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.
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.
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
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.
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.