Yönetim Bilişim Sistemleri Bölümü Makale Koleksiyonu

Bu koleksiyon için kalıcı URI

Güncel Gönderiler

Listeleniyor 1 - 20 / 26
  • Öğe
    Re-Analysis of Non-Small Cell Lung Cancer and Drug Resistance Microarray Datasets with Machine Learning
    (Taylor and Francis Ltd., 2025) Erol, Çiğdem; Bawa, Tchare Adnaane; Özkan, Yalçın
    Non-small cell lung cancer is the most common type of lung cancer. Identification of genes associated with this disease may contribute to the treatment of the disease. Therefore, a lot of work is being done. In some of these studies, genetic data is obtained by microarray analysis and shared publicly in databases such as NCBI Gene Expression Omnibus. In today’s big data era, machine learning algorithms are frequently used to access valuable information from data stacks. Within the scope of this study, all (6 pieces) microarray datasets related to NSCLC and drug resistance in the NCBI GEO database were analyzed by R Studio. With support vector machine, k nearest neighbor, naïve Bayes, random forest, C5.0 decision tree, multilayer perceptron, and artificial neural network algorithms with principal component step, the datasets were analyzed separately and related genes were determined through the caret package, and the top 10 genes for each algorithm were given in the findings section in order of importance. In this resulting gene table, ELOVL7, HMGA2, SAT1, RRM1, IER3, SLC7A11, and U2AF1 genes are included in at least 2 different datasets. These identified genes are recommended to researchers working in a wet laboratory environment to be validated experimentally. © 2023 Taylor & Francis Group, LLC.
  • Öğe
    Antik Efsanelerden Üretken Yapay Zekâya: Gerçeklik, Dezenformasyon ve İnsanlık Mücadelesi
    (Türkiye Radyo Televizyon Kurumu, 31 Ocak 2025) Özdemir, Şebnem
    İnsanlığın en eski rüyası yapay zekâ, antik Yunan efsanelerinde/kaynaklarında, eski Çin ve eski Türk yazıtlarından, insanlığın temel mirası masallara kadar her alanda kendini göstermiştir. İlk geliştirildiği zamanlarda nasıl öğreneceği bilinemeyen makine (yapay zekâ), düşünce değişikliği ile veriden öğrenme yolculuğuna başlamıştır. Ancak “veri temelli makineler” geliştiricilere yeterli gelmemiş, veri olsun ya da olmasın insan gibi düşünebilen, insan gibi karar verebilen makineler yaratma hayali yükseliş göstermiştir. Çünkü yapay zekâ bir mühendislik disiplini olmaktan ötedir. Yapay zekâ, insanlığı taklit etme ve onu aşma sanatıdır (Özdemir, 2021). Kasım 2022’den itibaren başladığı düşünülen, önce üretici sonra üretken yapay zekâlar olarak adlandırılan süreç, insanlığın yapay zekâ yolculuğunda yeni bir dönemi başlatmıştır. Ancak bu başlayan yeni dönem, yapay zekânın tekil görev bazlı, verinin gösterdiği yolda ilerlediği değil, bir zekâ olarak var olduğu adımlar silsilesini de kapsamaktadır.
