課程名稱 |
金融科技 Financial Technology |
開課學期 |
111-1 |
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 |
星期一7,8,9(14:20~17:20) |
上課地點 |
共103 |
備註 |
本課程以英語授課。 總人數上限:60人 |
課程網頁 |
|
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 |
金融科技(Fintech)是一個廣泛的類別,指的是在金融服務和產品的設計與交付中使用創新的技術。雖然許多技術創新在金融服務革命中發揮著重要作用,但本課程側重於深度學習 (DL) 及其在金融科技中的應用。深度學習是機器學習的一種形式,它使電腦能夠從經驗中學習並根據具有多層深度表示的概念來理解世界。它已被證明在電腦視覺和自然語言處理等應用的預測任務中非常成功。在本課程中,我們希望展示如何運用深度學習在金融科技應用中實現卓越的預測表現。
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. Deep learning is 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. It has been proven to be highly successful in predictive tasks for applications such as computer vision and natural language processing. In this course, we hope to demonstrate how DL can be applied to achieve superior predictive performance in FinTech applications. |
課程目標 |
在本課程中,我們將首先概述深度學習如何徹底改變金融行業。然後,我們將提供機器學習 (ML) 和 DL 的基礎知識。最後,我們將提供幾個關於如何應用 ML/DL 解決實際金融科技問題的案例研究。學生將通過完成編程作業和期末項目來學習如何在金融科技應用中應用 ML/DL 算法。
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 |
Basic python programming skills |
預期每週課後學習時數 |
|
Office Hours |
|
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, Marcos |
評量方式 (僅供參考) |
No. |
項目 |
百分比 |
說明 |
1. |
Programming Homework(x3) |
45% |
|
2. |
Midterm: ProposalPresentation |
10% |
|
3. |
Paper presentation |
10% |
|
4. |
Final project |
35% |
|
5. |
Extra : quiz (2%) |
0% |
|
|
週次 |
日期 |
單元主題 |
第1週 |
09/05 |
Introduction to FinTech / How Deep Learning is related to FinTech |
第2週 |
09/12 |
Machine Learning and Deep Learning Basics |
第3週 |
09/19 |
Deep Feedforward Networks / Convolutional Neural Networks |
第4週 |
09/26 |
Recurrent Neural Networks |
第5週 |
10/03 |
Transformer and Bidirectional Encoder Representations from Transformers (BERT) |
第6週 |
10/10 |
No class |
第7週 |
10/17 |
Case Study : Stock Price Prediction |
第8週 |
10/24 |
Midterm: Proposal Presentation |
第9週 |
10/31 |
Recommendation systems |
第10週 |
11/07 |
Case Study : AsiaYo |
第11週 |
11/14 |
Expert talk |
第12週 |
11/21 |
Paper Presentation |
第13週 |
11/28 |
Case Study: Avivid |
第14週 |
12/05 |
Graph Neural Networks |
第15週 |
12/12 |
Case Study : Cathay anomaly detection |
第16週 |
12/19 |
Final Presentations |
|