Search

With the developing technology, mobile payment systems have become increasingly popular. In the public transport industry, this system has convenient to the sector in terms of purchasing, using, carrying and storing tickets. One of the greatest challenges encountered in the mobile payment system in this sector is fraud. Fraud reduces customer satisfaction, reduces snow margins and causes severe costs for the company. Therefore, it is very important to detect and prevent fraudsters. This study is based on users using a real mobile ticketing application in USA/Kansas, a customer of Kentkart, which has a smart public transportation system. An automatic and intelligent detection system was developed using a machine learning algorithm to detect whether the users in question are fraudulent or not. For this system, the historical profiles of the variables that represent a user that the risky behavior are created. These profiles are classified using Random Forest, Support Vector Machines, Logistic Regression, K-Nearest Neighbor and Naive Bayes machine learning techniques and results are combined with simple ensemble learning methods. Users classified as frauds are automatically blacklisted in accordance with the company's management policy. Thus, the fraud costs that these users caused the company have been reduced.

It is a well-established fact that energy consumption and production, as the primary sources of greenhouse gases, contribute to climate change and global warming issues. The analysis and estimation of the factors that contribute to these harmful gases will be of great assistance in the development of policies to reduce carbon dioxide emissions. In addition to identifying the factors related to energy consumption and CO2 emissions, forecasting the variable of interest as accurately as possible has a key role in increasing the efficiency of energy strategies to be implemented. Unlike studies in the literature, this study not only forecasts the future value of energy consumption and CO2 emissions but also determines the relationship between the predictions and the influential variables by revealing the contribution of each variable to the prediction. For this purpose, the study proposes an interpretable forecasting framework based on values of the Shapley additive explanation (SHAP) to provide a simpler explanation of machine learning (ML) models in forecasting energy consumption and CO2 emissions. The results obtained show that the total electricity generation from different energy sources is found to be the most important variable interacting positively with both energy consumption and CO2 emissions. Also, the influence of the predictors on projections made before and after COVID-19 has changed dramatically. The proposed method may assist policymakers in making future energy investments and establishing energy laws more accurately and efficiently as it explains the drivers of the forecasts.

Günümüzde kripto para birimlerinin önemi gittikçe artmaktadır. Kripto para birimleri sanal oyun platformlarında kullanılırken, şu an pek çok kurum ve kuruluş tarafından ödeme aracı olarak kullanılmaktadır. Güvenlik risklerine karşı blockchain (Blok Zinciri) adı verilen algoritması ile üretimi sağlanmaktadır. Kripto para fiyatlarının doğru olarak tahmin edilmesi yatırımcı ve karar vericiler açısından büyük önem taşımaktadır. Bu çalışma kapsamında en çok kullanılan dört kripto para birimine (Bitcoin, Ethereum, Ripple, Litecoin) ait fiyat değerleri tahmin edilmiştir. Çoklu kırılma testinden yararlanılarak her seriye ait kırılmalar belirlenerek analiz genişletilmiştir. Ele alınan sanal para değerlerini doğru bir şekilde tahmin etmek amacıyla hem klasik zaman serisi modellerinden hem de üç farklı tür yapay sinir ağı modelinden faydalanılmıştır. Ayrıca elde edilen tahminler üzerinde basit birleştirilme teknikleri uygulanmıştır. Rassal yürüyüşün egemen olduğu bu seriler arasından, özellikle işlem hacmi ve bilinilirliği en fazla olan Bitcoin sanal parasında rassal yürüyüş modelinden daha iyi sonuçlar elde edildiği gözlemlenmiştir.

When the literature regarding applications of neural networks is investigated, it appears that a substantial issue is what size the training data should be when modelling a time series through neural networks. The aim of this paper is to determine the size of training data to be used to construct a forecasting model via a multiple-breakpoint test and compare its performance with two general methods, namely, using all available data and using just two years of data. Furthermore, the importance of the selection of the final neural network model is investigated in detail. The results obtained from daily crude oil prices indicate that the data from the last structural change lead to simpler architectures of neural networks and have an advantage in reaching more accurate forecasts in terms of MAE value. In addition, the statistical tests show that there is a statistically significant interaction between data size and stopping rule.

In today’s competitive global economy, businesses must adjust themselves constantly to ever-changing markets. Therefore, predicting future events in the marketplace is crucial to the maintenance of successful business activities. In this study, sales forecasts for a global furniture retailer operating in Turkey were made using state space models, ARIMA and ARFIMA models, neural networks, and Adaptive Network-based Fuzzy Inference System (ANFIS). Also, the forecasting performances of some widely used combining methods were evaluated by comparison with the weekly sales data for ten products. According to the best of our knowledge, this study is the first time that the recently developed state space models, also called ETS (Error-Trend-Seasonal) models, and the ANFIS model have been tested within combining methods for forecasting retail sales. Analysis of the results of the single models in isolation indicated that none of them outperformed all the others across all the time series investigated. However, the empirical results suggested that most of the combined forecasts examined could achieve statistically significant increases in forecasting accuracy compared with individual models and with the forecasts generated by the company’s current system.

