İlgi alanları

Sürdürülebilir Kalkınma Amaçları

• 3
• 2
• 1
• 1
• 1

• MakaleYalnız künye2026Scopus SJRQ2/r/bayburt/14320
  Analyzing IPO Performance on Borsa Istanbul: A Hybrid Econometric and Machine Learning Framework (2013-2025)

  Ayberkin, Doruk

  This study examines the determinants of the performance of initial public offerings (IPOs) conducted by 237 firms across 38 sectors on the Istanbul Stock Exchange between 2013 and 2025, using a hybrid analytical framework. To analyze the impact of sector characteristics, firm-level financial indicators, supply structure, and market timing on the returns of USD-denominated IPOs, this study combines heteroskedasticity-resistant ordinary least squares (OLS) regression with tree-based ensemble machine learning algorithms (random forest, XGBoost) and benchmark models (support vector regression, artificial neural network). The distributional characteristics of returns from IPOs highlight the use of nonlinear modelling techniques characterized by high positive skewness (5.12) and excess kurtosis (45.24). Our findings reveal significant sectoral heterogeneity. According to the findings, the Financial Services and Fisheries sectors showed statistically significant superior performance, while the Metal Mining, Insurance, and Construction sectors underperformed. Transportation and Storage exhibited the highest point estimate but did not reach conventional significance levels. The XGBoost machine learning model, with an R 2 of 0.869 and a mean absolute error (MAE) of 17.87, achieved superior single-split prediction accuracy compared to the OLS method, which yielded an R 2 of 0.220. However, cross-validation analyses indicated that all models exhibited limited out-of-sample generalizability (best CV R 2 = 0.04). The Diebold-Mariano test, conducted to compare prediction performance, confirmed that the artificial neural network (ANN) model provided a statistically significant improvement over the OLS method (DM = 2.121, p = 0.034). The SHAP value analysis used in the models reveals how each feature affects the final predictions, the relative importance of each feature, and the model's dependence on feature interactions. It identifies the IPO price (USD), the USD/TRY exchange rate, and the size of the supply as the most effective estimators with economically significant nonlinear interactions. The study aims to demonstrate the comparative advantages and limitations of ensemble learning under abnormal financial data conditions by presenting detailed sectoral evidence across 38 sectors. In this way, it aims to contribute to the IPO literature in emerging market economies by offering viable policy recommendations for investors, issuers, and regulators in Turkish capital markets.

  • 
  İncele
• MakaleYayıncıda açık erişim2026Scopus SJRQ2/r/bayburt/10955
  A pilot pre–post study of a scaffolded AI chatbot for financial literacy education among university students

  Ayberkin, Doruk; Yirik, Emirhan

  This pilot study examines pre- to post-test changes in university students’ financial literacy knowledge following a one-week student-directed learning period using a pedagogically scaffolded GPT‑4o Application Programming Interface (API) chatbot. Guided by constructivist learning theory [29], the immediate feedback model [10], and self-determination theory [24], the study employed a single-group pre-test–post-test quantitative design with 32 undergraduate students at a Turkish public university. The primary outcome was financial literacy knowledge, measured with 32 factual statements rated on a six-point agreement scale and keyed against correct responses, across six subscales (Basic Economics and Finance, Individual Banking, Retirement and Insurance, Financial Statements, Investment, and Tax and Legislation). Five objective multiple-choice items served as a limited, complementary performance check. Paired-samples t-tests were used for normally distributed difference scores, and Wilcoxon signed-rank tests for non-normal difference scores; six subscale comparisons were interpreted using Holm-adjusted p values. The overall score increased from pre-test to post-test, with a large standardized mean change (d = 1.09, 95% CI [0.64, 1.52]), and all six exploratory subscale comparisons remained statistically significant after Holm adjustment. Objective item performance also increased on several items, including the compound-interest item (3.1% to 81.2%). However, because the design included no control or comparison group, identical objective items were repeated, and chatbot interaction logs were not systematically recorded, the observed changes cannot be causally attributed to the chatbot. The findings therefore provide preliminary, uncontrolled evidence that warrants testing in controlled studies rather than evidence of intervention effectiveness.

