Arama Sonuçları
Listeleniyor 1 - 7 / 7
Yayın Convolutional neural network (CNN) algorithm based facial emotion recognition (FER) system for FER-2013 dataset(IEEE, 2022-11-18) Ezerceli, Özay; Eskil, Mustafa TanerFacial expression recognition (FER) is the key to understanding human emotions and feelings. It is an active area of research since human thoughts can be collected, processed, and used in customer satisfaction, politics, and medical domains. Automated FER systems had been developed and have been used to recognize humans’ emotions but it has been a quite challenging problem in machine learning due to the high intra-class variation. The first models were using known methods such as Support Vector Machines (SVM), Bayes classifier, Fuzzy Techniques, Feature Selection, Artificial Neural Networks (ANN) in their models but still, some limitations affect the accuracy critically such as subjectivity, occlusion, pose, low resolution, scale, illumination variation, etc. The ability of CNN boosts FER accuracy. Deep learning algorithms have emerged as the greatest way to produce the best results in FER in recent years. Various datasets were used to train, test, and validate the models. FER2013, CK+, JAFFE and FERG are some of the most popular datasets. To improve the accuracy of FER models, one dataset or a mix of datasets has been employed. Every dataset includes limitations and issues that have an impact on the model that is trained for it. As a solution to this problem, our state-of-the-art model based on deep learning architectures, particularly convolutional neural network architectures (CNN) with supportive techniques has been implemented. The proposed model achieved 93.7% accuracy with the combination of FER2013 and CK+ datasets for FER2013.Yayın Analysis of the variables that determine the satisfaction level of employees, agents and ultimate customers of an insurance company(Işık Üniversitesi, 2009) Özkol, Tufan; Sezgin, Selime; Işık Üniversitesi, Sosyal Bilimler Enstitüsü, Çağdaş İşletme Yönetimi Doktora ProgramıThe latest marketing theories and researches have showed that for understanding the complexity of service organizations and ensuring their long term success, the key point of success is the customer. Also the related concepts such as customer orientation, customer satisfaction and organizational culture have great importance. The purpose of this study is to analyze the variables that determine the satisfaction level of employees, agents and ultimate customers of an insurance company, to examine the relationships between them and additionally to describe and compare the types and patterns of organizational culture within the selected company. Three different surveys were sent to the groups (all company employees, all insurance agents and some ultimate customers assigned by their agents of the selected insurance company) by e-mail to determine their satisfaction levels and their perceptions with respect to the cultural profile of the company. The quantitative data collected were analyzed by statistical methods through the SPSS version 15.0 software. The results showed that there exist relationships both between company employee satisfaction and insurance agent satisfaction, and between perception of the insurance agent service quality and perception of the ultimate customer service quality. In spite of the strength of these associations being very low, it would be right to deal with these concepts in a holistic perspective and not to think separately for reaching the goals of the company. Also, organizational culture profile of the selected insurance company was determined and seen that there was evidence of reasonable balance in the four cultural types. It can be said that this balance will provide organizational effectiveness to the company.Yayın Customer retention dynamics of organized ready-to-wear textiles retailers in real and virtual markets(Işık Üniversitesi, 2017-10-13) Yılmaz, Kemal Özkan; Ferman, Ali Murat; Işık Üniversitesi, Sosyal Bilimler Enstitüsü, Çağdaş İşletme Yönetimi Doktora ProgramıCustomer retention dynamics have been receiving attention of the academic researchers especially for the last two decades. The challenging conditions of the swiftly increasing global competition have increased the importance of the customer retention concept in order to be able to foresee and react to the changes both in the competitive off-line and on-line business environment. This dissertation focuses on the customer retention strategy formulation among the marketing top level executives and senior management of the related companies. This study is an attempt to define the creation of customer retention intensions through explaining the proposed relationships between these dimensions based on the applications and ideas of the managers working at the leading organized ready-to-wear retailers of Turkey. A model is developed and related hypotheses are constructed based on the relevant academic literature and then tested through measuring attitudes of top management executives and marketing managers of leading organized ready-to-wear retailers in Turkey, who are members of United Brands Association and both active in off-line and online channels. The survey that has been conducted within this study employs an interval scale questionnaire, which has been applied online by sending an e-mail to each respondent including the website link of the survey and a scanned signed cover letter. The research findings provide useful implications to be considered on the way to sustain customer retention. The study is an attempt to reveal the attitudes of business professionals towards formulating inter-organizational customer retention strategies within the context of the proposed model in the dissertation.Yayın Application of ChatGPT in the tourism domain: potential structures and challenges(IEEE, 2023-12-23) Kılıçlıoğlu, Orkun Mehmet; Özçelik, Şuayb Talha; Yöndem, Meltem TurhanThe tourism industry stands out as a sector where effective customer communication significantly influences sales and customer satisfaction. The recent shift from traditional natural language processing methodologies to state-of-The-Art deep learning and transformer-based models has revolutionized the development of Conversational AI tools. These tools can provide comprehensive information about a company's product portfolio, enhancing customer engagement and decision-making. One potential Conversational AI application can be developed