機器學習與金融科技
Machine Learning and FinTech
| 節 | 週五 |
|---|---|
2 09:00–09:50 | 機器學習與金融科技 M101 3 節連堂 |
3 10:10–11:00 | |
4 11:10–12:00 |
* 根據陽明交大上課時間表所列
This comprehensive course offers an in-depth introduction to machine learning from a statistical perspective, focusing on its applications in financial technology (FinTech). Recognizing the growing importance of data analytics, the course explores using machine learning techniques in various domains within FinTech, such as default prediction and wealth management. To emphasize the practical application of machine learning, students will be required to apply their knowledge through a project component. Projects will be displayed on GitHub. By combining theoretical concepts with hands-on programming and project-based learning, this course ensures a dynamic and engaging educational experience. Students will develop essential skills in machine learning for problem-solving in the financial domain while fostering a collaborative and innovative approach to data analytics. Prof. Henry Lu will enrich the course content by offering advanced topics in deep learning.
This introductory course in machine learning focuses on its applications in financial technology (FinTech) and aims to provide students with a solid foundation. Emphasizing a statistical perspective, the course explores the principles and techniques of machine learning and their relevance to FinTech. While a mathematical background, including knowledge of calculus, probability, and linear algebra, can be advantageous, it is not a prerequisite for enrollment. Proficiency in Python programming is highly recommended, as it will facilitate understanding and implementing machine learning algorithms. Students who need to acquire or enhance their mathematical skills are encouraged to seek additional resources, such as online tutorials, videos, or collaborative learning with peers, and engage in conversations with instructors and teaching assistants to bridge knowledge gaps.
TA: 鄭翔澧 David Cheng
1. Participation & Weekly Homework (30%): Assigned tasks will be showcased by chosen students. 2. In-Class Exam (35%): Open-book format. 3. Group Project (35%): Teams of up to three members.
| 週次 | 主題 |
|---|---|
| 第 1 週 | Syllabus |
| 第 2 週 | C02: Statistical Learning & Lab on Python |
| 第 3 週 | Break (The Moon Festival) |
| 第 4 週 | C12: Unsupervised Learning |
| 第 5 週 | C12: Unsupervised Learning |
| 第 6 週 | C03: Linear Regression |
| 第 7 週 | C04: Classification |
| 第 8 週 | C04: Classification |
| 第 9 週 | C05: Resampling, C06: Model selection |
| 第 10 週 | C07: Beyond Linearity |
| 第 11 週 | C08: Tree-Based Methods |
| 第 12 週 | C09: SVM, C10: Neural Networks |
| 第 13 週 | The 17th NYCU International Finance Conference and the 3rd Yushan Conference |
| 第 14 週 | Exam |
| 第 15 週 | Presentation of Projects |
| 第 16 週 | Deep learning by Prof. Hong-Hsin Lu |
James et al. (July, 2023) An introduction to Statistical Learning with Applications in Python https://hastie.su.domains/ISLP/ISLP_website.pdf
- 地點
- by appointment
- 時間
- by appointment
- 聯絡方式
- Email: venteng@gmail.com