Hsu-Chao Lai (賴旭昭)

Data Mining

Tue, 01 Sep 2026 00:00:00 +0000

Course Information

Offered: Spring 2026 and Fall 2026
Level: Undergraduate
Institution: Chang Gung University

Overview

The first half of this course introduces classical data mining problems and algorithms. The second half examines a range of data types commonly encountered in practice and the corresponding mining tasks.

Assignments combine analytical exercises with Python programming tasks to build students’ core problem-solving and implementation skills. For the final project, students work in teams to select a real-world problem from Kaggle, apply techniques learned in class, and present their methods and results in a clear, well-structured report.

Student Feedback

Spring 2026

41 student responses · Positive ratings (Strongly agree + Agree)

5 · Strongly agree 4 · Agree

100%

Teaching Enthusiasm

100%

Student Support

95%

Clarity & Organization

Evaluation item	Strongly agree	Agree	Neutral	Disagree	Strongly disagree
The instructor was consistently punctual and did not leave early or miss class without reason.	98%	2%	0%	0%	0%
The instructor taught with enthusiasm, diligence, and a strong sense of responsibility.	93%	7%	0%	0%	0%
The instructor was readily available to answer questions and discuss course material with students.	90%	10%	0%	0%	0%
The instructor's explanations were clear and well organized.	85%	10%	2%	2%	0%
The instructor's teaching methods stimulated interest and encouraged students to think critically.	78%	20%	2%	0%	0%
The course pacing was well managed and aligned with the syllabus.	90%	10%	0%	0%	0%
The teaching materials effectively supported learning.	83%	10%	7%	0%	0%
The instructor provided sufficient background knowledge and course content.	85%	12%	2%	0%	0%
The grading methods and criteria were clearly explained in advance and were reasonable.	93%	5%	2%	0%	0%

Percent of respondents selecting each option. Values may not total 100% due to rounding.

Fall 2026

Feedback will be added here after the course concludes.

Group Recommendation

Mon, 01 Jan 0001 00:00:00 +0000

Individual preferences become diverse—and often conflicting—when people make decisions together. My research develops group recommendation methods that balance personal interests, social relationships, and feedback from multiple participants rather than optimizing for a single user.

Applications include configuring shared virtual-reality shopping experiences and recommending multi-streaming activities. The goal is to find choices that work well for the group while preserving the preferences that matter to each member.

Probability and Statistics

Sun, 01 Feb 2026 00:00:00 +0000

Course Information

Semester: Spring 2026
Level: Undergraduate
Institution: Chang Gung University

Overview

Beginning with fundamental counting principles and Bayesian reasoning, this course guides students in modeling problems in computer science using random variables and probability distributions. It then develops the laws of large numbers and the central limit theorem to reveal the regularities behind large-scale data sampling. Finally, the course connects these foundations to maximum likelihood estimation and regression analysis, establishing core competencies for machine learning and statistical inference.

Student Feedback

Spring 2026

39 student responses · Positive ratings (Strongly agree + Agree)

5 · Strongly agree 4 · Agree

100%

Teaching Enthusiasm

100%

Student Support

95%

Clarity & Organization

Evaluation item	Strongly agree	Agree	Neutral	Disagree	Strongly disagree
The instructor was consistently punctual and did not leave early or miss class without reason.	92%	8%	0%	0%	0%
The instructor taught with enthusiasm, diligence, and a strong sense of responsibility.	97%	3%	0%	0%	0%
The instructor was readily available to answer questions and discuss course material with students.	92%	8%	0%	0%	0%
The instructor's explanations were clear and well organized.	90%	5%	5%	0%	0%
The instructor's teaching methods stimulated interest and encouraged students to think critically.	77%	13%	10%	0%	0%
The course pacing was well managed and aligned with the syllabus.	85%	15%	0%	0%	0%
The teaching materials effectively supported learning.	79%	18%	3%	0%	0%
The instructor provided sufficient background knowledge and course content.	87%	10%	3%	0%	0%
The grading methods and criteria were clearly explained in advance and were reasonable.	92%	8%	0%	0%	0%

Percent of respondents selecting each option. Values may not total 100% due to rounding.

Social Influence in Networks

Mon, 01 Jan 0001 00:00:00 +0000

Online behavior is shaped by interaction. My research studies how streamer–viewer exchanges—such as donations and responses—and viewer–viewer relationships influence interests, engagement, and content over time.

By modeling these feedback loops, we can understand the co-evolution of communities and content, then build recommendations that respond to changing social dynamics rather than treating users as isolated individuals.

Graph Mining and Learning

Tue, 01 Sep 2026 00:00:00 +0000

Course Information

Semester: Fall 2026
Level: Graduate
Institution: Chang Gung University

Overview

This course equips students with the core principles and practical skills of graph mining and representation learning. Topics span classical algorithms, including PageRank and community detection, modern graph neural networks (GNNs), and the integration of graph structures with large language models (LLMs) to address large-scale, real-world data challenges. In-class presentations and project discussions are also central components of the learning experience.

