Applying machine learning to the right problems
An Introduction to Machine Learning
Machine learning is an important tool when applied to the right problem. William Myers, Principal Statistician at Procter & Gamble, emphasizes that the first step – clearly defining the problem – is vital any time you are considering data collection or statistical analysis.
“What you don’t want is a great solution to the wrong problem, or a solution that is too narrow for the project,” says Myers. For example, is your goal to develop a statistical model for the purpose of explaining, predicting or possibly both?
Watch to learn more about:
- A simple definition of machine learning and associated terms.
- Two general machine learning categories: supervised and unsupervised learning.
- Examples of how machine learning is used in industry.
- Critical steps to take before building a machine learning model.
- Advanced methods for more complex or unstructured data.
TEL Singapore finds a competitive advantage through analytics automation
Miao Chen, a data scientist at TEL Singapore, describes how analytics plays a key role in helping organizations develop and maintain their competitive advantage – and how automation has become increasingly important to many industries.
Chen talks about automation as a promising way for a variety of functional teams in an organization to overcome the complexity of data sources, ease the shortage of right resources and accelerate the process of extracting value from data. This presentation provides some basic background on automation in analytics, as well as the benefits of and techniques for automating analyses using JMP® scripts.