Welcome to the course page for Predictive Modelling Training Course SPC-7840.
Here you will find information and available online content for this course.
This course is an introduction to the core concepts in predictive modelling and fundamentals of data science. The training focuses on the foundations of data modelling and data science.
The skills taught are transferable to all predictive modelling software platforms, and the course does not involve extensive coding, or require any coding knowledge or experience. A tool with a graphical user interface is used so the students can focus on learning the central skills and concepts of data modelling while completing practical exercises.
Key skills taught include building, assessing, selecting, and deploying predictive models. Students also employ some of the most used methods in the field, including general linear models (GLMs), and more advanced methods, thereby obtaining practical experience with predictive analytics basics.
Course Leader
Eugene is a leader in the analytics field in Australia, with 20 years’ commercial data science experience. He is the head of the Sydney Data Science group (3,000+ members), the Sydney Users of R Forum (1,900+ members), and Datapreneurs (400+ members). He is regularly invited to be a conference presenter, consultant and advisor, and appears in print and on television to discuss data science and analytics. Eugene also applies data science in an entrepreneurial setting, to financial trading and online startups, and is the creator of ggraptR, an interactive visualisation package in R.
He is a Director at Presciient, providing analytics capability, development services including team selection, training, and executive coaching for team owners and sponsors. They also provide strategic advisory, communications and specialised advanced data analysis.
Core sessions
Main course: 16th & 17th August 2022. (1100-1645 AEST)
Follow up workshop: 24th August 2022. (1300-1500 AEST)
Monthly Mentoring Sessions
(Dates and times TBC):
- September 2022
- October 2022
- November 2022
- February 2022
- March 2022
- April 2022
- May 2022
- June 2022
Feedback
We welcome and value your feedback, good and constructive! Please complete our quick online feedback survey
Online Learning Resources
Course Session Recordings
These recordings are password protected and for the use of registered attendees only. To obtain the password contact your internal administrator.
Any usage outside of this is strictly prohibited and against the terms of agreements SPC-7840 and PO2300002930.
August 16, 2022: Session 1
- Introduction, housekeeping.
- What is Data Science? pt 1
August 16, 2022: Session 2
- What is Data Science? pt 2
- What is a predictive Model? pt 1
August 16, 2022: Session 3
- What is a predictive Model? pt 2
August 16, 2022: Session 4
- Lab: Loading Data, Data Exploration, Creating Visualisations
August 17, 2022: Session 1
- Classification and Regression
- Decision Trees for classification
- Decision Trees for regression
August 17, 2022: Session 2
- Linear Models for regression
- Logistic regression for classification
- Model Selection and out-of-sample testing
August 17, 2022: Session 3
- Thresholds and the confusion matrix
- The Value Measure
- Threshold selection
August 17, 2022: Session 4
- Predictive Modelling (II)
- Generate and deploy a predictive model
- Thresholds and the confusion matrix
- The Value Measure
- Threshold selection
- Area under the curve
August 24, 2022: Workshop session
- Model Stability
- K-fold cross validation
- Random Forest
- Ensembles
- Bootstrapping
- Out-of-Bag estimation
