MSc Data Science and its Applications

Program Overview

---

Our MSc Data Science and its Applications is a conversion course, designed for students with only a little prior experience of university-level mathematics and statistics, who want to be part of our fast-growing digital economy (students with no exposure to university-level mathematics may consider our MSc Applied Data Science ). This course will place you at the core of data science, with the application of theory and methods to real-world problems, including the use and exploitation of big data. At Essex, the techniques we use to model and manipulate data guide the political, financial and social decisions that shape our modern society and are the basis of growth of the economy and success of businesses. The course introduces you to programming with the R language and as well as text analytics. Relational databases and SQL are developed and used for relevant applications from humanities, life sciences, linguistics, marketing and social science. The course encourages statistical thinking by data visualisations and guides you to develop your creativity within a scientific framework. You cover topics such as:

• Modelling experimental data
• Machine learning and decision making
• Applied statistics
• Combinatorial optimisation
• Statistical methods
• Stochastic processes

The leading department on this course, our Department of Mathematical Sciences , is genuinely innovative and student-focused. Our research groups are working on a broad range of collaborative areas tackling real-world issues. The Department of Mathematical Sciences and our School of Computer Science and Electronic Engineering are working together with other departments across the University to deliver optional modules and summer projects with Essex Business School, the Department of Language and Linguistics, the School of Life Sciences, the School of Philosophy and Art History, and the Department of Psychology. Our course also benefits from many Knowledge Transfer Partnerships which support students through placements and an interdisciplinary outreach culture. The University of Essex is committed to transformational education and inclusion, focused on learning opportunities for every student, responsive to our students’ needs and aspirations. Our MSc Data Science and its Applications course reflects this by supporting every student, from every background, and removing the barriers to their education. This course is developed in collaboration with industry partners and public sector organisations, which include BT, Profusion, Essex County Council, Essex Police, and Suffolk County Council. Our active links with industry can broaden your employment potential and offer placement opportunities. This course is available on a full- and part-time basis, starting in October. You can also start this course in January, but this option is only available to those who wish to study full-time. Why we're great.

• We are international leaders in data science education for the digital industry.
• We offer you access to specialist research facilities such as the UK Data Archive and our Institute for Social and Economic Research (ISER), both located on campus.
• We have active links with industry to broaden your employment potential and placement opportunities.

Our expert staff

Today’s data scientists are creative people who are focused and committed, yet restless and experimental. We are home to many of the world’s top scientists, and our staff are driven by creativity and imagination as well as technical excellence. We conduct world-leading research in areas such as artificial intelligence, explorative data analysis, machine learning, classification and clustering, evolutionary computation, data visualisation and financial forecasting. Specialist staff at Essex working on data science across our departments include:

• Dr Yanchun Bao – longitudinal and survival analysis, causal methods, instrumental methods (Mendelian Randomization), covariance modelling, mediation analysis
• Professor Luca Citi – machine learning, learning from biological signals and data (EEG, etc)
• Professor Edward Codling - animal movement and dispersal, random walks and diffusion, path analysis of movement data, behaviour of animal groups, human crowd behaviour
• Dr Stella Hadjiantoni – estimation of large-scale multivariate linear models and applications, numerical methods for the development of recursive regularisation and machine learning algorithms, numerical linear algebra in statistical computing and data science, numerical methods for handling high-dimensional data sets
• Dr Andrew Harrison – bioinformatics, big data science
• Professor Berthold Lausen – biostatistics, classification and clustering, data science education, event time data, machine learning, predictive modelling
• Dr Osama Mahmoud – biostatistics, data science, machine learning, Mendelian Randomization
• Dr Yassir Rabhi – mathematical statistics, mathematical foundations of data science
• Professor Abdel Salhi – optimisation mathematical programming and heuristics (evolutionary computing, nature-inspired algorithms, the Strawberry Algorithm), numerical analysis data mining (big data) bioinformatics
• Dr Dmitry Savostyanov – high-dimensional problems, tensor product decompositions
• Dr Alexei Vernitski – machine learning in mathematics; reinforcement learning applied to knot theory; mathematical education, and in particular, increasing motivation of learners of mathematics
• Dr Spyros Vrontos – actuarial mathematics and actuarial modelling
• Dr Jackie Wong Siaw Tze – Bayesian estimation, MCMC methods
• Dr Xinan Yang – approximate dynamic programming, Markov decision process