Türkiye gerek coğrafik konumu gerekse sahip olduğu farklı iklim özellikleri nedeniyle büyük bir bitki çeşit zenginliğine sahip ülkelerdendir. Türkiye üzümsü meyvelerin anavatanı, kültür çeşitlerinin oluşum ve gelişim merkezi, önemli gen kaynaklarına sahip olan ülkelerden biridir. Üzümsü meyvelerin (çilek, ahududu, böğürtlen, dut kivi vb.) yetiştiriciliği son yıllarda ülkemizde üretimi artarak ülke ekonomisine katkı sağlamaktadır. Özellikle insan sağlığı açısında önemli rolleri olan bu üzümsü meyveler; aroması, içerdikleri organik asitler, mineraller ve vitaminler bakımından çok zengin olması ve değişik tüketim şekillerinin (meyve suyu, reçel, pasta, dondurma gibi) bulunması, üretime bağlı olarak tüketimi de artırmaktadır. Son yıllarda dondurma sanayisinde aroma ve çeşni maddeleri olarak önemli bir hammadde olması nedeniyle de ülke ekonomisine önemli katkı sağlamaktadır. Avrupa ülkelerinde ve Ülkemizde dondurma üretiminde özellikle meyveli dondurma üretimi önceki yıllara göre artış sağlayarak daha fazla talep görmüştür. Ülkemizde ise son yıllarda farklı meyve aromalı dondurma üretilmeye başlanmış olup bu ürünlerin tüketimi giderek artış göstererek yeni Pazar haline gelmiş hem ithalatta hem de ihracatta talep gören ve yüksek fiyatta satılan ürünler arasında yer almaya başlamıştır. Bu makalede üzümsü meyvelerin dondurma sanayisi açısından önemi değerlendirilmiştir fruit ice cream production is demand than by an increase compared to previous years. In our country, different fruit flavored ice cream has begun to be produced in recent years increased consumption of which has gradually become a new market that both exports and imports saw demand has begun to take place between the products sold at high prices. This article discussed in the importance of berries ice cream industry

Gunumuzde yapilan para talebinin modellenmesine iliskin literaturu inceledigimizde, modelleme yontemi olarak cogunlukla kointegrasyon testlerinin kullanilmis oldugu ve bu testlerden Engle-Granger (1987) yani sira Johansen-Juselius (1990) tarafindan onerilen kointegrasyon tekniklerinin bircok arastirmaci tarafindan cogu ulkenin para talebinin modellen-mesinde uygulandigi gorulmektedir. Para politikasinin uygulanmasi asamasinda politik tutumlarin gerlendirilmesinin yani sira para politikasi kapsaminda alinacak kararlar, para ve diger makroekonomik degiskenler arasindaki iliskinin incelen-mesine bagli oldugundan, farkli fonksiyonel iliskileri degerlendirmemize izin veren farkli modelleme ontemlerinin ele alinarak degerlendirilmesi onem kazanmaktadir. Bu calismanin amaci, literaturde yaygin bir bicimde kullanilan ekonometrik modelleme yontemine karsilik alternatif bir yontem ortaya koymaktir. Bu nedenle, calismada kointegrasyon yontemlerinden biri olan Engle-Granger (1987) tarafindan onerilen esbutunlesme testi ile bulanik modelleme yontemlerinden bulanik Takagi-Sugeno modeli kullanilip, iki yontem Turkiye’nin para talebi fonksiyonunun incelenmesi asamasinda karsilastirilarak yorumlanmýþtýr.

