|
課程名稱 |
金融科技
Financial Technology |
|
開課學期 |
112-2 |
|
授課對象 |
電機資訊學院 生醫電子與資訊學研究所 |
|
授課教師 |
林 澤 |
|
課號 |
EE5183 |
|
課程識別碼 |
921EU2610 |
|
班次 |
|
|
學分 |
3.0 |
|
全/半年 |
半年 |
|
必/選修 |
選修 |
|
上課時間 |
星期二7,8,9(14:20~17:20) |
|
上課地點 |
電二146 |
|
備註 |
本課程以英語授課。
總人數上限：60人 |
|
|
|
|
課程簡介影片 |
|
|
核心能力關聯 |
核心能力與課程規劃關聯圖 |
|
課程大綱
|
|
為確保您我的權利,請尊重智慧財產權及不得非法影印
|
|
課程概述 |
- Financial technology (Fintech) is a broad category that refers to the innovative use of technology in the design and delivery of financial services and products.
- While many technology innovations play important parts in revolutionizing financial services, this course focuses on deep learning (DL) and its applications in FinTech.
- DL is a form of machine learning that enables computers to learn from experience and understand the world in terms of a hierarchy of concepts with a deep representation of many layers.
- In this course, we hope to demonstrate how DL can be applied to achieve superior predictive performance in FinTech applications. |
|
課程目標 |
In this course, we will first provide an overview of how deep learning revolutionizes the financial industry. We will then provide basics for machine learning (ML) and DL. Finally, we will provide several case studies on how to apply ML/DL to solve real-world FinTech problems. Students are expected to learn how to apply ML/DL algorithms in FinTech applications via completing programming homework and final project. |
|
課程要求 |
Machine learning
- Capable of using Python packages (e.g., numpy, pandas, scikit-learn) to process data
- Capable of using Pytorch to construct/test regular deep models
- Capable of understanding and modifying the source code of advanced models
Math
- Calculus; Linear Algebra |
|
預期每週課後學習時數 |
|
|
Office Hours |
另約時間 備註： Prof. Che Lin: Wed. 14:30~16:30 online/by appointment
TAs:
Name: Ming-Yi Hong (洪明邑)
Email: d09948005@ntu.edu.tw
Name: Miao-Chen Chiang (江妙真)
Email: d09948004@ntu.edu.tw
TA hour: Thur. 14:30~15:30 online (https://meet.google.com/fop-yvak-vxp, please inform the TAs via email in advance) |
|
指定閱讀 |
|
|
參考書目 |
1. Deep Learning by Ian Goodfellow, Yoshua Bengio, Aaron Courville
2. Advances in Financial Machine Learning by Lopez de Prado, MarcosDesignated Reading |
|
評量方式
(僅供參考) |
|
No. |
項目 |
百分比 |
說明 |
|
1. |
Programming Homework (x3) |
30% |
Any changes will be notified in the first class! |
2. |
Midterm: Proposal Presentation |
15% |
|
3. |
Paper Presentation |
15% |
|
4. |
Final Project |
35% |
Group presentation: 25%,
Individual report: 10% |
5. |
Expert talk reports (x3) |
5% |
2% for each |
|
|
週次 |
日期 |
單元主題 |
|
第1週 |
2/20 |
1. Course announcement
2. Video record: Introduction to FinTech / How Deep Learning is related to FinTech (+ group discussion) |
|
第2週 |
2/27 |
Pre-class:
1. Machine learning basics
2. DFN basics
In-class:
Group discussion (pre-class materials) |
|
第3週 |
3/05 |
Case Study: Bank direct marketing |
|
第4週 |
3/12 |
Recurrent Neural Networks |
|
第5週 |
3/19 |
Case Study: AsiaYo / Stock prediction |
|
第6週 |
3/26 |
Transformer and Bidirectional Encoder Representations from Transformers (BERT) |
|
第7週 |
4/02 |
Case Study: Style4Rec / Push4Rec |
|
第8週 |
4/09 |
Midterm: Proposal Presentation |
|
第9週 |
4/16 |
Expert talk |
|
第10週 |
4/23 |
* Graph Neural Networks |
|
第11週 |
4/30 |
* Case Study: SynHIN / TreeXGNN |
|
第12週 |
5/07 |
* Expert talk |
|
第13週 |
5/14 |
Paper Presentation |
|
第14週 |
5/21 |
Generative model |
|
第15週 |
5/28 |
Expert talk |
|
第16週 |
6/04 |
Final Presentations |
|