Prerequisite: See below
This workshop can also be delivered using R.
Any team can employ machine learning to analyze data and discover powerful insights for the business. This three-day intensive workshop is designed to springboard teams with foundational skills in Python into applying machine learning to their business data.
The curriculum is designed specifically for any professional and does not require any previous background in advanced mathematics or statistics. Attendees build practical, actionable skills via nine hands-on labs using free, open source software.
Attendees will receive a thorough introduction to state-of-the-art machine learning techniques. Topics covered include how algorithms work, how to engineer features for the best predictive models, how to tune models for optimal predictive performance, and how to discover hidden structures in data using cluster analysis.
Although this workshop contains some mathematics, the math level is accessible to a broad audience and focuses on concepts, not calculations.
Your Team Will Learn:
- The different types of machine learning
- The two forms of supervised learning: classification and regression
- The CART classification tree algorithm
- The mathematics of classification trees
- Overfitting—the bugbear of machine learning
- The bias-variance tradeoff
- How to tune CART classification tree models
- How to measure the accuracy of your classification tree models
- How to engineer predictive features for your decision tree models
- The CART regression tree algorithm
- The mathematics of regression trees
- The random forest algorithm
- How to tune random forest models
- How cluster analysis differs from other forms of machine learning
- Use cases for cluster analysis
- The different types of clustering algorithms
- The k-means clustering algorithm
- How to optimize the number of k-means clusters
- The DBSCAN clustering algorithm
- How to optimize the clusters found by DBSCAN
- How to reduce dimensionality using principal component analysis (PCA)
- How to handle categorical data with one-hot encoding
- How to handle categorical data with factor analysis of mixed data (FAMD)
- Additional resources for honing machine learning skills
- Business and data analysts
- BI and analytics developers and managers
- Business users
- Data scientists
Anyone interested in using machine learning with their business data
No background in advanced mathematics or statistics is required.
Students must be familiar with Python and Jupyter notebooks or complete the prerecorded course “Python Quick Start” prior to the class. This prerecorded course will be made available in advance to any students who need it.
Attendees will need a laptop computer with specific software installed before the session. In advance of the class; attendees will receive detailed software download and installation instructions.