Dursun Delen

İş dünyasının giderek karmaşıklaşan ve dinamik hale gelen yapısı, farklı disiplinlerden gelen bireylerin aynı örgütsel çatı altında aynı amaçlar doğrultusunda etkin ve verimli çalışmalarını zorunlu hale getirmiştir. Bu sebeple de, işletmenin tüm işlevlerini bütüncül bir bakış açısı ile değerlendirebilecek ve bu hususları faaliyet gösterilen ekosistemin diğer dinamikleri ile uyumlu yönetebilecek bireylere duyulan ihtiyaç artmıştır. Ayrıca, teknoloji alanında yaşanan baş döndürücü gelişmeler rekabetin sahasını genişletmiş ve özellikle üretim, dağıtım, pazarlama ve finans alanlarında entegre bilgi birikimine sahip, yönetsel becerisi yüksek insan kaynağına önemli ölçüde bir talep doğurmuştur.

Adı Soyadı

Dursun Delen

İlgi Alanları

Sağlık Analitiği, Karar Destek Sistemleri, Sağlık Analitiği, İş Zekası, İş Analitiği

Kurumdaki Durumu

Pasif Personel

Detaylı Öğe Kaydı

Arama Sonuçları

Listeleniyor 1 - 10 / 20

A text-mining based cyber-risk assessment and mitigation framework for critical analysis of online hacker forums
(Elsevier, 2022) Delen, Dursun; Delen, Dursun; Biswas, Baidyanath; Mukhopadhyay, Arunabha; Bhattacharjee, Sudip; Kumar, Ajay; Delen, Dursun; Yönetim Bilimleri Fakültesi, İşletme Bölümü; Yönetim Bilimleri Fakültesi, İşletme Bölümü
Online hacker communities are meeting spots for aspiring and seasoned cybercriminals where they engage in technical discussions, share exploits and relevant hacking tools to be used in launching cyber-attacks on business organizations. Sometimes, the affected organizations can detect these attacks in advance, with the help of cyberthreat intelligence derived from the explicit and implicit features of hacker communication in these forums. Herein, we proposed a novel text-mining based cyber-risk assessment and mitigation framework, which performs the following critical tasks. (i) Cyber-risk Assessment - to identify hacker expertise (i.e., newbie, beginner, intermediate, and advanced) using explicit and implicit features applying various classification algorithms. Among these features, cybersecurity keywords, sharing of attachments, and sentiments emerged as significant. Further, we found that expert hackers demonstrate leadership in the online forums that eventually serve as communities of practice. Consequently, novice hackers gradually develop their cyber-attack skills through prolonged observations, interactions, and external influences in this social learning process. (ii) Cyber-risk mitigation - computes financial impact for every {hacker expertise, attack-type} combination, and then by ranking them on a {likelihood, impact} decision-matrix to prioritize mitigation strategies in affected organizations. Through these novel recommendations, our framework can guide managers to decide on appropriate cybersecurity controls using an {expected loss, probability, attack-type, hacker expertise} metric against financial losses due to cyber-attacks.
Assessing the supply chain performance: A causal analysis
(Springer US, 2019) Tatoğlu, Ekrem; Zaim, Selim; Delen, Dursun; Tatoğlu, Ekrem; Zaim, Selim; Delen, Dursun; Bayraktar, Erkan; Sarı, Kazım; Tatoğlu, Ekrem; Zaim, Selim; Delen, Dursun; Yönetim Bilimleri Fakültesi, İşletme Bölümü; Yönetim Bilimleri Fakültesi, İşletme Bölümü
Measuring the performance-related factors of a unit within a supply-chain is a challenging problem, mainly because of the complex interactions among the members governed by the supply chain strategy employed. Synergistic use of discrete-event simulation and structural equation modeling allows researchers and practitioners to analyze causal relationships between order-fulfillment characteristics of a supply-chain and retailers’ performance metrics. In this study, we model, simulate, and analyze a two-level supply-chain with seasonal linear demand, and using the information therein, develop a causal model to measure the links/relationships among the order-fulfillment factors and the retailer’s performance. According to the findings, of all the order-fulfillment characteristics of a supply-chain, the forecast inaccuracy was found to be the most important in mitigating the bullwhip effect. Concerning the total inventory cost and fill-rate as performance indicators of retailers, the desired service level had the highest priority, followed by the lead-time and forecast inaccuracy, respectively. To reduce the total inventory cost, the bullwhip effect seems to have the lowest priority for the retailers, as it does not appear to have a significant impact on the fill rate. Although seasonality (to some extent) influences the retailer’s performance, it does not seem to have a significant impact on the ranking of the factors affecting retailers’ supply-chain performance; except for the case where the backorder cost is overestimated.
An explanatory machine learning framework for studying pandemics: The case of COVID-19 emergency department readmissions
