Data Mining & Visualization

Anyone who wants to make better decisions with data — analysts, product managers, founders, MBAs, engineers moving toward analytics, or curious learners. No prior data-science background is assumed; comfort with spreadsheets and a willingness to write a little Python will get you most of the way.

By the end you'll be able to:

1. Apply predictive modeling techniques — regression, classification, clustering, and text analytics — to extract actionable insights from messy business datasets.
2. Execute the complete data mining workflow from data preparation through model development, validation, and interpretation.
3. Communicate technical findings effectively to both technical and non-technical stakeholders.

This course organizes content around business decisions, not techniques.

Why? Because five years from now, you'll remember "that's how I figure out which customers will leave" — not "that's logistic regression."

Each module starts with a real decision question your future employer will care about. We then introduce the technique that answers it, walk through a hands-on case using real company-style data, and reinforce with an integrative simulation at the end of the course.

Why both open-source and enterprise tools? In the real world, businesses use both. Open-source tools like Python offer flexibility and are industry standards for data science. Enterprise platforms like SAS provide governed, scalable environments that large organizations trust for critical decisions. You'll graduate comfortable with both.

• SAS Viya for LearnersFree enterprise analytics platform — Visual Analytics & Model Studio.
• IBM SkillsBuildFree e-learning platform for Python and data science credentials.
• Microsoft ExcelFor accessible data exploration and quick analysis.
• PythonUse any environment you like — Jupyter, Google Colab, VS Code.

Most of analytics is choosing the right method for the question in front of you. These short browser tools work across every decision in the course.

• Analytics Technique NavigatorDecision tree for "which technique fits this question?"
• Technique PickerA game-form version of the same idea — drill it until it's reflexive.
• Tool Selection GuideExcel, Python, or SAS? Pick the right tool for the job.
• Data Science FrameworksCRISP-DM, OSEMN, and the modern variations.
• Analytics Foundations ReviewCross-topic concepts review — great between modules.
• Analytics Foundations JeopardyGame-show drilling on the foundational vocabulary.

What happens after the model is good? You ship it, and you grow into the role around it.

• Model Deployment GuideFrom notebook to scoring service — the practical path.
• TrendCart Deployment ChecklistA concrete worked checklist for a retail deployment.
• Deployment hubLanding page collecting all the deployment material.
• Deployment typesBatch, real-time, edge — pick the right architecture.
• Analyst Soft-Skills AssessmentSelf-check on the human skills that complement the technical ones.
• Skills in the AI AgeWhich analyst skills hold their value as AI gets stronger.
• IBM SkillsBuild Badge ChooserPicks the right industry badge for your background.

Two ways to work through it:

1. Follow the schedule. The 15-week plan is a suggested rhythm — go faster or slower as you like. Each week ties to one of the seven decision questions.
2. Browse by topic. If you have a specific question ("how do I segment customers?"), jump straight to that decision page. Each one is self-contained.

The integrative cases at the end are where you stitch techniques together against realistic company-style data. Pick one that interests you and work through it end-to-end.

AI tools like ChatGPT, Claude, and Copilot are transforming data science. Use them — they make this work faster and often better. A few principles:

• Learn WITH AI, not FROM AI. Treat it as a coding partner, not a replacement for your thinking.
• Own your work. You should be able to explain every line of code and every decision you ship.
• Verify before you trust. AI confidently produces wrong answers. Always sanity-check.

If you're working on a real project at work or school, follow your organization's AI policy on top of these principles.