Master in Data Science

Module description

This module inculcates practical understanding and a framework that allows the execution of essential analytics actions such as extracting, cleaning, changing, and analysing data. In this module, learners grasp the knowledge of programming languages, tools, frameworks, and libraries utilised throughout the course to acquire and model data sets. Data analysis is accomplished through visualising, summarising, and developing rudimentary data handling abilities by paying attention to variable types, names, and values. In addition, managing data using dates, strings, and other elements, enhances learners’ abilities to perform data research and generate visualisations.

Learning Outcomes

L01: Analyse information using data visualisation, summary, and counting tools.

L02: Acquire rudimentary skills in data handling, focusing on variable types, names, and values.

L03: To learn how to use the pipe operator to combine numerous tidying operations in a chain.

L04: The ability to work with data that includes dates, strings, and other variable 

Content Covered

•  Data Cleaning Techniques
•  Data Preprocessing
•  Data Manipulation
•  Core Python Programming
•  Data Visualisation using Matplotlib
•  Linear Algebra
•  Statistics and Probability
•  Exploratory data analysis
•  Variance, Standard Deviation, Median
•  Bar charts and Line charts
•  Python libraries and framework in data analysis
•  2D Scatter Plot
•  3D Scatter plot
•  Pair plots
•  Univariate, Bivariate, and Multivariate
•  Histograms
•  Boxplot
•  IQR (InterQuartile Range)
•  Data analysis with Pandas

Module Description

The data mining process includes collecting necessary information from enormous databases that help make a knowledgeable decision. The module demonstrates data mining techniques like data processing, pattern discovery, and trends in information. These methods are employed to obtain the skills and abilities for applying data integration, cleansing, selection, and transformation on tables and graphs for knowledge discovery. Python matrix libraries allow learners to construct some realistic representation of text mining by executing tasks such as classification, estimation, segmentation, forecasting, sequence, and data association.

Learning Outcomes

LO1: Understand the fundamentals of text mining and analysis, including identifying exciting patterns, extracting helpful knowledge, and supporting decision-making.

LO2: Explore fundamental principles of text mining and essential algorithms and some of their practical applications.

LO3: Be able to apply the learned knowledge and skills to implement scalable pattern discovery techniques on large volumes of transactional data

LO4: Engaging in meaningful discussions about pattern evaluation metrics and investigating techniques for mining various patterns, including sequential and sub-graph patterns. 

Content Covered

•  Introduction to Data mining
•  Data Mining in a Python-based environment
•  What is a data warehouse
•  How to find patterns?
•  Affinity Analysis
•  Product rесоmmendаtіоn
•  Introduction to Database Mining
•  Databases and SQL
•  DDL, DML, Joins, and Schemas
•  How to use Python Matrix Libraries on Datasets.
•  Lоаd the Dataset with NumPy
•  Mining-friendly data representations
•  Text Representation for Data Mining.
•  Why is text complex?
•  Text mining
•  Data Modelling, Evaluation, and Deployment in Text Mining
•  Exemplary techniques: Bag of words representation in Text Mining
•  Frequent Subgraph Mining
• Data Filtering
• Power Query Editor
•  Risk Analysis
•  Sensitivity Analysis

Module Description

This module provides extensive knowledge of splitting data into training, validating, and creating test sets. Develop and assess predictive mining models by integrating a framework and practical perception. There are numerous performance metrics for estimation and categorization systems presented. The most prevalent predictive modelling approaches, including artificial neural networks, support vector machines, k-nearest neighbour, Bayesian learning, ensemble models, and different decision trees, are reviewed in this module, along with their internal workings, capabilities, and applications. Most of these strategies can tackle prediction difficulties of the classification and regression kinds. They are commonly employed to address challenging prediction challenges when other, more traditional approaches fail to deliver results.

Learning Outcomes

LO1: Introduce the fundamental algorithmic concepts, including sorting and searching, divide and conquer, and complex algorithms.

LO2: Sort data and use it for search; break down a huge problem into smaller ones and answer them recursively; apply dynamic programming to genomic research; and more.

LO3: Discuss and construct the most often used data structures for modern computing

LO4: To be able to use the most industry-used data structures in modern computing

Content Covered

•  Static Holdout Method
•  k-Fold Cross-Validation
•  Class Imbalanced Data
•  Evaluating the Classification of Categorical Outcomes
•  Evaluating the Estimation of Continuous Outcomes
•  Logistic Regression
•  K-nearest Neighbour
•  Nearest Neighbor Method for Prediction
•  Classification and Regression tree
•  Support Vector Machines
•  Process-Based Approach to the Use of SVM
•  Naïve Bayes Methods
•  Bayesian Networks
•  Neural Network Architectures
•  Ensemble Modelling

Course Description

This module gives learners the insight to apply many prediction models and grasps linear regression. Create predictions based on a group of input variables using regression analysis methods. Learners investigate the way to model an extensive range of real-world interactions using complicated statistical methodologies, such as generalised linear and additive models. This module inculcates intermediate and advanced statistical modelling methodologies. It is specifically created for learners to develop proficiency in linear regression analysis, experimental design, and extended linear and additive models. Based on these skills, interpreting data, discovering links between variables, and generating predictions are made simpler via intuitive representations.

