İşletme Bölümü

Permanent URI for this communityhttps://hdl.handle.net/20.500.12416/24

Browse

Now showing 1 - 4 of 4

Detecting stock-price manipulation in an emerging market: The case of Turkey
(Pergamon-Elsevier Science LTD, 2009) Öğüt, Hulusi; Doğanay, M. Mete; Aktaş, Ramazan; 112010; 1109
This paper aims to develop methods that are capable of detecting manipulation in the Istanbul Stock Exchange. We take the difference between manipulated stock's and index's average daily return, average daily change in trading volume and average daily volatility and used these statistics as explanatory variables. The data in post-manipulation and pre-manipulation periods are used as non-manipulated instances while the data in the manipulation period are used as manipulated instances. Test performance of classification accuracy, sensitivity and specificity statistics for Artificial Neural Networks (ANN) and Support Vector Machine (SVM) are compared with the results of discriminant analysis and logistics regression (logit). We found that the data mining techniques (ANN and SVM) are better suited to detect stock-price manipulation than multivariate statistical techniques (discriminant analysis, logistics regression) as the performances of the data mining techniques in terms of total classification accuracy and sensitivity statistics are better than those of multivariate techniques. We also found that unit change in difference between average daily return of manipulated stock and the index has the largest effect while unit change in difference between average daily change in trading volume of manipulated stock and index has the least effect on multivariate classifiers' decision functions
Increasing accuracy of two-class pattern recognition with enhanced fuzzy functions
(Pergamon-Elsevier Science Ltd, 2009) Doğanay, Mehmet Mete; Türkşen, İsmail Burhan; Aktaş, Ramazan; Doğanay, Mehmet Mete; Ceylan, Nildağ Başak; 122648; 1109; 112010; 108611
In building an approximate fuzzy classifier system, significant effort is laid oil estimation and fine tuning of fuzzy sets. However, in such systems little thought is given to the way in which membership functions are combined within fuzzy rules. In this paper, a robust method, improved fuzzy classifier functions (IFCF) design is proposed for two-class pattern recognition problems. A supervised hybrid improved fuzzy Clustering for classification (IFC-C) algorithm is implemented for structure identification. IFC-C algorithm is based oil it dual optimization method, which yields simultaneous estimates of the parameters of (c-classification functions together with fuzzy c partitioning of dataset based oil a distance measure. The merit of novel IFCF is that the information oil natural grouping of data samples i.e., the membership values, are utilized as additional predictors of each fuzzy classifier function to improve accuracy of system model. Improved fuzzy classifier functions are approximated using statistical and soft computing approaches. A new semi-non-parametric inference mechanism is implemented for reasoning. The experimental results Of the new modeling approach indicate that the new IFCF is it promising method for two-class pattern recognition problems
Prediction of bank financial strength ratings: the case of Turkey
(Elsevier Science BV, 2012) Öğüt, Hulusi; Doğanay, M. Mete; Ceylan, Nildağ Başak; Aktaş, Ramazan; 112010; 108611; 1109
Bank financial strength ratings have gained widespread popularity especially after the recent financial turmoil. Rating agencies were criticized because of their ratings and failure to predict the bankruptcy of the banks. Based on this observation, we investigate whether the forecast of the rating of bank's financial strength using publicly available data is consistent with those of the credit rating agency. We use the data of Turkish banks for this investigation. We take a country-specific approach because previous studies found that proxies used for environmental factors (political, economic, and financial risk of the country) did not have any explanatory power and it is hard to find international data for other important factors such as franchise value, concentration, and efficiency. We use two popular multivariate statistical techniques (multiple discriminant analysis and ordered logistic regression) to estimate a suitable model and we compare their performances with those of two mostly used data mining techniques (Support Vector Machine and Artificial Neural Network). Our results suggest that our predictions are consistent with those of Moody's financial strength rating in general.. The important factors in rating are found to be profitability (measured by return on equity), efficient use of resources, and funding the businesses and the households instead of the government that shows efficient placement of the funds.
Prediction of financial information manipulation by using support vector machine and probabilistic neural network
(Pergamon-Elsevier Science LTD, 2009) Öğüt, Hulusi; Aktaş, Ramazan; Alp, Ali; Doğanay, M. Mete; 1109; 6974; 112010
Different methods have been used to predict financial information manipulation that can be defined as the distortion of the information in the financial statements. The purpose of this paper is to predict financial information manipulation by using support vector machine (SVM) and probabilistic neural network (PNN). A number of financial ratios are used as explanatory variables. Test performance of classification accuracy, sensitivity and specificity statistics for PNN and SVM are compared with the results of discriminant analysis, logistics regression (logit), and probit classifiers, which have been used in other studies. We have found that the performance of SVM and PNN are higher than that of the other classifiers analyzed before. Thus, both classifiers can be used as automated decision support system for the detection of financial information manipulation.

Browse

Browsing İşletme Bölümü by Author "1109"