Predictive Analytics and Big Data
This program comprises Module 3 of the Masters Certificate in Analytics for Leaders.
1. Introduction to Big Data
How are today’s most forward-thinking organizations using big data analytics and data science to make more informed business decisions? This opening module will explain all of the terminology and allow participants to see innovative examples of Big Data applications from different sectors – and begin evaluating how their organization can grow through more effective use of data analytics.
Participants will learn:
- How to organize and analyze large sets of data
- Discover patterns, correlations, trends, preferences, interactions and other useful details to support knowledgeable decisions
- How Big Data relates to cloud, mobility, security, social media and online business activities
- How Big Data analytics drives competitive advantage in your industry
2. Introduction to Predictive Modelling
Predictive analytics and modelling allow leaders to identify the likelihood of future outcomes based on historical data. With easy-to-use software, predictive analytics can be performed by any organizational manager to better predict future outcomes in their industry. This module teaches participants how to leverage predictive modelling to support their business decision making.
Participants will learn:
- How to use predictive modelling to streamline decision making and produce new insights that lead to better actions
- The types of data inputs being used in predictive modelling
- How to measure the probability of a future outcome
3. Advanced Topics in Decision Trees
Decision trees provide a very organized means for splitting a dataset into branch-like segments and then making organized strategic decisions around a particular object of analysis. In this module, participants will gain an understanding of the decision rules that form branches or segments of the tree-like network, and the values in input fields and target fields.
Participants will learn:
- The underlying rules that guide the decision tree
- How to describe the relationship between different variables
- How to build decision trees
- How to update existing decision trees as new information becomes available
4. Introduction to Regression Analysis
As organizations collect more data through advances in technology, business managers have improved opportunities to make data-driven decisions. This module teaches participants how to use regression analysis to identify the relationships between different business and data variables, and make future predictions with statistical support.
Participants will learn:
- How to use regression analysis in your organization
- Identifying what variables will predict an outcome in a particular population or data segment of interest
5. Introduction to Logistics Regression
Logistics regression is a popular statistical technique to model the probability of discrete outcomes – such as predicting whether a customer will re-purchase a product, remain a customer or respond to a direct marketing stimulus. During this module, participants will examine what attributes (variables) are effective for conducting logistics regression.
Participants will learn:
- Why this approach is particularly well suited for predicting future consumer behaviour
- How to apply logistics regression to current organizational planning issues
- Concepts of conditional random fields, an extension of logistics regression to sequential data