Level: Beginner to Intermediate

This course will meet for two hours on consecutive Tuesdays, beginning on October 13 and finishing on November 17.

Weekly sessions run from 9 a.m. - 11 a.m. Pacific and will be recorded.

There will be take-home lab assignments between sessions.

Organizations are under constant pressure to make better decisions using data to remain competitive. Why?
Because everyday business decisions depend on answering important questions like:

• What are customers saying in surveys, chats, and social media posts?
• Should we open more stores, hire more employees, buy more inventory, etc.?

However, there’s a problem.

Many of the most important business questions cannot be answered with basic analytics alone. Dashboards and PivotTables are very useful tools, but they lack the power that modern organizations need to make data-driven decisions. Here are a couple of examples:

• Free-form text data (e.g., customer service chats) needs to be transformed into a format suitable for analysis.
• Forecasting requires methods that can mine hidden patterns over time and produce useful predictions.

In 2026, it's tempting to think generative AI tools are the solution to these problems, but leading organizations realize that a different type of AI is the best solution: machine learning. With machine learning, organizations get what they need, but can't get from LLMs—explainability, reproducibility, and (as AI token costs increase) predictable costs.

Through 6 weekly 2-hour sessions and 10 hands-on labs, you will learn the skills you need to tackle these real-world use cases.

By the end of the 6 weeks, you will not only have built the skills you need to make an impact at work, but you will also have built a library of Python code to accelerate you in making that impact.

You Will Learn

• What is text analytics?
• How to transform free-form text for use in analytics.
• Term frequency-inverse document frequency (TF-IDF).
• How to group (i.e., cluster) text documents based on similarity.
• How to classify documents (e.g., sentiment analysis and spam filtering).
• What is forecasting?
• How to evaluate your forecasts.
• Simple forecasting methods and why they’re usually not enough.
• Why machine learning is the future of forecasting.
• How to build machine learning forecasting models.

Pre-requisites

Students must be familiar with Python and Jupyter notebooks or complete the pre-recorded course “Python Quick Start” prior to the class. This pre-recorded course will be made available in advance to any students who need it.

This bootcamp assumes knowledge of machine learning using decision trees and random forests as covered in TDWI’s Introduction to Machine Learning course.

This training is designed for any professional. No knowledge of advanced mathematics or statistics is required.

Laptop Setup:

You must have a computer with the required software installed before the bootcamp.

Note on Corporate Laptops:

This course requires installation of software, as well as the ability to download data files, library files, and code.

If your corporate laptop blocks these activities:

• Contact your IT department early for assistance in preparing your laptop
• Or use a personal device instead

Machine Requirements:

• Windows or Max OS X
• 64-bit operating system
• 8 GB available RAM, 16 GB preferred
• 5 GB of HD space for Anaconda Python installation

Anaconda Python is used in this course because it is free, easy to install, and has all the needed libraries.

Setup:

Laptop preparation is required BEFORE the workshop. Instructions will be available on the seminar site prior to the first session.

There is no time allotted in class for laptop preparation.