Giảng viên phụ trách: Huỳnh Nhật Nam
Ngôn ngữ giảng dạy: Tiếng Việt
The first part of the course will review important statistics concepts with a focus on their applications in Exploratory Data Analysis. The second part introduces the fundamental principles and concepts underlying common algorithms in machine learning and their applications in business and policy. Specifically, students will first be introduced to the concepts that serve as the bedrock of developing effective supervised learning models, such as bias-variance trade-off, reducible and irreducible errors, and overfitting. Techniques for improving the generalisation of these models, including those for identifying overfitting (e.g. cross-validation) and eliminating (e.g. regularisation) will be discussed. While students may have been familiar with parametric approaches to supervised learning (e.g. regression models introduced in ‘Quantitative Methods’ courses), this course introduces students to non-parametric approaches (with a focus on classification problems) and methods to help evaluate and select classification models, as well as interpreting their results for decision-making given a specific use case. Students will also be introduced to the principles and application of popular unsupervised learning methods, such as clustering algorithms, association rules and collective filtering. The courses will consist of lectures and in-class computing exercises which are designed to help students practice and thus understand better the theoretical concepts presented in the lectures. Students will be asked to work in groups to read, prepare and present the key topics that will be discussed in each lecture. Lectures are primarily for recitation and discussion purposes. The course is not intended to be mathematical intensive. Mathematical details will be provided just enough to help students understand the data science concepts and associated techniques. Python will be used as the primary language to demonstrate the concepts and techniques that will be introduced in the course. Students will be required to write codes in Python for exercises, assignments and the final exam. In order to satisfactorily complete this course, it is strongly recommended that students are competent in Python. Those who do not have prior programming experience are required to complete an introductory programming course in Python on Mass Open Online Course (MOOC) platforms, such as www.coursera.org or www.edx.org, before taking this course.
