東吳大學教師授課計劃表

檔案產生時間:2022/3/4 下午 07:54:30
本表如有異動,於4小時內自動更新
一、課程基本資料 Course Information
科目名稱 Course Title:
(中文)虛擬交易與投資實作
(英文)VIRTUAL TRADING AND INVESTMENT IMPLEMENTATION
開課學期 Semester:110學年度第2學期
開課班級 Class:理財租稅
授課教師 Instructor:李宜熹 LEE, YI-HSI
科目代碼 Course Code:BBS20201 單全學期 Semester/Year:單 分組組別 Section:
人數限制 Class Size:50 必選修別 Required/Elective:選 學分數 Credit(s):3
星期節次 Day/Session: 三ABC  前次異動時間 Time Last Edited:111年02月23日17時01分
理財實務與租稅規劃基本能力指標 Basic Ability Index
編號
Code
指標名稱
Basic Ability Index
本科目對應之指標
Correspondent Index
達成該項基本能力之考評方式
Methods Of Evaluating This Ability
1國際視野與多元學習能力
International horizons and multicultural learning capacity
》出缺席狀況
》課堂討論與表現
》報告(含個人或小組、口頭或書面、專題、訪問、觀察等形式)
》實作(含分組演練/合作等)
》資料蒐集與分析
》團隊參與
2專業知識與人文涵養能力
Professional knowledge and cultural background
》出缺席狀況
》課堂討論與表現
》報告(含個人或小組、口頭或書面、專題、訪問、觀察等形式)
》實作(含分組演練/合作等)
》資料蒐集與分析
》團隊參與
3邏輯思考與分析決策能力
Logical thinking and analytical decision-making skills
》出缺席狀況
》課堂討論與表現
》報告(含個人或小組、口頭或書面、專題、訪問、觀察等形式)
》實作(含分組演練/合作等)
》資料蒐集與分析
》團隊參與
4溝通協調與團隊合作能力
The ability to communicate, coordinate, and work with a team
》出缺席狀況
》課堂討論與表現
》報告(含個人或小組、口頭或書面、專題、訪問、觀察等形式)
》實作(含分組演練/合作等)
》資料蒐集與分析
》團隊參與
二、指定教科書及參考資料 Textbooks and Reference
(請修課同學遵守智慧財產權,不得非法影印)
●指定教科書 Required Texts
Jansen, Stefan (2020), Machine Learning for Algorithmic Trading: Predictive models to extract signals from market and alternative data for systematic trading strategies with Python, 2nd Edition.

https://github.com/PacktPublishing/Machine-Learning-for-Algorithmic-Trading-Second-Edition

●參考書資料暨網路資源 Reference Books and Online Resources
阿布 (2017),量化交易之路 : 用 Python 做股票量化分析,第一版,機械工業出版社。
蔡立耑 (2018),金融科技實戰:Python 與量化投資,第一版,博碩。
Chan, Ernie (2013), Algorithmic Trading: Winning Strategies and Their Rationale, 1st Edition.Chan, Ernie (2017), Machine Trading: Deploying Computer Algorithms to Conquer the Markets, 1st Edition.
Hilpisch, Yves (2020), Python for Algorithmic Trading: From Idea to Cloud Deployment, 1st Edition.
Bacidore, Jeffrey (2020), Algorithmic Trading: A Practitioner's Guide, 1st Edition.
Conlan, Chris (2020), Algorithmic Trading with Python: Quantitative Methods and Strategy Development, 1st Edition.
Kissell, Robert (2020), Algorithmic Trading Methods: Applications Using Advanced Statistics, Optimization, and Machine Learning Techniques, 1st Edition.
三、教學目標 Objectives
以財務知識為基礎背景,金融科技整合應用為導向。希望透過「虛擬交易」的輔助,讓學生從虛擬的股票交易中,體驗金融市場運作可能面臨的風險與報酬。讓學生學習正確的理財觀,才能在急劇複雜的金融市場裡避免損失。另外,著重學生的技能與實務能力培養,以期將此經驗用於未來的工作之中。
This course makes students involve the risks and returns of financial market via virtual trading and investment enviroment. Base on the practices of virtual exchange, students can make good use of their financial knowledge which have learned to avoid the potential losses in financial markets and develop the necessarily practical abilities of their future works.
四、課程內容 Course Description
整體敘述 Overall Description
本課程會從量化交易的正確性認識出發,以 Python 語言進行實作。
所有範例都基於量化交易及相關知識,期望結合實戰的特點。
●分週敘述 Weekly Schedule
週次 Wk 日期 Date 課程內容 Content 備註 Note