  • Öğe
    Hybrıd Performance Analysıs Wıth Multı-Crıterıa Decısıon Makıng Methods: Example Of Store Managers
    (İstanbul Kent Üniversitesi, 13 Eylül 2024) Edinsel, Sercan; Duran, Cem; Akdemir, Mehmet Alper
    Effectively evaluating and enhancing managers' performance is crucial for achieving organizational success and maintaining competitive advantage in a dynamic business environment. This paper presents a new approach for store manager performance evaluation using a comprehensive framework that combines two important decision-making techniques: Global Fuzzy Step-by-Step Step Weight Rating Ratio Analysis (SF-SWARA) and Global Fuzzy Combined Consensus Solution (SF-CoCoSo). The presented SF-SWARA-CoCoSo method aims to address the inherent complexities and subjectivities involved in evaluating managers' performance by incorporating multiple perspectives and objective criteria into the evaluation process. The aim of this study is to apply multi-criteria decision-making methods in a hybrid way to evaluate the performance of store managers in a simple and understandable way. Global Fuzzy Step-by-Step Step Weight Rating Ratio Analysis (SF-SWARA) and Global Fuzzy Combined Consensus Solution (SF-CoCoSo) hybrid Multi-Criteria Decision Making Method were used in the study. The findings of the study reveal that the “Knowledge and Training Level” criterion is the most important criterion for the store manager and the criterion with the lowest importance is the “Salary” criterion. As a result of the study, it is concluded that the criterion “Knowledge and Education Level”, which is determined to be the most important criterion, has emerged due to the fact that today is the information age. Anahtar Kelimele
  • Öğe
    The Effect of Influencer Marketing on Purchase Intention: Online Buying Behavior in Morocco
    (Beta İlim Derneği, 31 Aralık 2024) Ouchen, Ouissal; Yurdabak, Merve Kadriye
    This article explores the impact of influencer marketing on the online buying behavior of Moroccan consumers, through four key hypotheses related to online buying behavior and its drivers. This study claims that the credibility, similarity, familiarity, and authenticity of influencers jointly impact the online buying behavior of Moroccan customers. A questionnaire involving 300 Moroccan participants was conducted. After that, a thorough interpretation was conducted on the obtained answers. The findings show strong evidence of the influence that influencer factors such as familiarity, similarity, authenticity, and credibility have on Moroccan online buying behavior, validating all the assumptions. In summary, this study underscores the critical function of influencer marketing in shaping Moroccan consumers’ online buying behavior. The findings hold practical relevance for marketers seeking to influence Moroccan consumer online buying behavior and can help them improve their influencer marketing strategies in the Moroccan market.
  • Öğe
    Malware Detection in Forensic Memory Dumps: The Use of Deep Meta-Learning Models
    (İstanbul Üniversitesi, 2 Ocak 2024) Özkan, Yalçın
    The present study aimed to design a high-performance deep meta-learning model that could be utilized in classification predictions using forensic memory datasets and propose a framework that would ensure the generalization and consistency of the predictions with the help of this model. To achieve this aim, a dataset containing malware and obtained from forensic memory dumps was addressed. First, it was subjected to the classification process with a deep learning algorithm, and a predictive model was acquired. The predictive model was found to have an accuracy metric of 98.25%. In addition to this finding, a meta-learning model consisting of five different models with the same hyperparameters was created. The accuracy of the obtained meta-model was computed as 97.69%. With the thought that this model would reduce the prediction variance and thus the predictive model could be generalized, it was ensured to be run 5 times in a row. As a result of this process, the prediction variance, indicating a very small change, was calculated as 0.000012. Accordingly, considering the acquired performance value, it can be determined that high performance is achieved in malware detection, and thus what hyperparameters ensure success can be revealed. If deep learning methods are used as a single model, the problem is that the variance between the predictions is large due to its stochastic structure. To avoid such drawbacks, a deep meta-learning model using the same parameters was designed instead of a deep learning model comprising a single model, and considerably smaller variance values were achieved, thus providing generalized and consistent predictions.
  • Öğe
    The Role of The Need For Uniqueness In Choosing Between Conventional / Unconventional Customization: The Case Of Gen Z
    (Bandırma Onyedi Eylül Üniversitesi, 8 Ekim 2022) Duran, Cem; Kılıç, Anıl
    Social sciences such as economics and marketing has growing interest on consumer behavior and the underlying psychological factors. In particular, Consumer Need for Uniqueness (CNfU) receives notable attention from scholars. However, the literature lacks focus on how customization is related with CNfU. Moreover, Gen Z, the highest population of consumers are neglected in previous studies. The main objective of this study is to understand the impact of CNfU on Gen Z consumers’ choice between conventional and unconventional customization options for technology products. The paper uses survey-based data and uses a combination of statistical techniques, such as EFA, CFA, and structural equation modeling (SEM). It is revealed that CNfU has no influence on choosing between conventional and unconventional customization options. The results have significant implications for researchers and practitioners.
