Students will be able to demonstrate in-depth knowledge on:
Students will be able to:
- The steps necessary to pre-process dataset prior to ML implementations
- The theoretical foundations of commonly used ML algorithms
- The mathematical formulation for different metrics of validation used in regressor and classifier ML algorithms
- The main methods to extract and the value of adding text-based features in predictive models
- The basics of python language and its data science and ML libraries
- The main concepts in reinforcement learning and their applicability
- The dynamics of hybrid ML frameworks
- Manipulate different datasets to perform data cleaning, integration, reduction, and transformation
- Understand and describe the foundations of commonly used ML algorithms
- Formulate, analyze and solve business analytics problems
- Use python language and its main libraries to set up and manage data science problems
- Exhibit fluent use of different ML algorithms, using not only numerical features, but also text-based variables
- Understand the importance of explainable AI and use its main libraries
- Improve their investigative and reflective attitudes, being able to discuss and analyze different aspects of problems
- Develop the ability to design solutions and predict their potential impact on their field and society
- Build team-working skills by collaborating with their peers
- Identify ethical issues in applications of AI in businesses and propose solutions to them
- Become more proactive and responsible by taking initiative and control of their learning process
- Week 1: Main ML concepts and field relevance are presented. Also, an end-to-end project is introduced.
- Week 2: Focus on data exploration analysis, presenting the main definitions and implementations of pre-processing data treatment and feature engineering tasks (e.g., handling missing values and outliers). Also, the main concepts of Green AI are introduced, and the course's first Application Case (AC) is explored.
- Week 3: The commonly used clustering algorithms (i.e., k-Means and DBSCAN) are explored. Main definitions, pseudo-codes, and implementation are presented.
- Week 4 and 5: Some of the most used supervised ML models are introduced (e.g., regression and decision trees). Pseudo-codes, definitions, and examples of implementation are presented. Also, important concepts in ML pipelines (e.g., cross-validation, feature importance, and validation metrics) are explored.
- Week 6: Different streams of research on NLP are explored along with the presentation of an AC (i.e., Customer Sentiment Analysis and Topic Modeling). A guest lecturer will take over the content and AC on this topic (IEBIS/BMS: Dr. Daniel Braun).
- Week 7: Main definitions and applications of Reinforcement Learning (RL) are presented along with an AC. A guest lecturer will take over the lecture and AC on this topic (IEBIS/BMS: Dr. Jorg Osterrieder and Dr. Woulter van Heeswijk).
- Week 8: Main concepts, relevance, and applications related to explainable AI and Ethics in AI will be presented by two guest lecturers. Speakers (TBA) will present their current work and different application cases.
- Week 9, 10, and 11: Exams, projects presentations, and resits will be respectively organized on those weeks.
Final Project (30%)
Written Exam (50%)
In order to get the most from the AAIB, knowledge in Probability and Statistics (e.g., Conditional probability, hypothesis testing, distributions), Mathematics (e.g., Linear algebra and calculus), and Python (fundamentals) are recommended but not mandatory. In order to ensure that students enrolling for the course would not be penalized because of their past educational background (pre-requisites), and also to offer the course to masters students from multiple programs, the commonly expected pre-requisites on Mathematics, Statistics, and Python will be suggested through video classes and summary sheets.
|Master Business Information Technology||Required materials-Recommended materials|
|To be announced|
|Books and academic publications will be suggested in the first lecture.|
|Assignments, Project, Written Exam|