Course Syllabus

Course Information：

Year-Semester Course Number Course Name Phase Credits Hours Required/Elective Instructor Class Student NO. Withdraw Note

Spring Semester
Year 2025 345990 Deep Learning 1 3.0 3 ★ Chen-Shu Wang
Shu-Kai Fan 4IFM4A 4 0 資財四甲資財所合開

Year-Semester	Course Number	Course Name	Phase	Credits	Hours	Required/Elective	Instructor	Class	Student NO.	Withdraw	Note
Spring Semester Year 2025	345990	Deep Learning	1	3.0	3	★	Chen-Shu Wang Shu-Kai Fan	4IFM4A	4	0	資財四甲資財所合開

Course Plan：

Instructor Chen-Shu Wang　Office Hours

Email wangcs@ntut.edu.tw

Last Updated 2025-01-15 16:05:26

Course Objective 金融科技是近年來新興的產業趨勢，影響的層面非常廣泛，不只是金融方面，更牽涉到新興科技與物聯網。本課程將從不同的角度分析金融科技的技術內容、應用領域及商業模式，並藉由國內外重要金融科技公司發展的經驗做一介紹，希望達到了解並運用此新興科技的目的。本課程內容包括:金融科技概論、金融科技商業模式、金融大數據、P2P 借貸、虛擬貨幣、雲端服務、第三方支付、群眾募資、區塊鏈、跨境電商、程式交易、機器人理財等主題。 FinTech includes two words: Finance and Technology. It is a new trend of industrial field. It has influences on lots of technical fields, not only finance, but also emerging technologies and IoT. This course will analyze FinTech from different angles, such as technology contents, application fields and business models. It also will utilize experiences of leading companies with FinTech to obtain decent knowledge of this new field. The contents of this course include introduction to financial technology, business models of financial technology, finance big data, P2P lending, virtual money, cloud services, third-party payment, crowd funding, blockchain, cross-border e-commerce, program trading, and robotic financial advisory etc.

Course Schedule Weekly Schedule and Course Outline Week 1: Course Overview Introduction to Deep Learning and AI Tools Introduction to Design Thinking Design Thinking and Project Development Process Explanation of Course Grading Rubric Week 2: Data Processing and the KDD Process Overview of the KDD Process Data Processing with Pandas/NumPy Feature Engineering Week 3: Financial Data Analysis and Credit Risk Models Credit Risk Assessment Using Kaggle Datasets Week 4: Fundamentals of Deep Learning Building Simple Neural Networks with Keras/TensorFlow Impact of Hyperparameter Tuning Week 5: Stock Price Prediction Model Development Training and Predicting with Historical Data Gradient Descent Method Week 6: Convolutional Neural Networks (CNN) - Theory and Applications Basic Structure and Implementation of CNN: LeNet, VGG Week 7: Application of CNN in Credit Card Fraud Detection Training Fraud Detection Models Using Kaggle Datasets Discussion on Model Accuracy and Overfitting Issues Week 8: Guest Lecture on AI Applications in Finance Expert Sharing Case Studies Focus on AI Applications in Financial Risk Control to Inspire Project Design Week 9: Project Progress Report and Discussion Group Presentations: Data Sources, Model Strategies, Expected Contributions Week 10: Recurrent Neural Networks (RNN) and LSTM Time Series Data Analysis: Applications of RNN and LSTM Week 11: Application of LSTM in Stock Price Prediction Training LSTM Models for Stock Price Forecasting Week 12: Generative Adversarial Networks (GANs) Structure and Applications of GANs: Data Augmentation, Financial Market Simulation Practical Implementation with PyTorch Model Building Week 13: Deep Reinforcement Learning (DQN) Design and Implementation of Deep Q-Networks (DQN) Software Implementation and Strategy Design Week 14: Model Export and Deployment Cloud Deployment Using TensorFlow Serving Week 15: Summary and Cross-Domain Applications Review and Discussion on Cross-Domain Applications of Deep Learning Week 16: Internal Final Project Presentation Preparation of Final Project Data and Model Design Week 17: External Final Project Presentation Presentation of Project Outcomes and Peer Evaluation Week 18: Course Reflection and Summary Reflection on the Course and Discussion on Future Applications

Evaluation and grading policy Grade: - Assignment (Weka, Rapid Miner) 30% - Financial Data analytics Project 70%

Materials All right reserved. Do not reproduce without permission.