  • Öğe
    Strategic deployment of piezoelectric energy harvesting in smart urban infrastructure: A hybrid QPFRS, M-SWARA, K-means clustering, and PROMETHEE evaluation for sustainable advantage
    (Elsevier ltd, 2025) Mızrak, Filiz; Yaşar, Okan
    This study develops a hybrid multi-criteria decision-making (MCDM) model to evaluate and prioritize kinetic energy harvesting materials for urban infrastructure, a critical area as cities increasingly adopt sustainable technologies to meet energy demands. The integration of Quadripartitioned Fuzzy Rough Sets (QPFRS), MSWARA, K-Means clustering, and PROMETHEE offers a novel approach for addressing the complexities of material selection by balancing factors such as energy efficiency, durability, cost, scalability, and environmental impact. The strategic importance of this research lies in its potential to guide urban planners and policymakers toward making informed decisions that align with long-term sustainability goals and competitive advantages in smart city development. The findings identify BaTiO3 and ZnO as the most suitable materials for large-scale urban projects, offering superior performance in scalability and environmental sustainability, while materials like PZT exhibit strong energy efficiency but pose environmental concerns. By offering a comprehensive, adaptable evaluation framework, this study contributes both methodologically and practically to the growing field of sustainable urban infrastructure, ensuring that material selection not only meets immediate energy needs but also supports long-term urban development strategies.
  • Öğe
    Bıblıometrıc analysıs of green entrepreneurshıp
    (Beykoz Üniversitesi, 26 Aralık 2024) Duran, Cem
    The implementation of environmentally friendly activities and sustainable business models can contribute to reducing environmental pollution in the world. Green entrepreneurs can contribute to the realization of such activities. The aim of this study is to analyze the scientific development of the concept of green entrepreneurship. In order to achieve this objective, the bibliometric analysis method was applied. To increase the consistency of the study, the articles in Web of Science were considered as the unit of analysis. As a result of the searches, 100 journals, 552 authors, 195 articles, and 626 keywords were reached, and these articles were analyzed through the package in the R program. VOSviewer program was used to visualize the relationships of keywords. The first article on green entrepreneurship was published in 2007. The concept of green entrepreneurship has focused on sustainability, innovation, and management. It was concluded that the concept of green entrepreneurship is in the growth stage, the number of articles on this concept has increased rapidly over the years, the journal with the highest number of publications on the subject is Sustainability, and the country with the highest number of publications is China, and articles are mostly qualitative studies.
  • Öğe
    Bibliometric analysis of refugee effects to economic development
    (Anadolu Üniversitesi, 23 Aralık 2024) Duran, Cem; Akdemir, Mehmet Alp; Aygün, Salih
    The global refugee crisis presents significant challenges to economic development, especially in developing countries and regions that host large numbers of refugees. This study provides a comprehensive bibliometric analysis of research conducted on the effects of refugees on economic development over the past three decades. The study utilized the Web of Science (WoS) database to identify and analyze scholarly publications related to the topic of economic impact of refugees. The analysis focused on trends, patterns, and key themes in the literature. The results indicate a growing body of research on the topic, with particular emphasis on the effects of refugees on food aid, market outcomes, labor markets, and macroeconomic performance. The study examines the economic impact of refugees to countries, specifically their effects on labor markets, housing, food prices, and employment sectors. The study employs bibliometric analysis to systematically review and synthesize existing research, providing a comprehensive overview of the current state of knowledge on the subject. The findings enhance comprehension of the economic consequences of refugee movements and can guide policy and practice in the realm of economic development and refugee integration.