(Elsevier, 2022) Delen, Dursun; Delen, Dursun; Davazdahemami, Behrooz; Zolbanin, Hamed M.; Delen, Dursun; Yönetim Bilimleri Fakültesi, İşletme Bölümü; Yönetim Bilimleri Fakültesi, İşletme Bölümü
One of the major challenges that confront medical experts during a pandemic is the time required to identify and validate the risk factors of the novel disease and to develop an effective treatment protocol. Traditionally, this process involves numerous clinical trials that may take up to several years, during which strict preventive measures must be in place to control the outbreak and reduce the deaths. Advanced data analytics techniques, however, can be leveraged to guide and speed up this process. In this study, we combine evolutionary search algorithms, deep learning, and advanced model interpretation methods to develop a holistic exploratory- predictive-explanatory machine learning framework that can assist clinical decision-makers in reacting to the challenges of a pandemic in a timely manner. The proposed framework is showcased in studying emergency department (ED) readmissions of COVID-19 patients using ED visits from a real-world electronic health records database. After an exploratory feature selection phase using genetic algorithm, we develop and train a deep artificial neural network to predict early (i.e., 7-day) readmissions (AUC = 0.883). Lastly, a SHAP model is formulated to estimate additive Shapley values (i.e., importance scores) of the features and to interpret the magnitude and direction of their effects. The findings are mostly in line with those reported by lengthy and expensive clinical trial studies.
Can customer sentiment impact firm value? An integrated text mining approach
(Elsevier, 2022) Delen, Dursun; Delen, Dursun; Eachempati, Prajwal; Srivastava, Praveen Ranjan; Kumar, Ajay; Mu˜noz de Prat, Javier; Delen, Dursun; Yönetim Bilimleri Fakültesi, İşletme Bölümü; Yönetim Bilimleri Fakültesi, İşletme Bölümü
Developing measures to capture customer sentiment and securing a positive customer experience is a strategic necessity to improve firm profitability and shareholder value. The paper considers the relationship between customer satisfaction, earnings, and firm value as these drives change in stock prices, customer, and investor sentiment. The present study investigates the impact of customer sentiment polarity on stock prices based on Indian automobile sector databased such as the Indian Nifty Auto SNE (Maruti Suzuki, Tata Motors, and Eicher). A top-down approach is adopted to construct a financial proxy-based sentiment index completed with sentiment extracted from automobile news and customer reviews. The paper uses a text mining approach to holistically measure customer sentiment’s impact on investor sentiment and stock prices. The study was initially performed at the overall individual stock from the Nifty Auto NSE but focused on the top three passenger vehicle manufacturing companies i.e., Maruti Suzuki, Tata Motors, and Eicher. It was found that the sentiment index was augmented with news and customer reviews allows predicting more accurately NIFTY AUTO stock price movements. This implies that customer sentiment is a major driver of investor sentiment which in turn impacts the stock market and the firm value. Thus, the present study is an integrated approach to holistically measure customer sentiment’s impact on investor sentiment and stock prices.
Development of a sustainable corporate social responsibility index for performance evaluation of the energy industry: A hybrid decision-making methodology
(Elsevier, 2023) Hacıoğlu, Ümit; Yılmaz, Mustafa Kemal; Delen, Dursun; Hacıoğlu, Ümit; Yılmaz, Mustafa Kemal; Delen, Dursun; Dinçer, Hasan; Yüksel, Serhat; Hacıoğlu, Ümit; Yılmaz, Mustafa Kemal; Delen, Dursun; Yönetim Bilimleri Fakültesi, İşletme Bölümü; Yönetim Bilimleri Fakültesi, İşletme Bölümü
The ever-increasing pressure from stakeholders and policymakers on energy companies to achieve Sustainable Development Goals (SDGs) and Corporate Social Responsibility (CSR) mission requires them to reinvent their policies and practices. This study aims to examine the performance of alternative business models for the oil and gas industry by employing a hybrid business analytics methodology under a fuzzy environment resulting in a generalizable model named “Sustainable Development Goals-oriented CSR Index.” The proposed methodology employs a hybrid framework that utilizes bipolar Q-rung Orthopair Fuzzy (q-ROF), Multi Stepwise Weight Assessment Ratio Analysis (M-SWARA), and Elimination and Choice Translating Reality (ELECTRE) methods. The findings show that (i) the proposed model is reliable and consistent throughout the similar fuzzy set value ranges, (ii) clean energy is the most important SDG-oriented CSR Index factor for the sustainable energy industry in emerging economies, (iii) drilling is the best alternative energy sourcing for the oil and gas industry, and (iv) clean energy projects have the highest priority for energy investors. The results also highlight that global warming can be managed with effective energy practices for long-term sustainability. Finally, the findings suggest that energy companies should have the essential technological infrastructure and capable workforce to increase investment efficiency.