  • 
  İncele
• MakaleAçık Erişim2026Scopus SJRQ4/r/bayburt/10924
  Experience-Based Decentralized Marketing and Advertising (Ex-Mad): A Blockchain Framework for Transparent and Fair Digital Campaigns

  Ayberkin, Doruk; Özen, Üstün

  The contemporary digital advertising ecosystem faces critical technical and operational challenges, primarily driven by centralized intermediaries, data opacity, and privacy vulnerabilities. To address these systemic issues, this paper proposes "Ex-Mad," a decentralized architecture leveraging blockchain technology and the Interplanetary File System (IPFS). The proposed framework integrates three core architectural layers: the user entities (advertisers and end-users), the blockchain ledger for immutable transaction recording, and IPFS for distributed content storage. Unlike traditional centralized models, Ex-Mad utilizes smart contracts to automate campaign management and enforce trustless interactions, ensuring verifiable reward distribution based on user contribution without third-party validation. Furthermore, the integration of IPFS optimizes on-chain storage costs by handling large media files off-chain while maintaining data integrity through cryptographic hashes. The system design enhances auditability through a tamper-proof ledger, eliminates single points of failure, and provides a technically robust alternative to current ad-tech intermediaries. This study demonstrates how the proposed architecture improves system efficiency, reliability, and cost-effectiveness in the digital advertising domain.

  • 
  İncele
• MakaleAçık Erişim2025/r/bayburt/16232
  TarBIoT KDS: Akıllı Tarım Uygulamaları için Blokzincir ve IoT teknolojileri ile Gerçek zamanlı Karar Destek Sistemi Tasarımı

  Ayberkin, Doruk

  Bu çalışma, tarım sektöründeki küresel zorlukları ele almak için yenilikçi bir yaklaşım sunmaktadır. Araştırma, blokzincir ve Nesnelerin İnterneti (IoT) teknolojilerini entegre ederek, tarımsal verilerin toplanması, güvenli bir şekilde depolanması ve analiz edilmesi için kapsamlı bir sistem önermektedir. TarBIoT olarak adlandırılan bu sistem, çeşitli sensörlerden elde edilen toprak ve iklim verilerini gerçek zamanlı olarak işleyerek, çiftçilere ve diğer paydaşlara yönelik bir karar destek mekanizması sunmaktadır. Sistemin temel bileşenleri arasında IoT sensör ağı, blokzincir altyapısı, veri işleme ve analiz modülü ile karar destek sistemi bulunmaktadır. Bu entegre yapı, tarımsal üretimde verimliliği artırma, kaynakları optimize etme ve çevresel sürdürebilirliği destekleme potansiyeli taşımaktadır. Blokzincir teknolojisinin sağladığı şeffaflık ve güvenilirlik, verilerin tüm paydaşlar arasında güvenli bir şekilde paylaşılmasına olanak tanırken, karar destek sistemi, bu verileri anlamlı ve uygulanabilir bilgilere dönüştürmektedir. Çalışma, önerilen sistemin simülasyonunu gerçekleştirerek, su seviyesi, nem oranı, toprak pH değeri gibi kritik tarımsal parametrelerin izlenmesi ve analiz edilmesindeki etkinliğini değerlendirmektedir. Sonuçlar, TarBIoT sisteminin, akıllı tarım uygulamalarının geliştirilmesinde, gıda güvenliğinin artırılmasında ve sürdürülebilir tarım pratiklerinin yaygınlaştırılmasında önemli bir rol oynayabileceğini göstermektedir. Bu araştırma, tarım sektöründeki dijital dönüşümü hızlandırma ve veri odaklı tarım uygulamalarını yaygınlaştırma potansiyeli taşımaktadır.

  • 
  • 
  • 
  İncele
• MakaleAçık Erişim2025/r/bayburt/16124
  The Effectiveness of Advanced Machine Learning Models in IQ Prediction in the Context of Education, Health, and Socioeconomic Indicators

  Sebetci, Özel; Ayberkin, Doruk

  This study investigates the effectiveness of advanced machine learning models in predicting IQ levels using a diverse set of socioeconomic and health indicators from global databases such as WHO, the World Bank, and United Nations organizations. The research employs various algorithms, including Linear Regression, Random Forest, Gradient Boosting, Support Vector Machines, Ridge and Lasso Regressions, XGBoost, LightGBM, and a Stacking Regressor to capture both linear and non-linear relationships. Evaluation metrics such as Mean Absolute Error (MAE), Root Mean Square Error (RMSE), and R-squared (R²) reveal that LightGBM and Stacking Regressor models excel in accuracy and generalization. The study highlights the trade-off between model interpretability and predictive power, emphasizing that simpler models offer greater transparency. In contrast, more complex models successfully capture intricate interactions among education, health, and economic factors. The findings provide valuable insights for policymakers and researchers, suggesting that machine learning approaches can significantly enhance understanding of the determinants of IQ and aid in developing targeted strategies in education and social policy.