  • Öğe
    Şirketlerde Sürdürülebilirliği Stratejik Olarak Gündeme Getiren Dinamikler
    (Yönetim Bilimleri Dergisi, 13.06.2024) Yurdakul, Melek
    With the climate crisis and global warming, the importance of sustainability is increasing day by day and it is on the agenda of businesses. Although the importance of external ties to mobilize sustainability is clear, it is not possible to talk about the success of sustainability transformation unless there is an internal action towards sustainability. The fact that the issue of sustainability finds its place at the operational and management level of the company depends on the strategic approach to this issue. In this respect, although the importance of strategically addressing sustainability is clear, the dynamics that strategically push companies towards sustainability remain unclear in the literature. The reason for the emergence of this research is to explain and reveal these dynamics comprehensively. A systematic literature review was conducted to identify the dynamics that reveal sustainability strategies. In this context, WoS (Web of Science) and Scopus databases were preferred as they are internationally valid and highly respected. Eleven papers, which were determined to be suitable for the scope of the research by using the relevant keywords, were evaluated in detail. In the research finding, it is seen that there are internal and external dynamics that mobilize companies and that stakeholders have a particularly important place within these dynamics. At the same time, it has been determined in the literature that the market factor and legal regulations have an important share in the sustainability decisions of companies. Accordingly, companies are affected by customer, consumer, supplier expectations and social pressures, the push effect of the market or the competitive factor triggers companies and legal regulations bring sustainability decisions to the agenda of companies. However, compared to external dynamics, research in the related field mostly focuses on internal dynamics that drive sustainability. While the research contributes to researchers as it presents a concise synthesis of the relevant literature, the comprehensive identification of the dynamics has the potential to contribute to decision makers who want to take action towards the spread of sustainability.
  • Öğe
    The impact of the characteristics of self-service technologies on customer experience quality: insights for airline companies
    (Center for international scientific research of VSO and VSPP, 2024) Duran, Cem; Uray, Nimet; Alkilani, Shaymaa
    Research on self-service technologies (SSTs) has not been fully developed, and it is still open to debate with many aspects concerning its effect on customer experience and potential outcomes empirically, especially in the airline industry. Studies regarding these technologies and their potential impact are needed in the airline industry as they represent an integral part of the tourism industry. Previous studies on the airline industry have merely focused on SSTs and their impact on customer adoption, tendency to use, and satisfaction. The SSTs have the capacity to influence how customers perceive their experience in the overall process of getting a service. Thus, customer experience quality (CXQ) is influenced by the perceived characteristics of SSTs. The literature on the impact of SSTs on CXQ is considerably limited in general, particularly in the airline industry. More research on this issue is needed, especially following the outbreak of COVID-19; thus, this study aims to investigate a model that integrates the impact of the perceived characteristics of SSTs as antecedents and outcomes of CXQ. The research design of this study is based on a mixed-method approach: a preliminary study consisting of two qualitative investigations and a main study through face-to-face questionnaires with airline passengers. Structural equation modeling (SEM) is applied to the data collected from passengers traveling with the airline company in Turkey (N=501) through questionnaires applied as mall intercepts. The results of this study include extending the CXQ dimensions to add consistency and institutionalism, hence contributing to the service and tourism literature. Furthermore, this research provides actionable insights for managers in airline businesses to invest more in SSTs to improve their CXQ, customer satisfaction, and positive word-ofmouth communication (WOM).