Learning Outcomes

LO1: Differentiate between various types of predictive models and Master linear regression

LO2: Understand the inner workings through algorithms of different models

LO3: Analyse and explore the results of logistic regression and understand when to discriminant analysis

LO4: Maximise analytical productivity by analysing different models and interpreting their accuracy in a well-organised manner

Content Covered

•  Selecting a Sample
•  Point Estimation
•  Sampling Distributions
•  Interval Estimation
•  Hypothesis Tests
•  Statistical Inference and practical significance
•  A Simple Linear Regression Model
•  Least Square method
•  Inference and Regression
•  Multiple Regression Model
•  Logistics Regression
•  Predictions with Regression
•  Model Fitting
•  Tableau data model
•  Shape and data transformation using Tableau Query Editor
•  Tableau Report View

Course Description

In this module, learners will better grasp artificial intelligence (AI) applications in business and comprehend AI decision-making. Through breakthroughs in IoT and the emergence of Blockchain, this curriculum prepares students with a broad foundation of AI-enabled software solutions. As learners continue through this module, they become acquainted with the technology that powers the automated world—knowing the sorts of algorithms and how they may be utilised to enhance or replicate human behaviour across diverse applications. This module teaches about AI, IoT, Blockchain, and machine learning components while building on a solid conceptual framework that will present rigorous, hands-on, and step-by-step ways to tackle realistic, complex real-world challenges.

Learning Outcomes

LO1. Introducing Artificial Intelligence (AI), exploring its features and variants in the business domain. Furthermore, to understand the business context of AI and interpret AI decision-making.

LO2. Understand & create an AI implementation plan for a business setup through recognition of suitable model parameters

LO3: To further explore the components of Blockchain and understand Distributed Ledger Technology (DLT) concept, features, benefits, and relevance in application

LO4: Understanding Hyperledger, Smart Contracts, and IoT (Internet of Things) in applied business models to assess the impact in the long term

Content Covered

•  Introduction to Artificial intelligence
•  AI enables applications
•  What is Deep Learning
•  Artificial Neural Networks
•  Image Processing and OpenCV
•  Introduction to NLP
•  Artificial Neural Networks
•  Text Processing
•  Text Classification
•  Topic Modelling
•  Recurrent Neural Networks
•  Major components of IoT
•  Variety of Sensors
•  Actuators
•  IoT protocols at various layers
•  Applications and user interface in IoT
•  Smart factories of tomorrow and the Industrial Internet of Things
•  Introduction to Blockchains
•  Introduction and usage of Hyperledger and Smart Contract
•  Blockchains Structure
•  Centralised, Decentralised, and Distributed systems
•  Introduction to DLT
•  DLT features, benefits, and usage in Blockchain
•  Types of Blockchains
•  Why Blockchain?
•  Building AI and ML applications using Blockchain technology

Modules: Research Methods & Dissertation 

Module Description

The purpose of this module is to discuss and explain the role of Data science and its practices in an organisation and their influence on the overall performance and competence of the organisation. This module is designed to develop an understanding of the contemporary practices and competence to develop a research or design question, illustrate how it links to current knowledge and carry out the study in a systematic manner. Learners will be encouraged to pick a research/development project that displays their past learning in the data science domain. It is meant to acquire an understanding of Data Science and the paradigm shift in the approaches and methods related to various functions of DS like data visualisation, probability, inference and modelling, data mining, data organisation, regression, and machine learning to name a few. It also endeavours to highlight the role and significance of data analytics and data modelling during the planning, decision-making, and implementation of change in the organisation. Upon successfully completing the module, the participants will have comprehensive knowledge about the broader data analysis context and a data product to demonstrate their data science expertise to potential employers or educational programs.

Learning Outcomes

LO1: Conduct independent Research and Development within the context of a Data Science Project

LO2: Developing the ability to independently solve problems using analytics and data science

LO3: Communicate technical information clearly and succinctly to a broad, non-specialist audience.

LO4: Create detailed written documentation to a standard expected of a professional in the field of Data Science & evaluate Project outcomes with reference to key research publications in the relevant field.