MBMahmut Bağcı

Mahmut Bağcı

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article

Previous Organizations / Institutes

The organizations / institutes from the scholar's other articles in the past ten years


Mahmut Bağcı has a total of 19 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    Bitcoin as an econometric tool for asset co-movement: the relation index

    by José Pedro Ramos-Requena, Mahmut Bağcı

    This study proposes a methodological strategy composed of econometric techniques and time series modelling to analyse the dynamic asynchrony between Bitcoin and a basket of traditional sustainable financial assets and emerging markets over a 10-year period marked by major economic and financial changes. The centrepiece of this proposal is the Relation Index that combines vector autoregression and detrended cross-correlation analysis to capture linear and nonlinear dependencies, causality, and time-scale sensitive correlations. Thus, this research fills existing gaps in understanding cross-market interdependencies by integrating cryptocurrencies, sustainability indices, and emerging economies into a rigorous multivariate time series framework. Sustainability indices, emerging markets and Bitcoin have shown a growing correlation since 2020, with both interest rates and Bitcoin having strong autoregressive components. The findings indicate that emerging market equities have undergone a structural shift towards synchronisation with global risk assets, with a correlation index that frequently exceeds 0.6 in periods of systemic stress. This evolution highlights the decline in the advantages offered by diversification in developed and developing economies in a complex and interrelated financial environment.

  • Using decision tree regression for self-tuning mode-locked lasers: an alternative objective function approach

    by Mahmut Bağci, Semih Ay

    This study proposes an adaptive control and self-tuning algorithm for mode-locked fiber lasers. The algorithm has three main stages: the birefringence estimation, maximum seeking, and adaptive control. The cavity birefringence is recognized by a decision tree regressor. The optimal position of the polarizer is detected by a maximum seeking algorithm, which involves a novel, to our knowledge, objective function. Thus, the maximal nonlinear polarization rotation is detected by an alternative approach. The adaptive control of the fiber-laser is achieved by combining the birefringence estimation and maximum seeking algorithms, and it is demonstrated that the proposed methodology can keep the fiber-laser mode-locked under varied conditions of cavity birefringence. It is noted that the proposed adaptive control and self-tuning algorithm is equation-free and can be applied to different configurations of mode-locked fiber lasers.


  • Open Access

    Using Statistical Moments in Hierarchical Machine Learning for Estimation of Birefringence in Mode-Locked Fiber Laser Systems

    by Hasan Arda Solak, Şeyma Koltuklu, Sueda Turgut, Mahmut Bağcı

    Adaptive control and self-tuning of mode-locked fiber laser systems is an interesting topic in applied optics. Rapid and accurate detection of the cavity birefringence value is critical for the adaptive control and self-tuning of fiber laser systems. The birefringence varies randomly and significantly affects the mode-locking performance of fiber laser. In addition, the birefringence value in the laser cavity cannot be measured directly. In this study, from a new perspective, the birefringence value is determined (estimated) by hierarchical implementation of supervised machine learning algorithms. Unlike previous studies, instead of using the laser pulse energy directly, the energy evolution is recorded and a separate time series is obtained for each case of birefringence. The four statistical moments (mean, variance, skewness and kurtosis) of these time series are used as input variables (features) in the machine learning algorithm. When the findings of this study are compared with the results of previous studies, it is seen that the birefringence value can be estimated with higher accuracy in a short time with the hierarchical approach. More accurate classification of birefringence increases efficiency of algorithms that enable adaptive control and self-tuning of mode-locked fiber laser systems. Consequently, the study contributes to the advancement of mode-locked fiber laser technology by enhancing performance in various industrial and scientific applications, enabling broader and more efficient use of laser systems.

  • Open Access

    The Optimal Threshold Selection for High-Frequency Pairs Trading via Supervised Machine Learning Algorithms

    by Mahmut Bağcı, Pınar Kaya Soylu

    A high frequency pairs trading (HFPT) algorithm is built by the integration of pairs trading and threshold rebalancing algorithm. The determination of optimal threshold (OT) for the HFPT is crucial to maximize its profitability, and this study suggests a procedure to classify OT ranges by supervised machine learning (ML) techniques. In this regard, a sample dataset is created for ML applications. In this dataset, the target variables (OT values) are computed by the application of HFPT algorithm to real price data of 50 crypto-assets, and input variables (features) are calculated as portfolio mean, variance, skewness, kurtosis, value at risk, and correlation coefficient of the pairs. Before classification process, the pairs (or portfolios) are divided into three sub-groups (as positively, weakly and negatively correlated), and then OT values are classified by 6 ML methods. Comparing the evaluation metrics for ML methods, it is observed that the best accuracy, precision and $$F_1$$ F 1 -scores are obtained by the Random Forest (RF) classifier for all portfolio groups in two-class, three-class and four-class classification. Also, it is seen that the right classification performance of ML methods on positively and negatively correlated pairs are better than weakly correlated pairs. Furthermore, the success of RF classifier is verified with a test dataset that contains price series of 50 crypto-assets in January and February 2024. The applicability of OT range classification procedure in practical exchange markets is also demonstrated, and it is shown that the HFPT algorithm can yield reasonable profits when threshold selected in predicted range.


  • Open Access

    Optimal portfolio selection with volatility information for a high frequency rebalancing algorithm

    by Mahmut Bağcı, Pınar Kaya Soylu

    We propose a high-frequency rebalancing algorithm (HFRA) and compare its performance with periodic rebalancing (PR) and threshold rebalancing (TR) strategies. PR refers to the process of adjusting the relative weight of assets within portfolios at regular time intervals, whereas TR is a process of setting allocation limits for portfolios and rebalancing when portfolios exceed a specific percentage of deviation from the target allocation. The HFRA is constructed as an integration of pairs trading and a threshold-based rebalancing strategy, and the profitability of the HFRA is examined to determine the optimal portfolio size. The HFRA is applied to a dataset of real price series from cryptocurrency exchange markets across various trends and volatility regimes. Using cointegrated price data, it is shown that increasing the number of assets in a portfolio supports the profitability of the HFRA in an up-trend and reduces the potential loss of the HFRA in a down-trend in a high-volatility environment. For low-volatility regimes, although increasing portfolio size marginally enhances the HFRA’s profitability, the profits of portfolios of varied sizes do not significantly differ. It is demonstrated that when volatility is relatively high and the trend is upward, the HFRA can yield a substantial return via portfolios of large sizes. Moreover, the profitability of the HFRA is compared with that of the PR and TR strategies for long-term application. The HFRA is more profitable than the PR and TR strategies. This achievement of the HFRA is also validated statistically using the Fisher–Pitman permutation test.