most real-world data sets. They are robust to irrelevant features and missing feature values. In this paper, we introduce an extension to VFC, called voting features based classifier with feature construction, VFCC for short, and show its application to the problem of predicting if a bank will encounter financial distress, by analyzing current financial statements. The previously developed VFC learn a set of rules that contain a single condition based on a single feature in their antecedent. The VFCC algorithm proposed in this work, on the other hand, constructs rules whose antecedents may contain conjuncts based on several features. Experimental results on recent financial ratios of banks in Turkey show that the VFCC algorithm achieves better accuracy than other well-known rule learning classification algorithms. © 2009 Elsevier Ltd. All rights reserved.
Ozmen A.,Middle East Technical University |
Weber G.-W.,Middle East Technical University |
Weber G.-W.,University of Siegen |
Weber G.-W.,University of Ballarat |
And 2 more authors.
Journal of Global Optimization | Year: 2013
This paper contributes to classification and identification in modern finance through advanced optimization. In the last few decades, financial misalignments and, thereby, financial crises have been increasing in numbers due to the rearrangement of the financial world. In this study, as one of the most remarkable of these, countries' debt crises, which result from illiquidity, are tried to predict with some macroeconomic variables. The methodology consists of a combination of two predictive regression models, logistic regression and robust conic multivariate adaptive regression splines (RCMARS), as linear and nonlinear parts of a generalized partial linear model. RCMARS has an advantage of coping with the noise in both input and output data and of obtaining more consistent optimization results than CMARS. An advanced version of conic generalized partial linear model which includes robustification of the data set is introduced: robust conic generalized partial linear model (RCGPLM). This new model is applied on a data set that belongs to 45 emerging markets with 1,019 observations between the years 1980 and 2005. © 2012 Springer Science+Business Media, LLC.
Tumen S.,Central Bank of the Republic of Turkey |
Unalmis D.,Central Bank of the Republic of Turkey |
Unalmis I.,Central Bank of the Republic of Turkey |
Energy Economics | Year: 2015
Long-term environmental consequences of taxing fossil fuel usage have been extensively studied in the literature. However, these taxes may also impose several short-run macroeconomic policy challenges, the nature of which remains underexplored. This paper investigates the mechanisms through which environmental taxes on fossil fuel usage can affect the main macroeconomic variables in the short-run. We concentrate on a particular mechanism: speculative storage. Formulating and using a dynamic stochastic general equilibrium (DSGE) model, calibrated for the United States, with an explicit storage facility and nominal rigidities, we show that in designing environmental tax policies it is crucial to account for the fact that fossil fuel prices are subject to speculation. The existence of forward-looking speculators in the model improves the effectiveness of tax policies in reducing fossil fuel usage. Improved policy effectiveness, however, is costly: it drives inflation and interest rates up, while impeding output. Based on this tradeoff, we seek an answer to the question how monetary policy should interact with environmental tax policies in our DSGE model of fossil fuel storage. We show that, in an environment with no speculative storers, monetary policy should respond to output along with CPI inflation in order to minimize the welfare losses brought by taxes. However, when the storage facility is activated, responding to output in the monetary policy rule becomes less desirable. © 2014 Elsevier B.V.
Ozturk H.,Central Bank of the Republic of Turkey |
Namli E.,Istanbul University |
Erdal H.I.,Turkish Cooperation and Coordination Agency TIKA
Computational Economics | Year: 2015
Sovereign credit ratings have been a controversial issue since the outbreak of the 2008 financial crisis. Among the debates the inaccuracies stay at the centre. By employing classification and regression trees, multilayer perceptron, support vector machines (SVM), Bayes net, and naïve Bayes; we compare the ability of various learning techniques with the conventional statistical method in predicting sovereign credit ratings. Experimental results suggest that all the techniques excluding SVM have over 90 % accurate prediction. According to within one and two notch accurate prediction measure, the prediction performance of SVM also increases above 90 %. These findings indicate a clear outperformance of AI methods over the conventional statistical method. The results have many implications for the practitioners in credit scoring industry. Amidst the regulatory measures that encourage individual credit scoring for international financial institutions, these findings suggest that up-to-date AI methods serve quite reliable technical tools to predict sovereign credit ratings. © 2015 Springer Science+Business Media New York
Seydim A.Y.,Central Bank of the Republic of Turkey |
Dunham M.H.,Southern Methodist University |
Meng Y.,Southern Methodist University
International Journal of Mobile Computing and Multimedia Communications | Year: 2012
Location based service (LBS) is an appealing technology in the pervasive mobile computing environment. In this environment, the answer to a location dependent query depends on the location of the mobile user. However, the location granularity to which the mobile unit is bound by a location service may differ from that stored in the content provider's database. As a result, a location granularity mismatch occurs. The authors propose a general software architecture, location leveling, to solve this problem. As their layered location leveling solution is independent of the support provided by the wireless provider and the content provider, it is flexible enough to be used by any. The location leveling (ll) model can be implemented as an independent agent or broker in the middleware layer. The proposed approach is developed with solid theoretical foundation found in previous multidimensional data modeling studies. Copyright © 2012, IGI Global.
