Rafet Aktaş

Rafet Aktaş

Auto-generated profile, based on publicly available information

Rafet Aktaş

Ankara Yıldırım Beyazit University, Department of Business Administration, Ankara, Türkiye

Research Focus & Metrics

Academic Career Length

2Years (2025-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
27 March 2025 in Financial Internet Quarterly
Verified
Journal Article
Open access
PDF file
CÖCansu Ergenç Özdaş
Cansu Ergenç Özdaş
RARafet Aktaş
Rafet Aktaş
This study examines the application of machine learning models to predict financial performance in various sectors, using data from 21 companies listed in the BIST100 index (2013-2023). The primary objective is to assess the potential of these models in improving financial forecast accuracy and to emphasize the need for transparent, explainable approaches in finance. A range of machine learning models, including Linear Regression, Ridge, Lasso, Decision Tree, Bagging, Random Forest, AdaBoost, Gradient Boosting (GBM), LightGBM, and XGBoost, were evaluated. Gradient Boosting emerged as the best-performing model, with ensemble methods generally demonstrating superior accuracy and stability compared to linear models. To enhance interpretability, SHAP (SHapley Additive exPlanations) values were utilized, identifying the most influential variables affecting predictions and providing insights into model behavior. Sector-based analyses further revealed differences in model performance and feature impacts, offering a granular understanding of financial dynamics across industries. The findings highlight the effectiveness of machine learning, particularly ensemble methods, in forecasting financial performance. The study underscores the importance of using explainable models in finance to build trust and support decision-making. By integrating advanced techniques with interpretability tools, this research contributes to financial technology, advancing the adoption of machine learning in data-driven investment strategies.

30 September 2025 in Economics and Business Review
Verified
Journal Article
Open access
PDF file
CÖCansu Ergenç Özdaş
Cansu Ergenç Özdaş
RARafet Aktaş
Rafet Aktaş
This study examines the Environmental, Social, and Governance (ESG) performance of S&P 500 companies using three clustering algorithms: K-Means, Gaussian Mixture Model, and Agglomerative Clustering. ESG scores from leading data providers are analysed to uncover sectoral patterns and performance trends. The findings indicate that technology and healthcare firms achieve the highest ESG scores, particularly in the governance and social dimensions, while the industrial and energy sectors face the greatest environmental challenges. Among the methods compared, K-Means demonstrates superior clustering performance by forming compact and well-separated ESG groups. These results offer a robust foundation for sector-specific ESG benchmarking, supporting investors and policymakers in identifying sustainability leaders, assessing risk, and targeting areas for improvement.

1 March 2025 in Review of Economic Perspectives
Verified
Journal Article
Open access
PDF file
CÖCansu Ergenç Özdaş
Cansu Ergenç Özdaş
RARafet Aktaş
Rafet Aktaş
The purpose of this study is to identify the most effective supervised machine learning models for predicting the financial performance of companies listed on the BIST100 index. In the rapidly evolving field of financial forecasting, machine learning techniques offer robust predictive capabilities. This research evaluates a range of supervised models, including Tree-Based Models (Decision Trees, Bagging, Random Forests, Adaboost, Gradient Boosting Machine (GBM), Light-GBM, XGBoost, CatBoost), Neural Network-based Models (Artificial Neural Networks (ANN), Convolutional Neural Networks (CNNs), Recurrent Neural Networks (RNNs), Long Short-Term Memory networks (LSTM)), and Instance-based Learning Models (K-Nearest Neighbors (KNN) and Support Vector Machines (SVM)). The models’ performance is assessed using comprehensive error metrics such as Mean Squared Error (MSE), Root Mean Squared Error (RMSE), Mean Absolute Error (MAE), Mean Absolute Percentage Error (MAPE), and relative Root Mean Squared Error (rRMSE). The findings reveal that no single machine learning model consistently outperforms others across all companies in the BIST100 index. However, models like XGBoost and Random Forests demonstrate strong and consistent performance, making them particularly effective for financial performance forecasting. Furthermore, deep learning models such as CNNs, RNNs, and LSTMs show promising results, especially for certain firms. The research highlights key insights for investors and financial analysts seeking to leverage machine learning for data-driven decision-making in the Turkish stock market. This study offers a unique contribution to the field by applying and comparing advanced machine learning techniques in the context of the BIST100 index. It provides actionable insights for improving financial prediction accuracy and offers a foundation for further research in other stock market contexts.

31 December 2025
Verified
Book Chapter
Closed access
RARafet Aktaş
Rafet Aktaş
CÖCansu Ergenç Özdaş
Cansu Ergenç Özdaş
ŞDŞevket Durmaz
Şevket Durmaz
This study investigates the integration of Environmental, Social, and Governance (ESG) metrics with traditional TFRS-based financial ratios to develop a comprehensive benchmarking framework for publicly listed firms in an emerging market context. Utilizing a unique panel dataset of BIST100 companies from 2014 to 2024, the research applies unsupervised machine learning methods—specifically K-Means, Agglomerative Clustering, and Gaussian Mixture Models—to classify firms according to their multidimensional performance profiles. The findings reveal significant heterogeneity in both financial and ESG dimensions across Turkish firms, with the inclusion of sustainability metrics fundamentally reshaping firm segmentation and cluster membership. Notably, a substantial number of firms are reclassified when ESG factors are incorporated, highlighting the material influence of sustainability on corporate benchmarking. Robustness checks using alternative clustering algorithms further validate the reliability of these results. The study contributes to the growing literature on sustainable finance by demonstrating that traditional financial metrics alone are insufficient for a holistic evaluation of corporate performance. The insights generated have important implications for investors, policymakers, and corporate leaders, emphasizing the need for integrated frameworks that account for both financial health and sustainability in corporate decision- making.

15 November 2026
Verified
Book Chapter
Closed access
CÖCansu Ergenç Özdaş
Cansu Ergenç Özdaş
ŞDŞevket Durmaz
Şevket Durmaz
RARafet Aktaş
Rafet Aktaş
This chapter examines whether family versus corporate ownership predicts ESG performance among BIST-100 firms over 2010–2024 using Refinitiv Eikon panel data. Overall ESG performance does not differ meaningfully between ownership types, and multivariate models with year and sector fixed effects confirm that ownership structure is not an independent driver of ESG variation once industry composition and time trends are accounted for. At the sub-pillar level, the only robust difference emerges in the environmental dimension, where family firms exhibit lower scores than corporate firms, while governance performance is essentially indistinguishable across groups. These findings challenge agency-theoretic expectations in Turkey’s institutional context and are consistent with regulatory isomorphism following post- 2014 SPK reforms that appear to have harmonised formal governance structures across ownership types. Importantly, the longitudinal evidence reveals a reversal over time: family firms move from underperformance in the early period to outperformance by the end of the sample, suggesting accelerated ESG capability development among large Turkish family conglomerates.

9 November 2026 in Corporate Social Responsibility and Environmental Management
Verified
Journal Article
Closed access
NANalan Akdoğan
Nalan Akdoğan
RARafet Aktaş
Rafet Aktaş
CÖCansu Ergenç Özdaş
Cansu Ergenç Özdaş