Data Analytics courses

• Build a practical foundation in descriptive statistics by summarizing datasets, examining distributions, and interpreting measures of central tendency.
• Apply inferential statistical methods, including hypothesis testing, confidence intervals, and analysis of variance (ANOVA), to draw conclusions from samples.
• Introduce Bayesian statistics and probabilistic modelling as approaches for representing uncertainty and updating analytical conclusions as new evidence becomes available.
• Develop the ability to select and interpret statistical summaries and inferential methods according to the analytical question and characteristics of the available data.

• Analyze time-dependent data using time-series approaches such as ARIMA, state-space models, and spectral methods.
• Apply causal inference and experimental-design principles through A/B testing, randomized controlled trials, and quasi-experimental approaches to distinguish correlation from causal effects.
• Use survival analysis and reliability modelling to study time-to-event outcomes, duration, failure, and risk over time.
• Apply multivariate methods, including principal component analysis, factor analysis, cluster analysis, and discriminant analysis, to explore complex relationships across multiple variables.

• Build supervised learning models for regression and classification using methods such as support vector machines, random forests, and gradient boosting.
• Apply unsupervised learning techniques, including clustering and dimensionality reduction, to discover structure in data without predefined labels.
• Understand how deep learning architectures such as CNNs, RNNs, and Transformers can be applied to tabular and time-series analytics problems.
• Compare predictive approaches according to the structure of the data, the analytical objective, and the assumptions of the modelling method.

See also: AI Foundations courses →

• Use AutoML and hyperparameter-optimisation approaches to automate parts of model selection and configuration.
• Combine multiple predictive models through ensemble methods and model stacking to improve robustness and predictive performance.
• Evaluate models using appropriate validation strategies, cross-validation procedures, and generalisation principles to reduce overfitting and obtain credible performance estimates.
• Apply transfer-learning and few-shot-learning concepts when analytics tasks have limited labelled data or can benefit from knowledge learned in related domains.

• Understand distributed data processing with Hadoop MapReduce, Apache Spark, and Flink for analytical workloads that exceed the capacity of a single machine.
• Design streaming and real-time analytics workflows using technologies such as Apache Kafka, Flink, and Spark Streaming.
• Orchestrate repeatable data pipelines with tools such as Airflow, Prefect, and Dagster to coordinate ingestion, transformation, analysis, and downstream processing.
• Relate batch, streaming, and orchestration patterns to the latency, scale, reliability, and operational requirements of analytics systems.

• Understand data lake and lakehouse architectures and the role of technologies such as Delta Lake, Apache Iceberg, and Apache Hudi in modern analytical platforms.
• Compare NoSQL and NewSQL database approaches for analytical workloads with different scale, consistency, and access requirements.
• Use in-memory computing concepts and columnar storage formats such as Parquet and ORC to improve analytical processing efficiency.
• Design scalable analytical storage and processing architectures by matching data formats, database technologies, and compute patterns to business requirements.

• Clean analytical datasets by addressing missing values, inconsistent records, duplicate information, and other common data-quality problems.
• Apply imputation and outlier-detection methods while considering how data-cleaning decisions can affect subsequent analysis and modelling.
• Engineer and select useful features that represent relevant information for statistical and machine-learning models.
• Assess data quality before modelling and document the transformations applied to preserve analytical traceability.

• Integrate heterogeneous data sources through data matching, schema alignment, and transformation into analytically usable structures.
• Apply data profiling and metadata-management practices to understand dataset structure, provenance, completeness, and quality.
• Use synthetic-data generation approaches where additional training data or privacy-preserving alternatives are required.
• Understand active-learning and human-in-the-loop annotation strategies for efficiently improving labelled datasets and analytical systems.

• Apply natural language processing techniques such as sentiment analysis, named-entity recognition, and topic modelling to extract information from textual data.
• Understand how large language models can support text classification, generation, and other analytics tasks involving unstructured language data.
• Use computer-vision approaches for business analytics scenarios such as defect detection and document image analysis.
• Apply speech analytics and audio data-mining concepts to derive information from spoken and acoustic data.

