Descriptive & Diagnostic Analytics – I
This module focuses on how to extract information from datasets by algorithms that automatically build models from historical data and predict future behaviours of systems. Data analysis using supervised learning is particularly powerful where there is no mathematical model available and classical statistics offer limited insights (e.g., market analysis, PID parameter tuning).
This module aims to provide an introduction to fundamental techniques of data diagnostics based on supervised learning, with the help of a number of numerical examples and real applications. Students will learn the fundamental concepts of the supervised machine learning and will apply these concepts to analyse data by using the most advanced software tools and programming languages.
Principal Learning Outcomes
By the end of module, students will be able to:
• Demonstrate knowledge and understanding of fundamental concepts of diagnostics and descriptive analytics.
• Decide whether supervised learning is the only/best choice for analysing data, compared to classical statistical analysis.
• Select and apply supervised learning algorithms by suitable programming languages and software suites.
• Describe limits and assumptions inherent to supervised learning from data.