---

Specialist facilities

• All computers run either Windows 10 or are dual boot with Linux
• Software includes R, Python, SQL, Hadoop and Sparc
• We also have specialist facilities for research into areas including non-invasive brain-computer interfaces, intelligent environments, robotics, optoelectronics, video, RF and MW, printed circuit milling, and semiconductors
• Collaborate with the Essex Institute of Data Analytics and Data Science (IADS) and the ESRC Business and Local Government (BLoG) Data Research Centre of the University of Essex
• The UK Data Archive and the Institute for Social and Economic Research (ISER) at Essex contribute to our internationally outstanding data science environment

---

Your future

With a predicted shortage of data scientists, now is the time to future-proof your career. A successful career in data science requires you to possess truly interdisciplinary knowledge and our staff ensure that you graduate with a wide-ranging, yet specialised, set of skills in this area. Data scientists are required in every sector, carrying out statistical analysis or mining data on social media. Our graduates are highly sought after by a range of businesses and organisations and find employment in financial services, scientific computation, decision making support and government, risk assessment, statistics, education and other areas. Our recent graduates have gone onto work as data scientists and data analysts in both the private and public sectors. We also offer supervision for PhD, MPhil and MSc by Dissertation. We additionally work with our Employability and Careers Centre to help you find out about further work experience, internships, placements, and voluntary opportunities.

Program Outline

Course structure

Our research-led teaching is continually evolving to address the latest challenges and breakthroughs in the field. The following modules are based on the current course structure and may change in response to new curriculum developments and innovation. The structure below is representative of this course if taken full-time. If you choose to study part-time, the modules will be split across two years. Please note that if you are studying full-time (either starting in October or January) there is no second year; you will develop your dissertation throughout the course of your single year. We understand that deciding where and what to study is a very important decision for you. We’ll make all reasonable efforts to provide you with the courses, services and facilities as described on our website. However, if we need to make material changes, for example due to significant disruption, or in response to COVID-19, we’ll let our applicants and students know as soon as possible.

---

---

Components

Components are the blocks of study that make up your course. A component may have a set module which you must study, or a number of modules from which you can choose. Each component has a status and carries a certain number of credits towards your qualification.

Status	What this means
Core	You must take the set module for this component and you must pass. No failure can be permitted.
Core with Options	You can choose which module to study from the available options for this component but you must pass. No failure can be permitted.
Compulsory	You must take the set module for this component. There may be limited opportunities to continue on the course/be eligible for the qualification if you fail.
Compulsory with Options	You can choose which module to study from the available options for this component. There may be limited opportunities to continue on the course/be eligible for the qualification if you fail.
Optional	You can choose which module to study from the available options for this component. There may be limited opportunities to continue on the course/be eligible for the qualification if you fail.

The modules that are available for you to choose for each component will depend on several factors, including which modules you have chosen for other components, which modules you have completed in previous years of your course, and which term the module is taught in.

---

---

Modules

Modules are the individual units of study for your course. Each module has its own set of learning outcomes and assessment criteria and also carries a certain number of credits. In most cases you will study one module per component, but in some cases you may need to study more than one module. For example, a 30-credit component may comprise of either one 30-credit module, or two 15-credit modules, depending on the options available. Modules may be taught at different times of the year and by a different department or school to the one your course is primarily based in. You can find this information from the module code . For example, the module code HR100-4-FY means:

HR	100	4	FY
The department or school the module will be taught by. In this example, the module would be taught by the Department of History.	The module number.	The UK academic level of the module. A standard undergraduate course will comprise of level 4, 5 and 6 modules - increasing as you progress through the course. A standard postgraduate taught course will comprise of level 7 modules. A postgraduate research degree is a level 8 qualification.	The term the module will be taught in. AU : Autumn term SP : Spring term SU : Summer term FY : Full year AP : Autumn and Spring terms PS: Spring and Summer terms AS: Autumn and Summer terms

