Practices of Big Data Planning - Kim Yonghee

Course Description

In a generative-AI and cloud-native environment, this project-based course takes students through the full data planning lifecycle from problem definition and pipeline design to dashboard demonstration and business model proposal.

Learning Objectives

Plan and execute practical workflows for collecting, storing, analyzing, and visualizing data
Design data-driven business models using generative AI and AutoML
Manage collaborative projects with ethical and governance perspectives
Produce portfolio-grade outputs through project demonstrations

Evaluation

Midterm

20%

Final

20%

Assignment

15%

Project

25%

Participation

10%

Attendance

10%

Weekly Schedule

Week	Topic	Details
1	Latest Trends in Big Data and AI	Data governance, ethics, and trend reporting
2	Data Collection and Cleaning Practice	Crawling and preprocessing pipeline with Python and AI APIs
3	Industrial and Public Data Case Analysis	Use-case analysis with public/enterprise datasets
4	Generative AI Pipeline Design	Prototype design for GPT-based data pipelines
5	Business Model Workshop	Value proposition and market-fit validation
6	Project Midpoint Review	Exploratory analysis, team presentation, and feedback
7	MLOps and AutoML Basics	Experiment tracking and model performance metrics
8	Midterm Exam
9	Data Storytelling and Visualization	Dashboard planning and visual communication design
10	Advanced Analytics	ML/DL basics and hyperparameter tuning concepts
11	Project Enhancement	KPI refinement and prototype completion
12	Final Project Coaching	Business problem solving and BM proposal coaching
13	Project Rehearsal	Demo flow and presentation quality refinement
14	Demo Day	Final presentation with dashboard demonstration
15	Final Exam

Textbook

Business Data Science

Matt Taddy

Hanbit Media, 2022