  • 
  İncele
• BildiriAçık Erişim2017/r/bayburt/12299
  Relations of attention and meditation level with learning in engineering education

  Ülker, Büsra; Tabakcioǧlu, Mehmet Bariş; Çizmeci, Hüseyin; Ayberkin, Doruk

  Neurons use electricity in order to communicate to each other. Due to numerous signals sent by neurons, there are oodles of electrical activity in the brain. Sensitive equipment like electroencephalogram (EEG) biosensor perceives the brainwaves emanated from neurons. Beta waves are responsible for problem solving or decision making and associated with attention. Alpha waves are associated with now and meditation. Neurosky EEG biosensor perceives the brainwaves and transforms these brainwaves into attention and meditation values. In this study, Neurosky EEG biosensor is used for measuring the attention and meditation levels of students. A program is developed in C# medium. The developed program records raw brainwave data, attention and meditation average while the students are studying. As the attention and meditation levels are high, the students learn the subjects in the course. If predetermined meditation and attention level are not caught, the developed program does not give permission to pass to another subject. Because of that the students have less meditation and attention average than the predetermined value; they get fewer grades in the exam.

  • 
  AtıfScopus16·OpenAlex16

  İncele
• MakaleYalnız künye2015/r/bayburt/15499
  Işın İzleme Tekniğinin Radyo Dalga Yayılım Modellerinde Kullanılması

  Tabakcıoğlu, Mehmet Barış; Ayberkin, Doruk

  Daha güvenilir, zaman açısından verimli ve kesinliği yüksek elektromanyetik dalga  şiddeti kestirimi yapmak için birçok yayılım modeli geliştirilmiştir. Bu modeller nümerik ve ışın izleme tekniği tabanlı olmak üzere iki kısımdır. Nümerik modellerin hesaplama zamanı ve kesinliği yüksektir. Buna karşın ışın izleme tekniği tabanlı modellerin hesaplama süresi daha kısadır. Vericiden çıkan ve alıcıda sonlanan tüm ışınların tespit edilmesi alıcı üzerindeki bağıl yol kaybının doğru hesaplanması için çok önemlidir. Bu çalışmada kısaca bazı yayılım modelleri hakkında bilgi verildikten sonra ışın izleme tekniği yazılımı açıklanacaktır ve karşılaştırmalar yapılacaktır.  

  İncele
• BildiriÖn baskısı açık2015/r/bayburt/14483
  Application of of Ray Tracing Technique into S-UTD-CH Model

  Tabakcioglu, Mehmet Baris; Ayberkin, Doruk

  To make higher accuracy predictions having less computation complexity, lower computation time, a lot of electromagnetic wave propagation models are developed. These models are classified into two classes, ray tracing based and numerical models. Computation complexity, computation time and accuracy of prediction of numerical model are high. On the contrary, computation complexity and computation time of ray tracing based model is lower. There is a tradeoff between computation time and accuracy. To predict the relative path loss at the receiver accurately, all ray paths have to be determined. In this study, after giving some brief information about some ray tracing based propagation models ray tracing software will be explained.

  AtıfWoS1

  İncele
• BildiriÖn baskısı açık2015/r/bayburt/14387
  Building Parameter Analysis with S-UTD-CH model in Multiple Diffraction

  Tabakcioglu, Mehmet Baris; Ayberkin, Doruk

  Electromagnetic wave propagation models are used in radio planning tool and coverage prediction. These models are based on ray tracing technique or numerical. Slope UTD with convex hull model is a model which has less computation time, higher accuracy of prediction and based on ray tracing technique. S-UTD-CH model is used in multiple diffraction due to that this model gives more accurate results in less computation time. Obstacles can be modelled as knife edge, wedge or cylinder in ultra-high frequencies. inner angle, structure type and relative permittivity constant and conductivity of obstacle and polarization type of electromagnetic wave change the relative path loss at the receiver. In the study, how building parameter changes the relative path loss is discussed.

  İncele
• BildiriYalnız künye2014/r/bayburt/13940
  Application of S-UTD-CH model into multiple diffraction scenarios at 900MHz

  Tabakcioglu, Mehmet Baris; Ayberkin, Doruk

  In this study, propagation prediction models based on ray tracing in coverage estimation for broadcasting systems are compared with respect to computation time and accuracy. Uniform Theory of Diffraction (UTD), Slope Diffraction (S-UTD) and Slope UTD with Convex Hull (S-UTD-CH) models are compared for computation time and propagation path loss. Moreover in this study, effects of transmitter height to relative path loss at the receiver are analyzed. S-UTD-CH model is optimum model with respect to computation time and relative path loss.

  İncele