In this study, the performance of machine learning methods in credit risk scoring for "Buy Now Pay Later" customers is compared with the performance of standard credit risk models. Both traditional credit risk models and machine learning algorithms are evaluated using a real dataset. The comparison of models is conducted through variable selection, model training, and performance metrics. The results summarize to what extent machine learning methods outperform traditional models in credit risk assessment for "Buy Now Pay Later" customers. It is expected that this study will provide practical recommendations to improve risk assessment processes for financial institutions and credit providers.

Date: 14.07.2023 / 13:30 Place: A-212

This thesis compares the performance of univariate and multivariate energy consumption forecasts using deep learning techniques. The study finds that the univariate model outperforms the multivariate models for two of the three data sets tested. Among all the model architectures, LSTM outperforms all the univariate experiments, while TFT performs best among the multivariate experiments. The results suggest that univariate models are superior in forecasting energy consumption despite being less complex and requiring significantly less training time, cost, and resources.

Date: 13.08.2023 / 13:15 Place: A-212

Understanding biological phenomena is not always easy. Some phenomena cannot be easily transferred due to their complexity. Various visualization methods are used to speed up the process. These include new technologies such as Virtual and Mixed Reality. Such new technologies offer new approaches in the field of education by giving users completely new interactive experiences. In this study, we interactively simulated the defense of white blood cells, one of the body's defense mechanisms, in a 3D environment. We developed the application on 3 different platforms and obtained data about the platforms that users would prefer for such an application.

Date: 18.07.2023 / 10:30 Place: A-212

This thesis proposes automatic evaluation techniques to assess mobile health applications as alternatives to manual methods. It utilizes large language models to classify applications' employed Persuasive System Design (PSD) principles from collected user reviews and application descriptions. Mobile Application Rating Scale (MARS) scores are predicted with regression models trained on classification probabilities that are enriched with additional descriptive data. The study’s proposed techniques outperform baseline models, while feature importance scores show that PSD principles have significant contributions to quality predictions of mobile applications.

Date: 20.06.2023 / 14:00 Place: A-212

This study aims to gain an understanding of the content and the epistemic causal connective acquisition process of children aged 6;5- 8 in Turkish. For this purpose, to test whether there are connectives that children use specific to domains of causality as adults do (Çokal, Zeyrek, & Sanders, 2020); child and adult participants are given both descriptive (biased for content relations) and argumentative (biased for epistemic relations) tasks. Data that is collected from these tasks are annotated and statistically analyzed.

Date: 27.04.2023 / 15:30 Place: A-212

This thesis contributed to the edge computing literature by providing the first sectoral edge computing technology roadmap. It identifies how the focus of edge computing research changes by the application domain and objectives. Market and technology trends are discovered with dynamic topic modeling, using LDA and BERTopic methods. Technology roadmapping literature is extended by integrating data layer in a data-driven technology roadmap for social change and technology forecasting.

Date: 17.04.2023 / 13:00 Place: A-212

This study investigates pronominal anaphora in a Turkish and English translated TED corpus, the TED-MDB (Zeyrek et al., 2020), and provides a heuristic-based resolution mechanism for each language. The corpus comprises 364 English-Turkish sentences aligned. Research has two phases. The annotator annotated the data in the first phase. In the second phase, the knowledge poor method of Mitkov (1998) was tested on the Turkish and English annotated corpuses independently. TED presentations can identify pronominal anaphora with an F1-score of 0.61 in English and 0.63 in Turkish.

Date: 27.01.2023 / 15:00 Place: A-212

Among various Agile Software Development methods, Scrum is one of the most widely adopted one. The Scrum Guide clearly describes the Scrum events, artifacts, and roles. However, due to various project characteristics such as team size, team distribution, project domain, technology and requirement stability levels, Scrum practices need to be tailored. In this thesis, we analyze the various adaptations and tailoring choices of companies using Scrum. By incorporating evidence from literature and a survey study that is conducted among participants who use Scrum in their organizations, the impact of Scrum tailoring on technical debt will be analyzed.

Date: 24.01.2023 / 15:00 Place: B-116

This research evaluates the convergence of High-Performance Computing (HPC), Big Data, Artificial Intelligence (AI), and Cloud Computing technologies using bibliometric analysis, including performance and network analysis. The results reveal a rapidly growing literature with a significant increase in research activities in recent years, identifying key trends and patterns in the literature, including top published authors, most productive institutions, cited articles, and influential publications. This thesis provides valuable insights by identifying the bibliometric trends across the concept of technological convergence of HPC-Big Data-AI-Cloud Computing technologies, which is important for both academia and industry.

Date: 24.01.2023 / 11:00 Place: A-212

Catastrophic forgetting is common in the connectionist models while learning from a sequence of tasks. This study aims to investigate different continual learning methods on face analysis tasks involving age estimation, gender recognition, emotion recognition, and face recognition.  We analyze face analysis in two stages, which is also very common in Artificial Neural Networks: face detection and face attributes analysis. Firstly, experiments for learning face detection and facial landmark detection are conducted by studying multitask learning. Secondly, some continual learning methods inspired by biological systems are leveraged to overcome catastrophic interference in artificial models.

Date: 26.01.2023 / 09:30 Place: B-116