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 M102 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 aims at training students with common machine learning techniques: clustering, principle component analysis, regression, and binary classification (logistic regression, decision tree, random forest, boosting, support vector machine, and neural network). Specifically, portfolio management and credit default prediction will be covered as applications in the realm of FinTech. The connection between machine learning techniques and statistics will be discussed. Data analysis will be implemented in Python. Prof. Henry Horng-Shing Lu will introduce advanced deep neural network, and Prof. Fang-Pang Lin will cover topics in other advanced topics. Real market data about stock and future prices will be used (downloaded from open source, or database such as TEJ and Option matrix) will be used as illustration.
Students are expected to be familiar with calculus and statistics.
1. 十月底前On-line course will be given simultaneously through out this semester via google meet Video call link: https://meet.google.com/xas-xnfm-ckx 2. Teaching Assistant: Ian Lee 李亦涵 (數據所碩二) Email: a0972425933@gmail.com
Grading policy 1. Homework (30%) : Homework will be assigned mostly weekly base. No late homework will be accepted. TA will post homework solutions for reference in new E3. 2. One exam (35%): In class and open-book 3. Project (35%)
| 週次 | 主題 |
|---|---|
| 第 1 週 | Overview |
| 第 2 週 | No class (中秋節) |
| 第 3 週 | Python basics |
| 第 4 週 | EDA of data |
| 第 5 週 | |
| 第 6 週 | Unsupervised learning: clustering |
| 第 7 週 | Principle Component Anlaysis |
| 第 8 週 | Portfolio management |
| 第 9 週 | Supervised learning: binary classification |
| 第 10 週 | Regression and feature selection |
| 第 11 週 | Text mining |
| 第 12 週 | High-performance computing and blockchain. By Prof. Fang-Pang Lin. |
| 第 13 週 | Deep learning 1 |
| 第 14 週 | Deep learning 2 |
| 第 15 週 | Exam |
| 第 16 週 | Presentation |
| 第 17 週 | Q&A (by appointment) |
| 第 18 週 | Q&A (by appointment) |
The following reference textbooks can be freely download from the NYCU library: James, Witten, Hastie, Tibshirani (2013) An Introduction to Statistical Learning with applications in R. Springer. Hastie, Tibshirani, and Freidman (2009) The Elements of Statistical Learning. Springer
- 地點
- M415 or online meeting using Google meet
- 時間
- 2EF or by appointment
- 聯絡方式
- Email: venteng@gmail.com