Introduction
Welcome to notes prepared for Research with AI @ Ritsumeikan Univeristy 2026.
The course introduces Gen AI, data science and ML for business/economics decision-making. Topics include data literacy and visualization, probability and inference, regression, basic supervised vs. unsupervised learning (e.g., classification, clustering), web scraping, text analysis and the responsible use of AI. Classes combine short lectures with hands-on exercises using Python in Google Colab. Students submit Colab notebooks and short reflections; feedback is provided through in-class review, rubric-based comments on submissions, and quiz explanations.
The course is organized into three phases: (1) foundations and data access (Classes 1–4), (2) the core analytics toolkit (Classes 5–10), and (3) AI-enabled research workflows, responsible AI, and synthesis through a capstone (Classes 11–14).
At the end of the course, students will be able to (1) describe data using appropriate visualizations and summary statistics, (2) apply basic probability and inference to real questions, (3) run and interpret simple/multiple regression, (4) explain supervised vs. unsupervised learning and apply basic examples, and (5) critically evaluate AI outputs and use AI tools to conduct academic research responsibly in analysis and reporting.
Tool Options (Python-first with Low-code Alternative) This course is taught using Python in Google Colab as the recommended default for hands-on analysis and reproducibility. Students who have limited programming background may choose an approved low-code workflow tool (e.g., RapidMiner or Orange) for selected practical tasks. Regardless of tool choice, students must demonstrate the same learning outcomes and submit the same evidence: (i) a data source note, (ii) a cleaning/preprocessing log, (iii) required outputs (tables/plots/evaluation metrics), (iv) an interpretation memo with limitations, and (v) a prompt/workflow log if generative AI tools were used. Grades prioritize reasoning, verification, and communication rather than tool complexity.
Students should choose one primary lane (Python or low-code) early in the semester and use it consistently, unless the instructor approves an exception.
TOC
Introduction
Course overview and how to use these notes
Setup
Python + Google Colab quickstart
Course AI policy and responsible use
Prompt & workflow log template
Class 1 — Where Analytics & AI/ML/DS Fit in Business
Supervised vs unsupervised learning
Class 2 — Data Literacy & Exploratory Data Analysis
(Optional) Python-for-data mini-bootcamp
Class 3 — Probability Foundations in Context
Simulation and intuition
Class 4 — Data Collection
APIs and responsible data sourcing
Our World in Data examples
Class 5 — Data Cleaning & Preprocessing
Cleaning pipeline, missingness, outliers, feature engineering
Class 6 — Simple & Multiple Regression
Interpretation and limitations
Class 7 — Data Visualization for Communication
Storytelling, chart choice, interactive plots
Class 8 — Unsupervised Learning
Clustering and PCA for segmentation
Class 9 — Decision Trees, Text-as-Data, and Ethical Implications
Tree reasoning, evaluation, bias risks
Sentiment analysis and error analysis
Class 10 — Time Series for Business/Economics
Trend, seasonality, forecasting baselines, evaluation
Class 11 — Scientific Research with AI in Social Sciences
Literature mapping, evidence synthesis, qualitative coding
Capstone proposal v1
Class 12 — AI Literacy
Prompting, verification, hallucinations, prompt logs
Human-in-the-loop “agentic” workflows
Class 13 — Ethics, Fairness & Responsible AI
Privacy, bias, explainability, deployment checklist
Class 14 — Capstone Presentations & Course Wrap-Up
Submission checklist and grading rubric
Appendices
Python cheat sheet (pandas, plotting, statsmodels, scikit-learn)
Visualization checklist (common pitfalls + best practices)
Verification checklist (sanity checks, leakage checks, reproducibility)
Mini glossary (key terms and definitions)