Foreign-language textbooks:No
rapidminer weka python

The access to curricular consultation wangcs@ntut.edu.tw

The course corresponds to the SDGs 無（None）

Note
　

Instructor	Chen-Shu Wang　Office Hours
Email	wangcs@ntut.edu.tw
Last Updated	2025-01-15 16:05:26
Course Objective	金融科技是近年來新興的產業趨勢，影響的層面非常廣泛，不只是金融方面，更牽涉到新興科技與物聯網。本課程將從不同的角度分析金融科技的技術內容、應用領域及商業模式，並藉由國內外重要金融科技公司發展的經驗做一介紹，希望達到了解並運用此新興科技的目的。本課程內容包括:金融科技概論、金融科技商業模式、金融大數據、P2P 借貸、虛擬貨幣、雲端服務、第三方支付、群眾募資、區塊鏈、跨境電商、程式交易、機器人理財等主題。 FinTech includes two words: Finance and Technology. It is a new trend of industrial field. It has influences on lots of technical fields, not only finance, but also emerging technologies and IoT. This course will analyze FinTech from different angles, such as technology contents, application fields and business models. It also will utilize experiences of leading companies with FinTech to obtain decent knowledge of this new field. The contents of this course include introduction to financial technology, business models of financial technology, finance big data, P2P lending, virtual money, cloud services, third-party payment, crowd funding, blockchain, cross-border e-commerce, program trading, and robotic financial advisory etc.
Course Schedule	Weekly Schedule and Course Outline Week 1: Course Overview Introduction to Deep Learning and AI Tools Introduction to Design Thinking Design Thinking and Project Development Process Explanation of Course Grading Rubric Week 2: Data Processing and the KDD Process Overview of the KDD Process Data Processing with Pandas/NumPy Feature Engineering Week 3: Financial Data Analysis and Credit Risk Models Credit Risk Assessment Using Kaggle Datasets Week 4: Fundamentals of Deep Learning Building Simple Neural Networks with Keras/TensorFlow Impact of Hyperparameter Tuning Week 5: Stock Price Prediction Model Development Training and Predicting with Historical Data Gradient Descent Method Week 6: Convolutional Neural Networks (CNN) - Theory and Applications Basic Structure and Implementation of CNN: LeNet, VGG Week 7: Application of CNN in Credit Card Fraud Detection Training Fraud Detection Models Using Kaggle Datasets Discussion on Model Accuracy and Overfitting Issues Week 8: Guest Lecture on AI Applications in Finance Expert Sharing Case Studies Focus on AI Applications in Financial Risk Control to Inspire Project Design Week 9: Project Progress Report and Discussion Group Presentations: Data Sources, Model Strategies, Expected Contributions Week 10: Recurrent Neural Networks (RNN) and LSTM Time Series Data Analysis: Applications of RNN and LSTM Week 11: Application of LSTM in Stock Price Prediction Training LSTM Models for Stock Price Forecasting Week 12: Generative Adversarial Networks (GANs) Structure and Applications of GANs: Data Augmentation, Financial Market Simulation Practical Implementation with PyTorch Model Building Week 13: Deep Reinforcement Learning (DQN) Design and Implementation of Deep Q-Networks (DQN) Software Implementation and Strategy Design Week 14: Model Export and Deployment Cloud Deployment Using TensorFlow Serving Week 15: Summary and Cross-Domain Applications Review and Discussion on Cross-Domain Applications of Deep Learning Week 16: Internal Final Project Presentation Preparation of Final Project Data and Model Design Week 17: External Final Project Presentation Presentation of Project Outcomes and Peer Evaluation Week 18: Course Reflection and Summary Reflection on the Course and Discussion on Future Applications
Evaluation and grading policy	Grade: - Assignment (Weka, Rapid Miner) 30% - Financial Data analytics Project 70%
Materials	All right reserved. Do not reproduce without permission. Foreign-language textbooks:No rapidminer weka python
The access to curricular consultation	wangcs@ntut.edu.tw
The course corresponds to the SDGs	無（None）
Note