Student Feedback

Fall 2026

Feedback will be added here after the course concludes.

Team Sports Intelligence

Mon, 01 Jan 0001 00:00:00 +0000

Movement in team sports is not an individual action: every decision depends on teammates, opponents, and the evolving rally. My research models these interactions to forecast player movement and reveal coordinated patterns in doubles badminton.

The broader goal is to turn tracking data into tactical insight—supporting performance analysis, strategy design, and a clearer understanding of how teams create and respond to space.

Intelligent Decision Support

Mon, 01 Jan 0001 00:00:00 +0000

Effective decision support must be technically sound and practical for the people it serves. In healthcare and long-term care, this means combining professional recommendations with each person’s lifestyle, preferences, and everyday constraints.

My research explores data-driven systems for real-world decisions, including gait assessment, power-efficient sleep-stage monitoring, and uncertainty-aware planning. The aim is AI that supports experts while remaining responsive to individual needs.

Learning in Dynamic Markets

Mon, 01 Jan 0001 00:00:00 +0000

Markets evolve continuously under uncertainty. My research develops learning-based strategies that adapt to changing conditions, imperfect predictions, and delayed or partially observed outcomes.

Applications include real-time bidding in online advertising and pairs trading in financial markets, with an emphasis on robust decisions, structural changes, and efficient use of market feedback.

SPAIT: A Novel Movement Forecasting Model with Shot-Based Position-Adaptive Inference Transformer in Badminton

Tue, 17 Mar 2026 00:00:00 +0000

A Market-Aware Real-Time Bidding Strategy Using Censored Data with Reinforcement Learning in Online Advertising

Mon, 08 Dec 2025 00:00:00 +0000

Towards Hierarchical Multi-Agent Decision-Making for Uncertainty-Aware EV Charging

Mon, 08 Dec 2025 00:00:00 +0000

DeCo: Defect-Aware Modeling with Contrasting Matching for Optimizing Task Assignment in Online IC Testing

Sat, 16 Aug 2025 00:00:00 +0000

NEST: A Novel Ensemble Method for Estimating Spatio-Temporal Gait Parameters Using Inertial Measurement Units

Wed, 01 Jan 2025 00:00:00 +0000

Player Movement Predictions Using Team and Opponent Dynamics for Doubles Badminton

Wed, 01 Jan 2025 00:00:00 +0000

A Confidence-Based Power-Efficient Framework for Sleep Stage Classification on Consumer Wearables

Mon, 01 Jan 2024 00:00:00 +0000

MoCVAE: Movement Prediction by A Conditional Variational Autoencoder for Doubles Badminton

Mon, 01 Jan 2024 00:00:00 +0000

Experience

Tue, 24 Oct 2023 00:00:00 +0000

A Robust Real Time Bidding Strategy Against Inaccurate CTR Predictions by Using Cluster Expected Win Rate

Sun, 01 Jan 2023 00:00:00 +0000

Learning the Co-evolution Process on Live Stream Platforms with Dual Self-attention for Next-topic Recommendations

Sun, 01 Jan 2023 00:00:00 +0000

Pairs Trading Strategy Optimization Using Proximal Policy Optimization Algorithms

Sun, 01 Jan 2023 00:00:00 +0000

Spread Movement Prediction for Pairs Trading with High-Frequency Limit Order Data

Sat, 01 Jan 2022 00:00:00 +0000

Structural break-aware pairs trading strategy using deep reinforcement learning

Sat, 01 Jan 2022 00:00:00 +0000

SPENT(^mbox+): A Category- and Region-aware Successive POI Recommendation Model

Fri, 01 Jan 2021 00:00:00 +0000

The Design and Implementation of a Blockchain-Based Logistics Platform for International Trade

Fri, 01 Jan 2021 00:00:00 +0000

Live Multi-Streaming and Donation Recommendations via Coupled Donation-Response Tensor Factorization

Wed, 01 Jan 2020 00:00:00 +0000

Optimizing Item and Subgroup Configurations for Social-Aware VR Shopping

Wed, 01 Jan 2020 00:00:00 +0000

Social Attentive Network for Live Stream Recommendation

Wed, 01 Jan 2020 00:00:00 +0000

On VR Spatial Query for Dual Entangled Worlds

Tue, 01 Jan 2019 00:00:00 +0000

Social-Aware VR Configuration Recommendation via Multi-Feedback Coupled Tensor Factorization

Tue, 01 Jan 2019 00:00:00 +0000

Predicting traffic of online advertising in real-time bidding systems from perspective of demand-side platforms

Fri, 01 Jan 2016 00:00:00 +0000