Some automobile insurance companies use computerized auto-detection systems to expedite claims payment decisions for insured vehicles. Claims suspected of fraud are evaluated using empirical data from previously investigated claims. The main objective of this manuscript is to demonstrate a novel data processing system and its potential for use in data classification. The data processing approach was used to develop a machine learning-based sentiment classification model to describe property damage fraud in vehicle accidents and the indicators of fraudulent claims. To this end, Singular Value Decomposition-based components and correlation-based composite variables were created. Machine learning models were then developed, with predictors and composite variables selected based on standard feature selection procedures. Five machine learning models were used: Boosted Trees, Classification and Regression Trees, Random Forests, Artificial Neural Networks, and Support Vector Machines. For all models, the models with composite variables achieved higher accuracy rates, and among these models, the artificial neural network was the model with the highest accuracy performance at 76.56%.
Yatırım bankaları, finansal araçları kullanarak sağladıkları kaynakları yatırıma dönüştürebilme yeteneğine sahiptirler. Sermaye piyasalarında işlem gören bu bankalar, özel işletmelerin ve devletlerin uzun dönemli fon taleplerini karşılayabilmek amacıyla, tahvil benzeri menkul kıymetleri piyasalara arz edebilecek yetki ile donatılmışlardır. Tahvil, uygun şartlarda finansman sağlamak amacı ile ihraç edilen ve ihracatçısına borçlanma yoluyla fon sağlayan finansal araçlardan biridir. Bu çalışmanın temel motivasyonu, on yıllık tahvil faizleri ile BIST 100’de işlem gören yatırım bankalarının hisse değerleri arasında bir ilişki olup olmadığıdır. Çalışmada kullanılan veri seti 2015 – 2020 yılları arası BIST 100’de işlem gören Türkiye Kalkınma ve Yatırım Bankası Anonim Şirketi (A.Ş.), GSD Yatırım Bankası A.Ş., Merrill Lynch Yatırım Bank A.Ş. ve Credit Agricole Yatırım Bankası Türk A.Ş. hisse değerleri ile Türkiye on yıllık tahvil verimi oranlarından oluşmaktadır. Çalışmanın amacı doğrultusunda lineer regresyon modellemesi, korelasyon ve gama (γ) ilişki katsayısı yöntemleri uygulanmıştır. Yapılan değerlendirme sonucu yatırım bankalarının hisse değerleri ile Türkiye on yıllık tahvil verim oranları arasında istatistiksel olarak 0.05 güven düzeyinde anlamlı bir ilişki saptanmıştır.
Tarihin her döneminde önemli bir ticaret ve finans aracı olan altın, günümüzde de önemli bir yatırım ve rezerv aracı olarak değerlendirilmeye devam etmektedir. Altın fiyatlarındaki değişim ve altına dayalı işlem hacminin büyüklüğü ile borsa ilişkisi çalışmanın temel araştırma konusunu oluşturmaktadır. Çalışmanın veri seti; 1988-2020 yılları arasındaki verilerden oluşmaktadır. Altın fiyatları ve BIST 100 endeksi arasındaki ilişkinin varlığı, yönü ve boyutu çalışma kapsamında incelenmiştir. Yapay sinir ağları (YSA) yöntemi veri analizinde kullanılmıştır. Değişkenler arasındaki nedensellik ilişkileri doğrusal ve olasılık tabanlı olarak iki aşamada incelenmiştir. Doğrusal ilişkinin %52 ve olasılığa dayalı ilişkinin ise %70 üzerinde olduğu gözlemlenmiştir. Bu amaçla, 1988-2019 dönemine ait kontrol veri üzerine geliştirilen model, 2020 yılına ait veri üzerinde test edilmiştir. İlgili model %54 üzerinde bir doğruluk oranı sağlamıştır.
Spotify is the world's largest online music streaming platform that offers a tremendous variety of playlists based on listeners' listening patterns. This paper proposes that music preference is highly associated with emotional state, and music is an emotion regulator tool during the pandemic in the Philippines. Well-known machine learning methods (i.e., classification and regression trees, boosted trees, random forests, Support Vector Machines, and Artificial Neural Networks) in combination with 5-fold cross-validation are used to classify periods in proportion to the severity of the pandemic and people's musical preferences. Daily official covid-19 statistics and Spotify data are used as main variables during the algorithms' learning processes. SVM outperformed the other alternatives in average accuracy rate by achieving a 98.01% accuracy rate. Additionally, ANN outperformed the other alternatives in terms of accuracy achieved specifically in a single model, achieving an accuracy rate of 99.30%. Moreover, the variables with the largest (absolute) change (in descending order) are ST_Intrumentalness (26,45%), ST_Acousticness (19,03%), ST_Liveness (16,11%), and ST_Valence (14,1%). Given pandemics-related stress and cancelation of concerts, it would be an intuitive expectation that the variables ST_Valence (musical positivity) and ST_Liveness would change at such a rate. The results confirm that musical preference is a significant indicator of emotional state.
The level and direction of the relationship between WT (World Trade) and TFT (Turkey Foreign Trade) statistically analysed in this study. For this purpose, in addition to some descriptive statistics, correlation and regression algorithms were utilized to observe the relationship. In addition, point, box and line graphs were used to observe the relative distributions of WT and TFT. According to the results, there is a 99.258 % correlation between WT and TFT. In addition, a linear regression model was designed in which TFT was determined as dependent and WT was determined as independent variable. The model is statistically significant at a confidence level of 0.05 and R, R-square and adj.-R-square explanatory ability rates of the model are 99.2 %, 98.5 % and 98.4 %, respectively. The scatter-plot shows that the binary value points are generally distributed around the linear line. In the box-plot, it is observed that WT has a wider range than TFT, but generally both variables have a symmetrical distribution. Finally, the line graph shows the ordered and consequetive 38-year distribution of both variables. Although the distribution is generally parallel to each other, the upward movement of WT has been observed to be sharper and accelerated in the last 10 years. All these results indicate that TFT has a very strong level of relationship with WT and that WT can be used as an important parameter in understanding TFT.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
customersupport@researchsolutions.com
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
This site is protected by reCAPTCHA and the Google Privacy Policy and Terms of Service apply.
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.