An integrated approach for lean production using simulation and data envelopment analysis
(Springer, 2021) Zaim, Selim; Delen, Dursun; Zaim, Selim; Delen, Dursun; Buyuksaatci Kiris, Sinem; Eryarsoy, Enes; Zaim, Selim; Delen, Dursun; Yönetim Bilimleri Fakültesi, İşletme Bölümü; Yönetim Bilimleri Fakültesi, İşletme Bölümü
According to the extant literature, improving the leanness of a production system boosts a company’s productivity and competitiveness. However, such an endeavor usually involves managing multiple, potentially conflicting objectives. This study proposes a framework that analyzes lean production methods using simulation and data envelopment analysis (DEA) to accommodate the underlying multi-objective decision-making problem. The proposed framework can help identify the most efficient solution alternative by (i) considering the most common lean production methods for assembly line balancing, such as single minute exchange of dies (SMED) and multi-machine set-up reduction (MMSUR), (ii) creating and simulating various alternative assembly line configuration options via discrete-event simulation modeling, and (iii) formulating and applying DEA to identify the best alternative assembly system configuration for the multi-objective decision making. In this study, we demonstrate the viability and superiority of the proposed framework with an application case on an automotive spare parts production system. The results show that the suggested framework substantially improves the existing system by increasing efficiency while concurrently decreasing work-in-process (WIP).
A probabilistic data analytics methodology based on Bayesian Belief network for predicting and understanding breast cancer survival
(Elsevier, 2022) Delen, Dursun; Delen, Dursun; Dağ, Aslı Z.; Akcam, Zümrüt; Kibis, Eyyub; Şimşek, Serhat; Delen, Dursun; Yönetim Bilimleri Fakültesi, İşletme Bölümü; Yönetim Bilimleri Fakültesi, İşletme Bölümü
Understanding breast cancer survival has proven to be a challenging problem for practitioners and researchers. Identifying the factors affecting cancer progression, their interrelationships, and their influence on patients’ long-term survival helps make timely treatment decisions. The current study addresses this problem by proposing a Tree-Augmented Bayesian Belief Network (TAN)-based data analytics methodology comprising of four steps: data acquisition and preprocessing, variable selection via Genetic Algorithm (GA), data balancing with synthetic minority over-sampling and random undersampling methods, and finally the development of the TAN model to determine the probabilistic inter-conditional dependency structure among breast cancer-related variables along with the posterior survival probabilities The proposed model is compared to well-known machine learning models. A what-if analysis has also been conducted to verify the associations among the variables in the TAN model. The relative importance of each variable has been investigated via sensitivity analysis. Finally, a decision support tool is developed to further explore the conditional dependency structure among the cancer-related factors. The results produced by the proposed methodology, namely the patientspecific posterior survival probabilities and the conditional relationships among the variables, can be used by healthcare professionals and physicians to improve the decision-making process in planning and managing breast cancer treatments. Our generic methodology can also accommodate other types of cancer and be applied to manage various medical procedures.
An ANP and fuzzy TOPSIS-based SWOT analysis for Turkey's energy planning
(Elsevier, 2018) Zaim, Selim; Demirel, Ömer Fahrettin; Delen, Dursun; Zaim, Selim; Demirel, Ömer Fahrettin; Delen, Dursun; Ervural, Beyzanur Çayır; Zaim, Selim; Demirel, Ömer Fahrettin; Aydın, Zeynep; Delen, Dursun; Yönetim Bilimleri Fakültesi, İşletme Bölümü; Yönetim Bilimleri Fakültesi, İşletme Bölümü