with ChatGPT. In this study, we explore the potential of using ChatGPT, a cutting-edge Conversational AI, in the context of Setur's products and services, focusing on two distinct scenarios: intention recognition and response generation. We incorporate Setur-specific data, including hotel information and annual catalogs. Our research aims to present potential structures and strategies for utilizing Language Model-based systems, particularly ChatGPT, in the tourism domain. We investigate the advantages and disadvantages of three different architectures and evaluate whether a restrictive or more independent model would be suitable for our application. Despite the impressive performance of Large Language Models (LLMs) in generating human-like dialogues, their end-To-end application faces limitations, such as system prompt constraints, fine-Tuning challenges, and model unavailability. Moreover, semantic search fails to deliver satisfactory performance when searching filters that require clear answers. To address these issues, we propose a hybrid approach that employs external interventions, the assignment of different GPT agents according to intent analysis, and traditional methods at specific junctures, which will facilitate the integration of domain knowledge into these systems.Yayın An applied study on the customer retention dynamics of organized ready-to-wear textiles retailers in real and virtual markets in Turkey(PressAcademia, 2017-12-30) Yılmaz, Kemal Özkan; Ferman, MuratPurpose - This descriptive field study aims to reveal customer retention strategy formulation insights among top level marketing professionals of the organized ready-to-wear textiles retailers, who are members of United Brands Association (BMD) both active in off-line and online channels, in the Turkish market. Methodology - Regarding the literature review conducted a research model with seven variables was proposed, and depending on the proposed research model, six hypotheses were formulated. The research is conducted by a questionnaire which has been applied on-line, by e-mail, post; which is designed specifically to test the proposed relationships, namely the hypotheses constructed. Factor analysis has been conducted to reveal the dimensionality of the variables in the research model. In this regard, principle component analysis using Varimax rotation was performed and the reliabilities of the scales have been assessed by alpha coefficient. Depending on the results of the factor analysis, correlation and regression analyses have been used to test the hypotheses of the study. Findings - Results indicate that perceived product quality, service support and complaint handling, customer experience and suggestions provided and perceived price fairness have significant and positive effects on customer satisfaction. Furthermore, customer satisfaction, trust towards service provided, trust towards company and brand, corporate reputation and corporate social responsibility have significant and positive effects on customer retention. Conclusion - The outcomes and findings of the study were found to support the objectives of the study and the results of the statistical analysis were found to accept hypotheses of the study. Perceived product quality, perceived service quality, perceived price fairness, trust and corporate image are some vital challenges for customer retention.Yayın The impact of the COVID-19 pandemic on online grocery supply chain management: a case study in Istanbul(Gazi Üniversitesi, 2024-03) Javadi, Sonya; Keten, Olcay; Özer, Ali İhsan; Alkan, Remziye ZeynepThe COVID-19 pandemic has already crippled normal life all over the world. Its negative impact not only changed the human health system tragically but also disrupted the global economic system. One negative result was ended up in the global food supply chain. As the lockdown times have suspended the manufacturing and logistic activities, therefore, the customers have experienced unimaginable chaos in the shopping markets. Moreover, the purchasing habit of the consumers has remarkably changed compared to pre-pandemic. To meet this new demand pattern, many grocery retailers have tried to adapt to the new normal. While before COVID-19 offline grocery purchasing was popular, after the pandemic, online service got tremendous attention in market. In this study, online grocery supply chain management during the COVID-19 in Istanbul is considered. The aim is to find out how online grocery companies will serve more efficiently during the pandemics and which factors have more effect on the customer’s satisfaction. To do so, first, three popular grocery retailers in Istanbul were selected. Then, a related survey was designed to understand the consumer experience as doing online grocery shopping in COVID-19. Unsurprisingly, a result shows that 60% of the respondents did online shopping every 3-4 days in one week, and the delivery time is the most important factor for the customers. Then, the SWOT analyses were performed accordingly, and the related strategies were summarized. Finally, several managerial implications were given to may improve the company’s online services in COVID-19 and post COVID-19 in Turkey.Yayın Sentiment analysis for hotel reviews in Turkish by using LLMs(Institute of Electrical and Electronics Engineers Inc., 2024) Özdemir, Ata Onur; Giritli, Efe Batur; Can, Yekta SaidThe field of sentiment analysis plays a pivotal role in consumer decision-making and service quality improvement within the hospitality industry. This study explores the application of Large Language Models (LLMs) for sentiment analysis of Turkish hotel reviews, contributing to the understanding of customer feedback and satisfaction. We created a dataset of 5,000 reviews by translating an English corpus into Turkish, which was then utilized to evaluate the performance of a state-of-the-art Turkish language model, TURNA. The study demonstrates that LLMs, particularly TURNA, outperform traditional machine learning algorithms and other advanced models in sentiment classification tasks, achieving an accuracy of 99.4%. This research underscores the potential of LLMs to enhance the accuracy of sentiment analysis, offering valuable insights for the tourism and hospitality sectors. The findings contribute to the ongoing evolution of sentiment analysis methodologies and suggest that LLMs can significantly improve t he understanding a nd processing of customer feedback in Turkish hotel reviews.