  • Öğe
    An analysis of similarities and dissimilarities among categories of deep tech entrepreneurship: Evidence from Turkey
    (TR- Dizin, 2021) Kılıç, Anıl Savaş; Duran, Cem
    Amaç: Bu çalışma, derin teknoloji girişim kategorileri arasındaki benzerlikleri ve farklılıkları anlamayı ve derin teknoloji alanında bundan sonra gerçekleştirilecek akademik çalışmalar için bir başlangıç noktası olmayı amaçlamaktadır. Yöntem: İhtiyaçlar, kurucuların eğitim seviyesi ve finansman tipi gibi özelliklerin derin teknoloji kategorileri bazında nasıl değiştiğini anlamak amacıyla 126 derin teknoloji girişimi ile anket yapılmış ve hipotez testi uygulanmıştır. Bulgular: Derin teknoloji girişimlerinin bulunduğu lokasyon, kurucuların eğitim seviyesi, kurucuların geçmiş girişimcilik deneyimi ve derin teknoloji girişiminin satış ayak izi özelliklerinin derin teknoloji kategorisine göre farklılık gösterdiği görülmüştür. Sonuç ve Öneriler: Sonuçların, uygulayıcıların derin teknoloji girişimlerine yatırım yaparken veya onlarla iş birliği yaparken kararlarını daha doğru vermelerine yardımcı olması beklenmektedir. Benzer şekilde politika yapıcılar da derin teknoloji girişimciliği ekosistemini desteklemek için daha etkili politikalar geliştirmek için bu çalışmadan faydalanabilir. Özgün Değer: Bu çalışma şu açılardan özgündür; 1) akademik literatürde derin teknoloji tanımı yapılması 2) derin teknoloji özelliklerinin derin teknoloji kategorileriyle olan ilişkisinin anlaşılması 3) gelişmekte olan bir ülkede derin teknolojinin anlaşılması.
  • Öğe
    Yeni nesil tehdit: Derin kurgu (DeepFake)
    (DergiPark, 2021) Özdemir, Şebnem
    No Abstract Available
  • Öğe
    Özel hastanelerde müşteri deneyimi yönetimi üzerine bir değerlendirme
    (DergiPark, 2021) Duran, Cem
    Küreselleşen dünyanın yeni ekonomik ve ticari şartları, rekabeti ve ürün çeşitliliğini artırmıştır. Örgütler bu noktada müşteri kazanmanın, mevcut olanları korumaktan çok daha maliyetli olduğunu görmüş ve yoğun rekabet ortamında başarılı olabilmek için müşteri odaklı stratejiler geliştirmeye başlamışlardır. Müşteriye farklı deneyimler sunma ve bağlılık sağlama noktasında “müşteri deneyimi yönetimi”, örgütlerin kullandıkları stratejilerin en yenilerinden biri olarak karşımıza çıkmaktadır. Bu çalışma ile günümüzde tüm sektörlerde önemli role sahip olan ve örgütlerin marka değerini güçlendirerek satışlarını artırmak amacıyla yatırım yaptığı öncelikli alanların başında gelen “müşteri deneyimi yönetiminin, özel hastaneler bağlamında araştırılması ve değerlendirilmesi amaçlanmıştır. Literatür taramasının yöntem olarak belirlendiği araştırmada hastane, müşteri, müşteri deneyimi ve müşteri deneyimi yönetimi açıklanmış; çalışmanın konusu bağlamında özel hastanelerde müşteri deneyimi yönetimi incelenmiştir.
