大數據分析與資料治理
Big Data Analytics and Data Governance
| 節 | 週四 |
|---|---|
A 18:30–19:20 | 大數據分析與資料治理 M-b01（光復） 3 節連堂 |
B 19:30–20:20 | |
C 20:30–21:20 |
* 根據陽明交大上課時間表所列
由於超級電腦、高速資/通訊網路、物聯網及人工智慧的迅速發展,逐步改變各個產業競爭形式,不可避免加速其數位轉型,本課程旨在引導非資訊專業領域學生,以資料科學角度切入,建立在計算網路平台、計算方法之基礎觀念,並了解及學習以財務金融服務上為主之新型應用,以利面對未來數位轉型之挑戰。
1. 具備Python或R基本程式語言能力。 2. 基礎線性代數。
無備註
教材編選: 以基本觀念為切入點,採用教材以開放資訊為主(參考教科書1-2),計算分析實習採用國網中心前瞻AI超級電腦TWCC,應用則與李正福教授及國網中心自然語言分析及區塊鍊團隊合作。 教學方法: 一般教授,輔以互動式問題答詢、作業及專題計畫 評量方式: 課堂表現 15%, 作業 40%, 期末專題 45%。 教學資源: 提供國網中心 TWCC, DAS 平台及區塊鍊沙盒。 教學相關配合事項: 本課程將以英文授課為主。
評量方式: 課堂表現 15%, 作業 40%, 期末專題 45%。
Applications of Big Data and Machine Learning
1. Blockchain for Digital Coins. 2. Deep Learning & Technical Analysis 3. High Frequency Trading 4. Natural Language Processing in Finance
- 講授：
- 15
- 示範：
- 3
- 實作：
- 3
- 其他：
- 9
Concept, Methods & Tools for Big Data and Machine Learning
1. Cyberinfrastructure & Data Analysis Platforms 2. Big data Concept and Tools 3. Machine Learning Concept and Methods
- 講授：
- 15
- 示範：
- 3
- 實作：
- 3
- 其他：
- 3
| 週次 | 主題 |
|---|---|
| 第 1 週 | Overview of Big Data & Machine Learning |
| 第 2 週 | Cyberinfrastructure for Big Data Analysis – AI Supercomputer Taiwan Cloud Computing (TWCC) |
| 第 3 週 | Cyberinfrastructure for Big Data Pipeline –Data Analysis Services (DAS) |
| 第 4 週 | Learning from Data – Basic Concepts (Learning, Error/Noises, Bias/Variance and Overfitting explained with linear models) |
| 第 5 週 | Learning from Data – Regularization & Validation (explained with linear models) |
| 第 6 週 | Machine Learning (ML) Methods – Types of ML, Some useful ML methods and practices. |
| 第 7 週 | Machine Learning Methods – Neural Networks & Deep Learning |
| 第 8 週 | Tour to NCHC – Introduction of Facility and how it operates. |
| 第 9 週 | Blockchain for digital Coin – Introduction (Seminar) |
| 第 10 週 | Blockchain for digital Coin – NCHC Blockchain Sandbox, Demo & Smart Contract Case Study, e.g. StableCoin. |
| 第 11 週 | Deeping Learning and Technical Analysis in Finance – Introduction & Alternative Traditional Approaches for Technical Analysis (Seminar) |
| 第 12 週 | Deeping Learning and Technical Analysis in Finance – Deep Learning Approach for Technical Analysis |
| 第 13 週 | Deeping Learning and Technical Analysis in Finance – Applications in comparison of Traditional and Technical Analysis. |
| 第 14 週 | High Frequency Trading - Introduction |
| 第 15 週 | High Frequency Trading - Theoretical Models for High-Frequency Trading & Traditional Approach for High-Frequency Trading |
| 第 16 週 | High Frequency Trading- Machine Learning Approach for High-Frequency Trading |
| 第 17 週 | Natural Language Processing in Finance (Seminar) |
| 第 18 週 | Final Project Report |
“Learning from Data”, Yaser S. Abu-Mostafa, Malik Magdon-Ismail, Hsuan-Tien Lin, AMLBook, 2012. (also available at https://work.caltech.edu/telecourse) “The Elements of Statistical Learning: Data Mining, Inference, and Prediction”, Trevor Hastie, Robert Tibshirani, and Jerome Friedman, Springer, 2ed, 2009 (also available at https://web.stanford.edu/~hastie/ElemStatLearn/) Python for Finance “Mastering Data-Driven Finance”, Yves Hilpisch, O’Reilly, 2ed, 2019. "Essentials of Excel, Excel VBA, SAS and Minitab for Statistical and Financial Analysis", Cheng-Few Lee, John Lee, Jow-Ran Chang, Tzu Tai, 2016. (2ed will be published in 2021 with Machine Learning.) “Big Data Science in Finance”, Irene Aldridge, Marco Avellaneda, Wiley, 2021.
- 地點
- Room 339@NCHC
- 時間
- By appointment
- 聯絡方式
- 03-5776085@360 fplin@nchc.narl.org.tw