機器學習與金融科技
Machine Learning and FinTech
| 節 | 週一 |
|---|---|
2 09:00–09:50 | 機器學習與金融科技 M-b09（光復） 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 course offers an introduction to machine learning from a statistical perspective, with a strong emphasis on applications in Financial Technology (FinTech), including credit risk modeling, wealth management, and fraud detection. Students will engage in hands-on projects—shared via GitHub—that integrate theoretical concepts with practical programming. The course centers on solving real-world problems in FinTech, encouraging collaboration, innovation, and data-driven decision-making. In addition to technical skills, students will enhance their oral presentation abilities and learn to leverage tools like ChatGPT to improve their coding and writing. Team projects will focus on key FinTech applications such as credit scoring, fraud detection, factor investing in Taiwan’s stock market, and cryptocurrency trading. To facilitate the course, students are required to: 1) Bring a laptop to every lecture. 2) Create free accounts on the following platforms: GitHub, Overleaf, and Microsoft Teams (using their NYCU accounts).
The course covers machine learning principles from a statistical perspective, focusing on FinTech applications. While calculus, probability, and linear algebra are helpful, they are not required. Python proficiency is recommended but not mandatory. AI techniques are encouraged to use and explored during the class.
無備註
1. TA: Claire 2. Please bring your laptop in each class. We will go through data analysis using various tools.
* Participation 10 % (Course Summary, HW presentation, papers summary, in-class exercises, we will use cold calls during class) * Project 20% (Replicate a high-quality paper with AI skills. Results must be in slides and manuscript forms of words limits 2400 in a professional writing style) * Data competition 20% in a group https://www3.stat.sinica.edu.tw/pds2026/ * Exam 50% (You can bring one page formula sheet)
教師未提供此項資料
| 週次 | 主題 |
|---|---|
| 第 1 週 | Syllabus & Introduction 2026-09-07(一) |
| 第 2 週 | Python and visualizing data 2026-09-14(一) |
| 第 3 週 | C12: Unsupervised learning 2026-09-21(一) |
| 第 4 週 | C12: Unsupervised Learning 2026-09-28(一) |
| 第 5 週 | Proposal Presentation and EDA 2026-10-05(一) |
| 第 6 週 | Break (Mid-Autumn Festival) 2026-10-12(一) |
| 第 7 週 | C03: Linear Regression 2026-10-19(一) |
| 第 8 週 | C04: Classification 2026-10-26(一) |
| 第 9 週 | C05: Resampling 2026-11-02(一) |
| 第 10 週 | C06: Model selection 2026-11-09(一) |
| 第 11 週 | C07: Beyond Linearity 2026-11-16(一) |
| 第 12 週 | C08: Tree-Based Methods 2026-11-23(一) |
| 第 13 週 | C09: SVM, C10: Neural Networks 2026-11-30(一) |
| 第 14 週 | Exam 2026-12-07(一) |
| 第 15 週 | Presentation of Projects 2026-12-14(一) |
| 第 16 週 | Presentation of Projects 2026-12-21(一) |
James et al. (July, 2023) An introduction to Statistical Learning with Applications in Python https://hastie.su.domains/ISLP/ISLP_website.pdf GitHUB: https://github.com/HWTeng-Teaching/202509-ML-FinTech
- 地點
- by appointment
- 時間
- by appointment
- 聯絡方式
- Email: hwteng@nycu.edu.tw