  • Öğe
    The effect of artificial intelligence on sustainable development goal
    (2021) Özdemir, Şebnem; Özuyar, Pınar Gökçin; Sundu, Mustafa
    Artificial intelligence (AI), which was built for "a better world" motto, reveals its potential in many fields. Despite of such good intension, results of AI systems caused bias, and sharpened the social prejudices. Besides in order to create such powerful AI systems and unbiased machines, the massive data collected, storaged, processed, also caused high energy consumption, ecological degradation. Although efforts have been made to integrate artificial intelligence into the sustainability field, the main limitation is about the AI researcher's, developer's point of view. In this study, revealing the contribution of artificial intelligence to the Sustainable Development Goals is aimed. At this point, data were collected using the analytical hierarchy process (AHP) from 30 individuals who were trained and worked as a developer in the field of artificial intelligence. As a result, it has been understood that while the developers believe that artificial intelligence will contribute mostly in the fields related to the industry and economy, they believe that i
  • Öğe
    Lider-üye etkileşiminin iş tatmini ve işten ayrılma niyetine etkisinde psikolojik sermayenin düzenleyici rolü
    (ADAMOR Toplum Araştırmaları Merkezi, 2021) Büyükkaymakçı, Yasemin; Sundu, Mustafa
    Bu araştırma ile lider-üye etkileşiminin iş tatmini ve işten ayrılma niyetine etkisi ile oluşan etkide psikolojik sermayenin düzenleyici rolü olup olmadığının incelenmesi amaçlanmıştır. Çalışmada nicel bir saha araştırması yapılmıştır. Geçerli ölçekler kullanılarak hazırlanmış olan anket, yüksek lisans tez çalışması esnasında 2019 yılında toplanmıştır. Anketin 45 adeti basılı form olarak, ilgililer tek tek bilgilendirilerek doldurulması sağlanmıştır. 237 adet anket ise SurveyMonkey ve Google/Docs uygulaması ile online olarak doldurulmuştur. Tüm sonuçlar SPSS programı kullanılarak analiz edilmiş ve yorumlanmıştır. Yapılan inceleme ve çalışmalar neticesinde lider üye etkileşiminin pozitif ve negatif olarak işten ayrılma niyeti ve iş tatmini üzerinde etkili olduğu ortaya çıkmıştır. Lider üye etkileşiminin işten ayrılma niyetine etkisinde, üyenin psikolojik sermayesinin düzenleyici etkisinin olduğu, ancak Lider üye etkileşiminin iş tatmine etkisinde ise psikolojik sermayenin düzenleyici etkisinin olmadığı görülmüştür. Bu nedenle çalışanın psikolojik sermaye düzeyinin ölçülmesinin örgütler için anlamlı sonuçlarının olacağı önerilmiştir. Analiz sonuçları incelendiğinde lider üye etkileşiminin örgüt için önemli iki unsur olan işten ayrılma niyeti ve iş tatmini üzerinde etkili olduğu görülmüştür. Ayrıca bu iki değişken arasındaki ilişkide çalışanların psikolojik sermaye düzeylerinin etkili olduğu ortaya çıkmıştır. Personellerin bu kıstas göz önüne alınarak seçilmesi organizasyonun etkinliğini artıracak ve insan kaynakları yönetimi politikalarına katkı sağlayacaktır.
  • Öğe
    Özel hastanelerde müşteri deneyimi yönetimi üzerine bir değerlendirme
    (DergiPark, 2021) Duran, Cem
    Küreselleşen dünyanın yeni ekonomik ve ticari şartları, rekabeti ve ürün çeşitliliğini artırmıştır. Örgütler bu noktada müşteri kazanmanın, mevcut olanları korumaktan çok daha maliyetli olduğunu görmüş ve yoğun rekabet ortamında başarılı olabilmek için müşteri odaklı stratejiler geliştirmeye başlamışlardır. Müşteriye farklı deneyimler sunma ve bağlılık sağlama noktasında “müşteri deneyimi yönetimi”, örgütlerin kullandıkları stratejilerin en yenilerinden biri olarak karşımıza çıkmaktadır. Bu çalışma ile günümüzde tüm sektörlerde önemli role sahip olan ve örgütlerin marka değerini güçlendirerek satışlarını artırmak amacıyla yatırım yaptığı öncelikli alanların başında gelen “müşteri deneyimi yönetiminin, özel hastaneler bağlamında araştırılması ve değerlendirilmesi amaçlanmıştır. Literatür taramasının yöntem olarak belirlendiği araştırmada hastane, müşteri, müşteri deneyimi ve müşteri deneyimi yönetimi açıklanmış; çalışmanın konusu bağlamında özel hastanelerde müşteri deneyimi yönetimi incelenmiştir.
  • Öğe
    Müşteri memnuniyeti ölçüm kalitesini tercih edilen ölçek derece sayısı nasıl etkiler?