1

2/23 Part 1: From Data to Strategy Development
01 Machine Learning for Trading: From Idea to Execution
  

2

3/2 Part 1: From Data to Strategy Development
02 Market & Fundamental Data: Sources and Techniques
03 Alternative Data for Finance: Categories and Use Cases
  

3

3/9 Part 1: From Data to Strategy Development
04 Financial Feature Engineering: How to research Alpha Factors
05 Portfolio Optimization and Performance Evaluation

24 Appendix - Alpha Factor Library
  

4

3/16 Part 2: Machine Learning for Trading: Fundamentals
06 The Machine Learning Process
07 Linear Models: From Risk Factors to Return Forecasts
08 The ML4T Workflow: From Model to Strategy Backtesting
  

5

3/23 Part 2: Machine Learning for Trading: Fundamentals
09 Time Series Models for Volatility Forecasts and Statistical Arbitrage
10 Bayesian ML: Dynamic Sharpe Ratios and Pairs Trading
11 Random Forests: A Long-Short Strategy for Japanese Stocks
  

6

3/30 Part 2: Machine Learning for Trading: Fundamentals
12 Boosting your Trading Strategy
  

7

4/6 Part 2: Machine Learning for Trading: Fundamentals
13 Data-Driven Risk Factors and Asset Allocation with Unsupervised Learning
  

8

4/13 Part 3: Natural Language Processing for Trading
14 Text Data for Trading: Sentiment Analysis
15 Topic Modeling: Summarizing Financial News
16 Word embeddings for Earnings Calls and SEC Filings
  

9

4/20 期中提案報告   

10

4/27 Part 4: Deep & Reinforcement Learning
17 Deep Learning for Trading
  

11

5/4 Part 4: Deep & Reinforcement Learning
18 CNN for Financial Time Series and Satellite Images
  

12

5/11 Part 4: Deep & Reinforcement Learning
19 RNN for Multivariate Time Series and Sentiment Analysis
  

13

5/18 Part 4: Deep & Reinforcement Learning
20 Autoencoders for Conditional Risk Factors and Asset Pricing
  

14

5/25 Part 4: Deep & Reinforcement Learning
21 Generative Adversarial Nets for Synthetic Time Series Data
  

15

6/1 Part 4: Deep & Reinforcement Learning
22 Deep Reinforcement Learning: Building a Trading Agent
  

16

6/8 Part 4: Deep & Reinforcement Learning
23 Conclusions and Next Steps
  

17

6/15 期末報告 I   

18

6/22 期末報告 II   
五、考評及成績核算方式 Grading
配分項目 Items 次數 Times 配分比率 Percentage 配分標準說明 Grading Description
出席1030%課堂報告、課堂參與
期中考120%提案報告
學期考150%期末報告
配分比率加總 100%  
六、授課教師課業輔導時間和聯絡方式 Office Hours And Contact Info
●課業輔導時間 Office Hour
星期二中午/星期三下午
●聯絡方式 Contact Info
研究室地點 Office:2334 EMAIL:eclee@scu.edu.tw
聯絡電話 Tel:3621 其他 Others:
七、教學助理聯絡方式 TA’s Contact Info
教學助理姓名 Name 連絡電話 Tel EMAIL 其他 Others
八、建議先修課程 Suggested Prerequisite Course
財務管理、投資學、金融市場、
程式設計、演算法、資料庫設計
微積分、統計學、線性代數、作業研究
九、課程其他要求 Other Requirements
本課程不會講授 Python 程式語法,修課者應先有 Python 中階程式能力。
十、學校教材上網、數位學習平台及教師個人網址 University’s Web Portal And Teacher's Website
學校教材上網網址 University’s Teaching Material Portal:
東吳大學Moodle數位平台:http://isee.scu.edu.tw
學校數位學習平台 University’s Digital Learning Platform:
☐東吳大學Moodle數位平台:http://isee.scu.edu.tw
☐東吳大學Tronclass行動數位平台:https://tronclass.scu.edu.tw
教師個人網址 Teacher's Website:https://www.feam.scu.edu.tw/faculty_personal/72
其他 Others:
十一、計畫表公布後異動說明 Changes Made After Posting Syllabus