GLBH0031 - Academic year 2023/2024
Course summary for exam preparation
1) Compartmental Modelling
• Understand the relationship between compartment, arrows and corresponding equations.
• Be able to draw conclusions about the behaviour of a system by looking at its graph.
2) Machine Learning
• Understand the difference between different types of learning.
• Understand the steps that make the algorithms studied in class work.
• Understand the role and definition of expectation, variance and covariance.
• Conducting linear regression analysis in matrix form (manually on pen and paper); assessing the goodness offit; setting up and execute a supervised machine learning analysis using linear regression.
3) Capacity planning
• Assumptions that enable analysis of an M/M/squeueing system (distributions, steady-state condition).
• Formulas for M/M/sand M/M/∞ queueing systems (probability of having N customers in the system, expected waiting time in the queue, expected time in the system, expected queue length, expected number of customers in the system), including application of Little’slaw.
• Conditions enabling analysis of queueing networks using Queueing Theory formulas.
• Being able to recognise the right formulas to apply.
• Defining scenarios based on problem description.
• Analysing scenarios and draw conclusions.
• Differences between stochastic simulation and analytical modelling (pros and cons of the two approaches).
4) Python
• Being able to reproduce the code seen in practical sessions, adapted to the case at hand.