    (DergiPark, 2021) Tavsan, Nihat; Duran, Cem
    Sürdürülebilir müşteri ilişkileri yönetimi, sürdürülebilir müşteri değerinden; müşteri değerini anlamanın yansıması ise müşteri memnuniyetinin ölçümünden geçmektedir. Bu gerçekten hareketle müşteri memnuniyetinin ölçümünde ölçek derece seçimi kritik rol oynamaktadır. Netice itibariyle kurumların mümkün olan en iyi ölçüm enstrümanı ile hareket etmeleri onların müşteri devamlılığını sağlıklı biçimde kurmalarını sağlayacaktır. Halihazırda kurumlar müşteri memnuniyetini çeşitli derecede ölçekler kullanarak ölçmektedirler. Amaç: Bu araştırmanın amacı; üç, beş, yedi ve on dereceli ölçekler ile müşteri memnuniyetinin ölçüm farklılıklarını ortaya koymak ve müşteri memnuniyeti ölçümünde ideal ölçek derece sayısına yönelik bir yaklaşım geliştirmektedir. Böylelikle müşteri memnuniyeti ölçümü yapan araştırmacıların ve uygulamacıların daha güvenilir sonuçlara ulaşmaları sağlanacaktır. Yöntem: Bankacılık sektöründe yapılan bu araştırmaya toplam 212 katılımcı iştirak etmiştir. Banka müşterilerinin hizmet aldıkları bankaya dair memnuniyet seviyeleri üçlü, beşli, yedili ve onlu ölçekler vasıtasıyla ölçülmüş, akabinde hangi dereceli ölçeğin müşteri sadakatini daha güvenilir olarak açıkladığı sınanmıştır. Bulgular: Müşteri memnuniyetinin müşteri sadakatine olan etkisinin de nomolojik anlamda sınandığı araştırma bulguları ışığında; on dereceli ölçeğin müşteri sadakatini açıklamakta diğer ölçek derecelerine kıyasla daha anlamlı sonuçlar doğurduğu ortaya konmuştur. Özgünlük: Türkiye’de memnuniyet ölçek derecesinin müşteri sadakatini ne güvenilirlikte açıkladığına dair bir çalışma bulunmamaktadır. Bu yönüyle çalışma literatürde özgün bir rol oynamaktadır.
  • Öğe
    Sentiment classification performance analysis based on glove word embedding
    (DergiPark, 2021) Kırelli, Yasin; Özdemir, Şebnem
    Representation of words in mathematical expressions is an essential issue in natural language processing. In this study, data sets in different categories are classified as positive or negative according to their content. Using the Glove (Global Vector for Word Representation) method, which is one of the word embedding methods, the effect of the vector set based on the word similarities previously calculated on the classification performance has been analyzed. In this study, the effect of pre-trained, embedded and deterministic word embedding classification performance has analyzed by using Long Short-Term Memory (LSTM). The proposed LSTM based deep learning model has been tested on three different data sets and the results have been evaluated
  • Öğe
    Contributions of crm applications to company performance
    (DergiPark, 2020) Duran, Cem
    Purpose- The purpose of this study is to find out the answer to the contributions of CRM applications to sales efficiency, lead management, pipeline, customer tracking, mobility and ensuring customer loyalty. Under this purpose, this study also indicates the reasons of resistance in CRM application use and solutions to them with an overall analyze of CRM’s contributions to company performance. Methodology- The study examines advantages of using CRM for employees in 4 primary basis; Sales Efficiency via Sales Force Automation, Employee Access to Corporate Memory, Mobility, Service and Complaint Management. This study also examines resistances and solutions against CRM application use. Findings- The findings of the study indicates that CRM is a mandatory tool for today’s companies to prevail competitors in the market by showing what is the unpredictable for the employees, by using the power of data. Also shows how CRM software strengthens the customer engagement and increase customer loyalty and profitability in multi aspects. Conclusion- CRM software is intended to be used in order to strengthen the relationship with the customer and increase customer loyalty, profitability, increase the productivity of the entire organization, especially the sales and service teams, to ensure collaboration between teams, to institutionalize with a modern technological infrastructure and to ensure the process of transforming from data to wisdom in order to increase corporate memory.