Year 1 COMPONENT 01: CORE WITH OPTIONS MA981-7-FY or MA983-7-SU (60 CREDITS) In a world increasingly driven by data, the need for analysis and visualisation is more important than ever. In this module you will look at data through the eyes of a numerical detective. You will work on the lost art of exploratory data analysis, reviewing appropriate methods for data summaries with the aim to summarise, understand, extract hidden patterns and identify relationships. You will then work on graphical data analysis, using simple graphs to understand the data, but also advanced complex methods to scrutinise data and interactive plots to communicate data information to a wider audience. For data analysis and visualisations you will use R-studio, and a combination of R-shiny applications and google visualisations for interactive plotting. View Data Visualisation on our Module Directory The module will introduce you to concepts from data analysis and statistics and show how they can be applied effectively via the R language. It will cover a wide introduction to statistics and provide practical experience of real-world examples of how statistics is used to gain insights. Throughout these examples, and many more, we will teach programming techniques that will enable you to apply statistical approaches to real-world applications. This module assumes no previous exposure to statistics. View Data analysis and statistics with R on our Module Directory This module will introduce you to the underlying principles and basic concepts of programming with the R language. It will cover a wide range of analytics, provide practical experience of powerful R tools, and present real-world examples of how data and analytics are used to gain insights and to improve a business or industry. These examples include string processing, text analytics, and sentiment analysis. Throughout these examples, and many more, we will teach programming techniques that will enable you to apply advanced data science approaches to real-world applications. This module assumes no prior programming skills. View Programming and Text Analytics with R on our Module Directory Relational databases and SQL are developed and used as a fundamental tool for relevant applications from different disciplines including humanities, life sciences, linguistics, marketing and social science. They are essential to the efficient information management for IT systems and commercial applications in almost all modern organisations. The purpose of this module is to provide you with an introduction to the underlying principles and practical experience of the design and implementation of relational databases. It will cover the data modelling and SQL, database analysis, design and management, and advanced topics including big data, security and privacy issues of modern databases. View Databases and data processing with SQL on our Module Directory This module will introduce you to the principles for the application of linear modelling methodologies for the analysis of experimental and observational data. The first strand of the module will study the assumptions of the general linear model. Collinearity, influential data, assessing the fitted model and model selection techniques will be discussed. The second strand will introduce statistical methods for the efficient analysis of experiments when the data are normally distributed, for example one-way ANOVA. The methodology will be extended to logistic regression and the analysis of contingency tables when the variable of interest is categorical. The third strand of the module will study various multivariate methods for the analysis of large and high-dimensional data sets. View Modelling experimental and observational data on our Module Directory COMPONENT 07: OPTIOL Option from list (15 CREDITS) COMPONENT 08: COMPULSORY WITH OPTIONS CE156-7-AU or MA214-7-SP (15 CREDITS) COMPONENT 09: COMPULSORY WITH OPTIONS MA336-7-SP or CE802-7-SP (15 CREDITS) What skills do you need to succeed during your studies? And what about after university? How will you realise your career goals? Develop your transferable skills and experiences to create your personal profile. Reflect on and plan your ongoing personal development, with guidance from your personal advisor within the department. View Research Skills and Employability on our Module Directory

---

---

Teaching

• Core components can be combined with optional modules, to enable you to gain either in-depth specialisation or a breadth of understanding
• Learn to use LATEX to produce a document as close as possible to what professional mathematicians produce in terms of organisation, layout and type-setting
• Our postgraduates are encouraged to attend conferences and seminars

---

---

Assessment

• On this course you are assessed mostly by coursework and projects, but this does vary from module to module
• Some modules may also incorporate written examinations

---

---

Dissertation

• You will be provided with a list of dissertation titles or topics proposed by staff and it may be possible to propose a project of your own
• Most dissertations are between 10,000 and 30,000 words in length. However, these are guidelines, not mandatory word counts
• Close supervision by academic staff