Data Analytics Master's Program

This course will provide the essential background to start to develop programs that will run on Hadoop Distributed File System (HDFS). The course will also show the students the limitations of traditional programming techniques and how Hadoop addresses these problems. After learning the basics of a Hadoop Cluster and Hadoop Ecosystem, students will learn to write programs using Apache Spark framework and run these programs on a Hadoop Cluster.

Instructor: Ahmet Demirelli

Time Series Forecasting is one of the most applied data science techniques across many disciplines, most notably in finance, in supply-chain management, and in production planning. This course is intended to provide a comprehensive introduction to forecasting methods used in the analysis and forecasting of Time Series. At the end of the course, students will be able to analyze and explore time series data, build and apply various Time Series models suitable for a wide range of business problems. PYthon programming language and libraries will be used in the analysis and forecasting of Time Series problems throughout the course.

Instructor: Özgür Asar

In this course, we will cover fundamental aspects of Machine Learning. We will start with fundamentals of machine learning, including different learning paradigms, regression and classification problems, evaluation methods, generalization and overfitting. We will then cover some of the fundamental machine learning techniques such as decision trees, Bayesian approaches, Naive Bayes classifier, and logistic regression, k-Nearest neighbor, and online learning algorithms. Besides understanding the basic theory behind the techniques, students are expected to apply them on different platforms like Weka or Matlab.

Instructor: H.Sait Ölmez

In the scope of this course we will begin with data extraction, cleaning, and normalization to prepare the data for Data Mining Algorithms. We will then cover Data Mining techniques including association rule mining, sequential patterns, clustering, text mining. Students are expected to understand the fundamental theory behind each technique, as well as implementing them using an environment such as RapidMiner or Weka.

Instructor: İnanç Arın

Recent advances in deep learning have led to groundbreaking advances in many fields, including computer vision and natural language processing. This course aims to equip students with practical skills and theoretical knowledge to leverage cutting-edge deep neural network architectures and algorithms to solve real-world challenges. Students will first gain a thorough understanding of deep learning fundamentals such as network architecture design,activation functions, loss functions, optimization algorithms, and regularization techniques that collectively enable neural networks to learn complex patterns and representations from data. Students will then gain practical knowledge on deploying deep learning models,conducting experiments, and optimizing model performance through hands-on experience with real-world datasets using the Python Programming language and the PyTorch framework.

Instructor: Ahmet Onur Durahim

Causal Data Science Causal data science has recently become a sub-discipline of general data science. The aim of this area is to draw cause-effect relationships from experimental and especially observational data. With this, the possible effects of the plannned interventions will be better understood. Application areas of causal data science consist of medicine, economy and finance, marketing, political sciences, management and tech industry. The main output of this course will be that the students will be able to obtain cause-effect relationships with modern machine learning methods. The course will be taught with applications in Python.

Instructor: Özgür Asar

This in-depth course is designed to give participants a strong grasp of Generative AI, with a special emphasis on Large Language Models (LLMs) and their real-world applications. You’ll explore core concepts, learn about LLM architectures and training methods, and develop an understanding of their strengths and limitations. By the end of the course, you’ll be ready to apply various techniques in practice, including fine-tuning LLMs for specific tasks, connecting them to external data sources using Retrieval-Augmented Generation (RAG), and creating agents and agentic workflows to handle complex tasks.

Instructor: Ahmet Onur Durahim

The widespread adoption of artificial intelligence (AI) technologies in the business world necessitates a strong emphasis on ethical principles and legal compliance in the development and deployment of such systems. This course explores the ethical and legal challenges arising from the use of AI. Key topics include algorithmic bias and discrimination, accountability, transparency, data protection, privacy, and the role of human oversight in automated decision-making. The course also provides a legal perspective through the examination of relevant legislation such as the EU AI Act, GDPR, Türkiye’s Personal Data Protection Law (KVKK), and other international frameworks. Topics such as the classification of AI systems, specific rules for high-risk AI, and corporate compliance obligations will also be discussed in detail.

Instructor: Yasin Beceni

This course is intended to provide industry insight into the world of project management and business communication. Upon completion of this course, students are expected to have a clear understanding of the tasks and challenges that are fundamental to project management requirements. The course will also cover issues on team management and other aspects of project management on schedules, risks and resources for a successful project outcome. The second part of this course will concentrate on effective communication with team members, presentation techniques for a wide range of audiences and communicating results and recommendations to upper management and clients.

Instructor: Hakan Aksungar

This course will provide the essential background to start to develop programs that will run on Hadoop Distributed File System (HDFS). The course will also show the students the limitations of traditional programming techniques and how Hadoop addresses these problems. After learning the basics of a Hadoop Cluster and Hadoop Ecosystem, students will learn to write programs using Apache Spark framework and run these programs on a Hadoop Cluster.

Instructor: Ahmet Demirelli

All graduate students pursuing a non-thesis MSc. Program are required to complete a project. The project topic and contents are based on the interest and background of the student and are approved by the faculty member serving as the Project Supervisor. At the completion of the project, the student is required to submit a final report and present the project. The final report is to be approved by the Project Supervisor.

This course aims at discussing the key principles of knowledge discovery process through various case studies arising from different application areas. The students are expected to learn the main steps to traverse when they face new data analytics problems. With each case study, the tools for cleaning, processing and altering the data shall be visited. A particular attention shall be given to data inspection, feature reduction and model selection. Each case study will be completed by a thorough discussion and interpretation of the results.

DA 515 Syllabus

The Machine Learning with Graphs course explores the intersection of graph theory, machine learning, and social network analysis to model and analyze complex networks in modern applications. The course covers foundational concepts, including graph representations, link analysis, centrality measures, and community detection, alongside machine learning techniques such as node embeddings and Graph Neural Networks. Throughout the course, students will gain hands-on experience using tools such as NetworkX and PyTorch Geometric, applying these techniques to real-world challenges, including analyzing large-scale networks and modeling social, technological, and biological systems.

DA 516 Syllabus

Exploratory Data Analysis (EDA) is an approach to data analysis for summarizing and visualizing the important characteristics of a data set. EDA focuses on exploring data to understand the data’s underlying structure and variables, to develop intuition about the data set, and decide how it can be investigated with more formal statistical methods. EDA is distinct from Data Visualization in that EDA is done towards the beginning of analysis and data visualization is done towards the end to communicate one’s finding. This course particularly pays attention to the applied techniques to data visualization narratives. We will draw on case studies from the business world, industry to news media.

DA 518 Syllabus