• Combine text, image, and structured information through multimodal data-fusion approaches to support richer analytical tasks.
• Use knowledge graphs and semantic analytics to represent entities, relationships, and contextual knowledge across heterogeneous information sources.
• Design analytical workflows that integrate structured and unstructured enterprise data rather than treating each modality in isolation.
• Assess the opportunities and technical challenges involved in combining multiple modalities within practical analytics systems.

• Perform exploratory data analysis and use visual analytics to investigate distributions, relationships, patterns, and anomalies before formal modelling.
• Design interactive dashboards that organize key metrics and analytical information around a clear decision-making objective.
• Use data storytelling principles to connect visual evidence with a coherent analytical narrative for business and technical audiences.
• Apply geospatial analytics and cartographic visualisation to communicate patterns associated with locations, regions, and spatial relationships.

• Visualize networks and graphs to communicate relationships, connectivity, and structural patterns within complex systems.
• Represent uncertainty and model confidence in ways that help audiences interpret analytical results without overstating precision.
• Use narrative analytics to transform analytical findings into explanations that connect evidence, context, and implications.
• Understand automated report generation as a method for producing repeatable analytical summaries while maintaining human review of meaning and accuracy.

• Identify algorithmic fairness problems and assess how bias can enter datasets, analytical methods, and model outputs.
• Apply explainability and interpretability concepts, including approaches such as SHAP, LIME, and attention-based analysis, to communicate how models reach predictions.
• Understand privacy-preserving analytics techniques such as differential privacy, federated learning, and secure computation.
• Balance analytical performance with fairness, transparency, and privacy requirements when designing data-driven systems.

See also: Responsible AI courses →

• Understand how GDPR, CCPA, and related regulatory requirements affect the collection, processing, storage, and use of data in analytical pipelines.
• Build auditability and reproducibility into analytics workflows through documentation, traceability, repeatable procedures, and scientific-integrity practices.
• Assess the environmental cost of large-scale analytics, including the compute and energy implications of model training and inference.
• Integrate governance, compliance, reproducibility, and sustainability considerations into responsible analytics practice.

• Explore healthcare and clinical analytics applications involving electronic health records, genomics, and epidemiological data.
• Apply analytics concepts to finance through risk modelling, fraud detection, and algorithmic trading use cases.
• Understand marketing analytics through customer segmentation, attribution modelling, and customer lifetime value analysis.
• Use domain context to determine appropriate data, methods, evaluation criteria, and interpretations for applied analytics projects.

• Apply analytics to supply-chain and operations problems such as demand forecasting and optimisation.
• Explore HR and people analytics applications including talent acquisition, attrition prediction, and diversity, equity, and inclusion metrics.
• Understand sports analytics and performance modelling as examples of data-driven evaluation and prediction in specialized domains.
• Apply environmental and climate data analytics to investigate complex patterns, trends, and decision-support questions in environmental systems.

• Develop data literacy as an organisational capability that enables a broader workforce to understand, question, and use analytical information.
• Examine the democratisation of analytics and how self-service tools can expand access to data-driven decision-making beyond specialist teams.
• Understand analytics adoption and change-management challenges through perspectives such as the Technology Acceptance Model and Technology-Organization-Environment frameworks.
• Explore how data-driven culture and organisational learning influence whether analytics capabilities produce sustained business value.

• Understand DataOps and the operationalisation of analytics pipelines, including their relationship with MLOps and LLMOps practices.
• Use analytics maturity models, including approaches associated with Gartner and TDWI, to assess organisational capabilities and identify development priorities.
• Examine the role of the Chief Data Officer and the importance of data strategy in aligning analytics investments with organisational objectives.
• Connect technology, people, governance, operating models, and strategy when planning the long-term development of enterprise analytics capabilities.