Günümüzde yapılan para talebinin modellenmesine ilişkin literatürü incelediğimizde, modelleme yöntemi olarak çoğunlukla kointegrasyon testlerinin kullanılmış olduğu ve bu testlerden Engle-Granger (1987) yanı sıra Johansen-Juselius (1990) tarafından önerilen kointegrasyon tekniklerinin birçok araştırmacı tarafından çoğu ülkenin para talebinin modellenmesinde uygulandığı görülmektedir. Para politikasının uygulanması aşamasında politik tutumların değerlendirilmesinin yanı sıra para politikası kapsamında alınacak kararlar, para ve diğer makroekonomik değişkenler arasındaki ilişkinin incelenmesine bağlı olduğundan, farklı fonksiyonel ilişkileri değerlendirmemize izin veren farklı modelleme yöntemlerinin ele alınarak değerlendirilmesi önem kazanmaktadır. Bu çalışmanın amacı, literatürde yaygın bir biçimde kullanılan ekonometrik modelleme yöntemine karşılık alternatif bir yöntem ortaya koymaktır. Bu nedenle, çalışmada kointegrasyon yöntemlerinden biri olan Engle-Granger (1987) tarafından önerilen eşbütünleşme testi ile bulanık modelleme yöntemlerinden bulanık Takagi-Sugeno modeli kullanılıp, iki yöntem Türkiye’nin para talebi fonksiyonunun incelenmesi aşamasında karşılaştırılarak yorumlanmıştır, At the present day, we investigate literature about Money demand, we can see that cointegration techniques are used in most of studies. Money demand econometric modelling techniques are used by a great number of researchers. Mostly, cointegration techniques are being used as estimating methods for any money demand function.Cointegration techniques which were proposed by Engle-Granger (1987) and Johansen-Juselius (1990) have been used for modelling countries’ money demand function by researchers. In stage of application of monetary policy, when assessment of policy stance as well as monetary policy decisions depend on the relationship between money and the other macroeconomic variables, different methods which allows for different functional relations are being important. The purpose of this study is proposing an alternative method, instead of econometric modelling methods which have been used widely in literature. Thus, in this study, cointegration test which was proposed by EngleGranger (1987) and fuzzy Takagi-Sugeno method are used to estimate Turkey’s money demand function and two methods are compared and consequently,the results are interpreted

Forecasting inflation accurately in a data-rich environment is a challenging task and an active research field which still contains various unanswered methodological questions. One of them is how to find and extract the information with the most predictive power for a variable of interest when there are many highly correlated predictors, as in the inflation forecasting problem. Traditionally, factor models have been used to tackle this problem. However, a few recent studies have revealed that machine learning (ML) models such as random forests may offer some valuable solutions to the problem. This study encourages greater use of ML models with or without factor models by replacing the functional form of the forecast equation in a factor model with ML models or directly employing them with several feature selection techniques. This study adds new tree-based models to the analysis in the light of the recent findings in the literature. Moreover, it proposes the integration of feature selection techniques with Shapley values to find out concise explanations of the inflation predictions. The results obtained by a comprehensive set of experiments in an emerging country, Turkey, facing a high degree of volatility and uncertainty, indicate that tree-based ensemble models can be advantageous by providing better accuracy together with explainable predictions.

Machine learning techniques have been used frequently for volatility forecasting. However, previous studies have built these hybrid models in a form of a first-order GARCH(1,1) process by following general use for GARCH models. But the way of estimating parameters for GARCH and machine learning models differs considerably. Hence, we have investigated the effect of different model orders of the GARCH process on the volatility forecasts of Bitcoin obtained by the four most used machine learning models. Furthermore, we have proposed a stacking ensemble methodology based on GARCH hybrid models to improve the results further. The proposed stacking ensemble methodology utilizes the techniques of feature selection and feature extraction to reduce the dimension of the predictors before meta-learning. The results show that using higher model orders increases the accuracy of volatility forecasts for hybrid GARCH models. Also, the proposed stacking ensemble with LASSO produces forecasts superior to almost all hybrid models and better than the ordinary stacking ensemble.

WOS: 000442902500007, Background: Smoking cessation is potentially the most effective secondary prevention measure and improves prognosis after acute ST-segment elevation myocardial infarction (STEMI), but more than half of the patients continue to smoke after STEMI. The awareness of the disease's severity and the short hospital stay at the index STEMI have been found to be associated with persistent smoking after STEMI. Objective: To assess whether the paradoxical relationship between smoking quitting rates and health-related quality of life (QOL) scores in STEMI patients undergoing primary percutaneous intervention (pPCI) by radial (RA) versus femoral approach (FA). Methods: Our population is represented by 138 STEMI patients undergoing pPCI by FA or RA. The smoking cessation rates and QOL scores were evaluated. Results: Patients at RA group (46 patients, 57 +/- 9 years, 87% male) had a higher European Quality of Life-5 Dimensions (EQ-5D) index score at post-PCI first week compared to FA group (92 patients, 57 +/- 8 years, 75% male) [FA: median 0.81 (0.22) vs. RA: 1 (0.22), p = 0.042], although it was similar at baseline [FA: median 1 (0) vs. RA: 1 (0), p = 0.992]. Total hospital length of stay [RA: median 3 (1) day vs. FA: 4 (1), p < 0.001] was significantly reduced in the RA group. Whereas the smoking cessation rates at 1-year post-discharge were 41% in RA group, it was 67% in FA group (p = 0.003). Female sex, pain-to-door time and RA during p-PCI were independent predictors of continued smoking after STEMI. Conclusion: This study shows that the smoking cessation was lower in RA group compared to FA group. The more comfortable conditions of STEMI management related to RA may cause a lower awareness of the disease severity and lower motivation to quit smoking. Therefore, it is important to inquire about smoking status at each clinical encounter, particularly in patients undergoing pPCI by the radial approach. (c) 2018 The Czech Society of Cardiology. Published by Elsevier Sp. z o.o. All rights reserved.