Energy planning involves a perpetual process of reevaluating alternative energy strategies. Authorities responsible for energy planning and management have to adjust their strategies according to new and improved alternative solutions based on the sustainability criteria. In this study, we propose an integrated hybrid methodology for the analysis of Turkey’s energy sector using Strengths, Weaknesses, Opportunities, and Threats (SWOT) analysis, Analytic Network Process (ANP) process, and weighted fuzzy Technique for Order Performance by Similarity to Ideal Solution (TOPSIS) to formulate and holistically analyze the energy strategy alternatives and priorities. The methodology proposed in this study allowed identifying the relevant criteria and sub-criteria using a SWOT analysis. Then, ANP approach, which is one of the popular multi-criteria decision making (MCDM) methods, is employed to determine the weights of each SWOT factors and sub-factors. Finally, fuzzy TOPSIS methodology is conducted to prioritize alternative energy strategies. We discuss the obtained results for the development of long-range alternative energy strategies. The results showed that turning the country into an energy hub and an energy terminal by effectively using the geo-strategic position within the framework of the regional cooperation is the most important priority. On the other hand, using the nuclear energy technologies within the energy supply strategies found to be the least favored priority.
An analytic approach to assessing organizational citizenship behavior
(Elsevier, 2017) Tatoğlu, Ekrem; Zaim, Selim; Delen, Dursun; Tatoğlu, Ekrem; Zaim, Selim; Delen, Dursun; Arda, Özlem Ayaz; Delen, Dursun; Tatoğlu, Ekrem; Zaim, Selim; Yönetim Bilimleri Fakültesi, İşletme Bölümü; Yönetim Bilimleri Fakültesi, İşletme Bölümü
This study examines the organizational citizenship behavior (OCB) of employees by designing and developing an analytic network process (ANP) methodology. The viability of the proposed methodology is demonstrated via the sales representatives of Beko, a brand name controlled by Koç Group. We first develop a conceptual framework based on qualitative research methods – in-depth interviews and focus group sessions. We employ the principles of ANP methodology to examine and discover the inter-relationships among the OCBs. This process results in a descriptive model that encapsulates the findings from both qualitative and analytics methods. Necessity, altruism, departmental, compliance, and independence are the underlying dimensions of OCBs found to be the most influential/important. The key novelty of this study resides in designing and developing a prescriptive analytics (i.e. ANP) methodology to evaluate the OCBs, which is rare in the area of organizational behavior (a managerial field of study that have been dominated by traditional statistical methods), and thus serves as a useful contribution/augmentation to the business/managerial research methods, and also extends the reach/coverage of analytics-based decision support systems research and practice into a new direction.
Deep-learning-based short-term electricity load forecasting: A real case application
(Elsevier, 2022) Delen, Dursun; Delen, Dursun; Yazıcı, İbrahim; Beyca, Ömer Faruk; Delen, Dursun; Yönetim Bilimleri Fakültesi, İşletme Bölümü; Yönetim Bilimleri Fakültesi, İşletme Bölümü
The rising popularity of deep learning can largely be attributed to the big data phenomenon, the surge in the development of new and novel deep neural network architectures, and the advent of powerful computational innovations. However, the application of deep neural networks is rare for time series problems when compared to other application areas. Short-term load forecasting, a typical and difficult time series problem, is considered as the application domain in this study. One-dimensional Convolutional Neural Networks (CNNs) use is rare in time series forecasting problems when compared to Long Short Term Memory (LSTM) and Gated Recurrent Unit (GRU), and the efficiency of CNN has been rather remarkable for pattern extraction. Hence, a new method that uses one-dimensional CNNs based on Video Pixel Networks (VPNs) in this study, in which the gating mechanism of Multiplicative Units of the VPNs is modified in some sense, for short term load forecasting. Specifically, the proposed one-dimensional CNNs, LSTM and GRU variants are applied to real-world electricity load data for 1-hour-ahead and 24-hour-ahead prediction tasks which they are the main concerns for the electricity provider firms for short term load forecasting. Statistical tests were conducted to spot the significance of the performance differences in analyses for which ten ensemble predictions of each method were experimented. According to the results of the comparative analyses, the proposed one-dimensional CNN model yielded the best result in total with 2.21% mean absolute percentage error for 24-h ahead predicitions. On the other hand, not a noteworthy difference between the methods was spotted even the proposed one-dimensional CNN method yielded the best results with approximately 1% mean absolute percentage error for 1-h ahead predictions.

Delen, Dursun

Araştırma projeleri

Organizasyon Birimleri

Adı Soyadı

İlgi Alanları

Kurumdaki Durumu

Filtreler

Yazar

Konu

Tarih

İndeks

WoS Q

Scopus Q

Dil

Tür

Kategori

Bölüm

Erişim Hakkı

Tam Metin

Öğe Türü

Ayarlar

Sırala

Sayfa Başına Sonuç

Arama Sonuçları