Aysoy C.,Central Bank of the Republic of Turkey |
Kirli D.H.,Central Bank of the Republic of Turkey |
Tumen S.,Central Bank of the Republic of Turkey
Food Policy | Year: 2015
The market for fresh food is often characterized by a large number of intermediaries delivering the product from the farmer to the retailer. The existence of these intermediaries, especially the informal ones, is often claimed to introduce market frictions that push fresh food prices up. We test the hypothesis that scaling down these frictions reduces the level of prices. Our data come from a policy reform in Turkey concerning the supply chain regulations in the market for fresh fruits and vegetables. Starting from January 1st, 2012, a new law is enacted (i) to remove informal intermediaries, (ii) to reduce the farmers' cost of access to formal intermediaries such as wholesale market places, and (iii) to provide the farmers with the option to directly sell their products to retailers-bypassing the wholesale intermediaries. This policy reform resembles a natural experiment that exogenously reduces the supply chain barriers in the market for fresh fruits and vegetables. Using quasi-experimental methods, we show that the policy reform has strikingly reduced the prices in the wholesale market. We also provide some rough evidence that there is no price effect in the retail market, which suggests that part of the wholesale markups may have been transferred to the retailers. Taken at face value, these results provide some hints that consumers have not received any direct benefits from the reform-ignoring the general equilibrium effects. © 2015 Elsevier Ltd.
Ozorhan E.K.,Central Bank of the Republic of Turkey |
Kuban E.K.,Central Bank of the Republic of Turkey |
Cicekli N.K.,Central Bank of the Republic of Turkey
Information Sciences | Year: 2010
This paper proposes the application of the abductive event calculus to the web service composition and execution problem. There are different approaches to web service composition, which are suitable for different application scenarios. In this paper, we are concerned with the formalization of both the interleaved and template-based approaches using the event calculus framework. First, in the interleaved approach, it is shown that given a set of OWL-S web service descriptions in a service repository and a set of user specified inputs and outputs from domain ontology, the abductive event calculus can be used to generate web service compositions and return values for the outputs by executing the necessary web services. Next, in the template-based approach, it is shown that if generic web service compositions are given as templates using OWL-S, they can be translated into the axioms of the event calculus and the abductive theorem prover can be used to generate the actual web service compositions which can be executed afterwards. © 2010 Elsevier Inc. All rights reserved.
Atuk O.,Central Bank of the Republic of Turkey |
ozmen M.U.,Central Bank of the Republic of Turkey
Tobacco Control | Year: 2016
Background The current tobacco taxation scheme in Turkey, a mix of high ad valorem tax and low specific tax, contains incentives for firms and consumers to change pricing and consumption patterns, respectively. The association between tax structure and price and tax revenue stability has not been studied in detail with micro data containing price segment information. Objectives In this study, we analyse whether incentives for firms and consumers undermine the effectiveness of tax policy in reducing consumption. Methods We calculate alternative taxation scheme outcomes using differing ad valorem and specific tax rates through simulation analysis. We also estimate price elasticity of demand using detailed price and volume statistics between segments via regression analysis. Findings A very high ad valorem rate provides strong incentives to firms to reduce prices. Therefore, this sort of tax strategy may induce even more consumption despite its initial aim of discouraging consumption. While higher prices dramatically reduce consumption of economy and medium price segment cigarettes, demand for premium segment cigarettes is found to be highly price-inelastic. Conclusions The current tax scheme, based on both ad valorem and specific components, introduces various incentives to firms as well as to consumers which reduce the effectiveness of the tax policy. Therefore, on the basis of our theoretical predictions, an appropriate tax scheme should involve a balanced combination of ad valorem and specific rates, away from extreme (ad valorem or specific dominant) cases to enhance the effectiveness of tax policy for curbing consumption. © 2016 by the BMJ Publishing Group Ltd.
Ozmen M.U.,Central Bank of the Republic of Turkey
Online Information Review | Year: 2015
Purpose The purpose of this paper is to analyse usersattitudes towards online information retrieval and processing. The aim is to identify the characteristics of information that better capture the attention of the users and to provide evidence for the information retrieval behaviour of the users by studying online photo archives as information units. Design/methodology/approach The paper analyses a unique quasi-experimental data of photo archive access counts collected by the author from an online newspaper. In addition to access counts of each photo in 500 randomly chosen photo galleries, characteristics of the photo galleries are also recorded. Survival (duration) analysis is used in order to analyse the factors affecting the share of the photo gallery viewed by a certain proportion of the initial number of viewers. Findings The results of the survival analysis indicate that users are impatient in case of longer photo galleries; they lose attention faster and stop viewing earlier when gallery length is uncertain; they are attracted by keywords and initial presentation and they give more credit to specific rather than general information categories. Practical implications Results of the study offer applicable implications for information providers, especially on the online domain. In order to attract more attention, entities can engage in targeted information provision by taking into account people attitude towards information retrieval and processing as presented in this paper. Originality/value This paper uses a unique data set in a quasi-experimental setting in order to identify the characteristics of online information that users are attracted to. © Emerald Group Publishing Limited.