MSc Applied Data Analytics
Queen Mary University of London
The MSc Applied Data Analytics developed by Queen Mary University of London is designed to develop the skill set required for a successful career in data analysis—today and in the future.
In year one of the degree you will develop machine learning skills and the ability to store, manipulate and display data. You’ll also look at both theory and applications for different time series models that are widely used in practice.
In year two you’ll build familiarity with a variety of tools and measures for the analysis and visualisation of network data and an overview of different techniques to transform other kinds of data sets into graphs. You will develop your understanding of the basic optimisation techniques employed in business and will finish the degree by embarking on a four-week project that will require you to build reports that will be compiled into a portfolio. Once you have graduated you will be able to keep up to date with industry trends and understand the theory and practice of data analysis.
When you graduate, you’ll be able to:
- Understand the mathematical foundations of data analysis
- Gain experience with a wide variety of data
- Use a variety of statistical techniques, including Bayesian approaches, time series analysis, and more
- Keep up to date with industry trends through study of techniques and methodologies such as numerical computing and optimisation techniques.
- Understand the theory and practice of data analysis, as reinforced through independent projects
- Learn how to deal with data with a time aspect, graph and network-based data analysis, and standard tools in machine learning
Machine Learning 1
In this module, you’ll develop machine learning skills which will be primarily based on the Python programming language as it is currently used in industry. Presented methods include: regression and classification techniques (linear and logistic regression, least-square); clustering; dimensionality reduction techniques such as PCA, SVD and matrix factorization. More advanced methods will be covered in a follow-up module (Machine Learning 2).
Probability and Statistics
In this module, you’ll learn some of the essential theoretical notions of probability and the distributions of random variables which underpin statistical methods. You’ll also learn different types of statistical tests of hypotheses and address the question of how to use them, and when to use them. This material is essential for the proper use of statistics in applications.
Storing, Manipulating, and Visualising Data
In this module, you’ll be introduced to many of the most widely-used techniques in the field for storing, manipulating, and displaying data. The emphasis will be on using tools interactively rather than programming. You’ll learn best practices for data visualisation, as well as various methods for preparing data for further analysis.
In this module, you’ll learn the fundamentals of modern time series analysis. You’ll look at both theory and applications for different time series models that are widely used in practice. As you progress through your coursework, you’ll gain hands-on experience applying the methods you’ve learned to real-world case studies.
In this module, you’ll get introduced to the Bayesian paradigm, and explore some of the problems with frequentist statistical methods. You’ll discover how the Bayesian paradigm provides a unified approach to problems of statistical inference and prediction and enables you to make Bayesian inferences in a variety of problems, and you’ll witness the use of Bayesian methods in real-life examples.
Capstone Research Project
The aim of this module is for you to apply what you’ve learned throughout the MSc to a four-week project. You can choose to deepen your understanding of particular techniques in data analytics or perform an in-depth investigation of a dataset. To successfully complete your project, you’ll also need to communicate your results in the form of reports that will then be compiled into a portfolio.
Network-based Data Analysis
In this module, you’ll cover methods to handle, cleanse, represent, and store network data sets efficiently. You’ll build familiarity with a variety of tools and measures for the analysis and visualisation of network data and get an overview of different techniques to transform other kinds of data sets into graphs—including time-series and spatial distributions, which are typically not presented as graphs, but which can benefit from a network-based analysis.
Machine Learning 2
The aim of this module is for you to get introduced to more advanced machine learning techniques. An emphasis will be on current techniques which are relevant for practical applications. In addition to practical programming assignments, you’ll also develop your understanding of the mathematical underpinning of the techniques and the limitations of the methods, which are crucial for correctly assessing their performance.
In this module, you’ll develop your understanding of the basic optimization techniques employed in business. You’ll also refine your critical thinking through the study of business problems with incomplete or imprecise requirements.
This module will build upon previously taught statistical methods to show how they can be extended to deal with various issues that arise in realistic data analysis, such as non-normal outcomes, grouped data, non-random samples and missing data. Among the topics you’ll cover are: generalised linear models; hierarchical models; model checking and model comparison. You’ll apply these methods to real datasets throughout the module, using the R statistical computing language.
This module focuses on using computers to solve numerical problems that arise in applied data analytics. The goal is for you to possess the proper computational tools to solve problems you're likely to encounter when dealing with data and for you to establish a solid understanding of the numerical issues that arise in the applied sciences—particularly in the context of commonly used programming languages such as Python. The topics covered will include the basics of scientific programming, polynomial interpolation, numerical differentiation and integration, numerical solution of ordinary and partial differential equations, random numbers and Monte Carlo methods, and simulation of stochastic processes. The module's emphasis is on numerical aspects of mathematical problems, with a focus on applications rather than theory.
Capstone Research Project
The aim of this module is for you to apply what you’ve learned in the MSc to a four-week project. You can choose to deepen your understanding of particular techniques in data analytics, or do an in-depth investigation of a data set. You will also need to communicate your results in the form of reports that will be compiled into a portfolio.
It is required that students take 24 months to complete the programme.
Coursera on Mobile
Access all course materials anywhere with the mobile app, used by over 80 percent of degree students on Coursera. Available on iOS and Android.
Using the mobile app, learners can:
- Save a week’s worth of content for offline access with one click
- Save and submit quizzes offline
- View text transcripts of lecture videos
- Take notes directly in the app
- Set reminder alerts to help you make progress
Baixe o aplicativo móvel da Coursera
Coursera does not grant credit, and does not represent that any institution other than the degree granting institution will recognise the credit or credential awarded by the institution; the decision to grant, accept, or transfer credit is subject to the sole and absolute discretion of an educational institution.
We encourage you to investigate whether this degree meets your academic and/or professional needs before applying.