Advanced Data Analytics

Advanced Data Analytics is available as a postgraduate-level subject offered by the International College of Management, Sydney (ICMS). Please click the button below to find a postgraduate course.

Subject Code:

DAT803A

Subject Type:

Specialisation

Subject Level:

800

Pre-requisite:

DAT701A Analytics for Business Intelligence 

ICT701A Software Design and Construction 

Course level study pre-requisite: a total of 16 credit points (4 subjects) prior to enrolling into the subject. 

Credit Points:

4 credit points

Subject Aim:

To successfully navigate today’s complex business landscape, organisations need to adopt advanced analytical capabilities that go far beyond traditional descriptive and diagnostic analysis techniques. Advanced forms of analytics use inferential statistics and can help businesses to discover deeper insights on customer preferences, market trends, and key business activities.

This subject will introduce students to the relevant predictive and prescriptive data analysis techniques designed to develop data-driven solutions to complex business problems. The subject will cover foundations of advanced data analysis including probability distributions, random sampling, confidence interval estimation, and hypotheses development and testing. Using real-world examples, students will learn how to apply regression and classification techniques to make predictions, and perform time series analysis and forecasting. The basics of text and natural language processing as well as graph analysis will be covered.

Learning Outcomes:

a) Apply advanced analytical methods and underlying statistical techniques to provide solutions to complex business problems. 

b) Critically evaluate business challenges, identify analytical gaps, and develop an analytics plan utilising advanced data analytical techniques and tools.

c) Apply statistical fit assessment tests to  assess the quality and accuracy of prediction models.

d) Construct and run classification algorithms to generate insights on a complex business problem and to provide recommendations for management.

e) Effectively communicate the steps and results of advanced data analysis to technical and non-technical audiences with the goal to drive innovation and change within an organisation.

Assessment Information:

Learning outcomes for this subject are assessed using a range of assessment tasks as described in the table below.

Broad topics to be covered: 

Week 1: Introduction to advanced data analytics

• Relevance of advanced data analytics
• Conceptual foundations
• Differences between descriptive and inferential analytics
• Analytics hardware, software, and network implications for organisations
• Challenges associated with analytics

Week 2: Probability and distributions

• Probability rules
• Subjective and objective probability
• Probability distribution of discrete and continuous random variables
• Types of probability distributions (Bernoulli distribution, uniform distribution, binomial distribution, normal distribution, Poisson distribution, exponential distribution)

Week 3: Sampling methods and distribution

• Sampling types (random sampling, systematic sampling, stratified sampling, cluster sampling, multistage sampling)
• Estimation errors
• Distribution of the sample mean
• Central Limit Theorem

Week 4: Confidence interval estimation

• Sampling distribution
• Confidence interval for a mean, total, proportion
• Confidence interval for a standard deviation
• Confidence interval to compare means and proportions

Week 5: Hypothesis development and testing

• Null and alternative hypothesis
• One-tailed vs. two-tailed tests
• Type 1 and type 2 error
• Significance level
• Hypotheses test and confidence intervals
• Tests for normality

Week 6: Estimating relationships with regression and clustering

• Graphical relationships: scatterplot
• Indicators of a linear relationship (correlation)
• Linear und multiple regression (least square estimation, standard error of estimate, R-square)
• Fit assessment
• Hard clustering and soft clustering
• Clustering techniques (k-means, hierarchical clustering)

Week 7: Predictions with classification algorithms

• Logistic regression
• K-Nearest Neighbours (kNN)
• Decision trees
• Naïve Bayes
• Random Forrest
• Support Vector Machine

Classification accuracy and precision evaluation

Week 8: Association rules

• Business use cases
• Apriori Algorithm
• Measures of confidence, lift, and leverage
• Output rule generation
• Validation methods
• Approaches to improve Apriori’s efficiency

Week 9: Time series analysis

• Application cases
• Components of time-series models
• Autoregressive models
• Moving average models
• ARMA and ARIMA

Week 10: Text and sentiment analytics

• Text mining with NLP
• Steps in text mining
• Raw text collection
• Text transformation techniques
• Term Frequency—Inverse Document Frequency (TFIDF)
• Sentiment analysis application and processes
• Tools for text mining and sentiment analysis

Week 11: Web and social media analytics

• Web content and web structure mining
• Graph databases
• Conceptual foundations of search engine and search engine optimization
• Web and social media usage mining techniques
• Web and social media analytics tools

Please note that these topics are often refined and subject to change so for up to date weekly topics and suggested reading resources, please refer to the Moodle subject page.