Course content
9 modules · 48 hours. Open a module to see what it covers.
1 Introduction to Data Analysis and Generative AIObjectives · topics · practical exercise · 3 hours
Introduces data analysis, business intelligence, data-driven decision-making and the application of Generative AI in modern analytics.
Learning objectives
- Explain the data analysis process and identify suitable analytical questions.
- Describe ways AI can support analytical tasks and decision-making.
Topics covered 3 hours
- The data analysis lifecycle: collection, preparation, modelling, analysis, visualisation and communication.
- Structured versus semi-structured data; descriptive, diagnostic, predictive and prescriptive analytics.
- Introduction to Generative AI and large language models.
- Overview of ChatGPT, Microsoft Copilot, Gemini and Power BI Copilot.
- Prompt engineering for data analysis and AI-assisted data storytelling.
- Responsible AI: accuracy, bias, confidentiality and validation.
Practical exercise
Use a sample sales dataset to identify business questions and ask an AI assistant to suggest useful performance indicators.
Expected outcome
Learners understand how data analysis and AI work together to solve business problems.
2 Excel Fundamentals for Data AnalysisObjectives · topics · practical exercise · 6 hours
Builds the Excel skills needed to prepare, calculate, summarise and interpret business data before progressing to Power BI.
Learning objectives
- Organise datasets and apply formulas to answer business questions.
- Clean common data-quality issues and summarise information using PivotTables and charts.
Topics covered 6 hours
- Excel interface, workbooks, worksheets and structured tables.
- Sorting, filtering, data types and data validation.
- Essential formulas: SUM, AVERAGE, COUNT, IF, SUMIFS and COUNTIFS.
- Lookup functions: XLOOKUP and INDEX/MATCH; text, date and error-handling functions.
- Identifying duplicates, missing values and inconsistent records.
- Conditional formatting, PivotTables and PivotCharts.
- KPI summaries and introductory dashboard design.
- Using ChatGPT and Copilot to generate and explain formulas, troubleshoot errors and suggest analytical questions.
Practical exercise
Clean a sales or employee dataset, calculate KPIs, build PivotTables and prepare an Excel summary report.
Expected outcome
Learners can conduct basic business analysis in Excel and prepare datasets for advanced analytics.
3 Power Query and Power Pivot — Data Preparation and Modelling in ExcelObjectives · topics · practical exercise · 7 hours
Introduces repeatable data preparation and relational data modelling through Excel Power Query and Power Pivot.
Learning objectives
- Import and transform data from multiple sources.
- Build relationships between fact and dimension tables and create basic DAX calculations.
Topics covered 7 hours
- Import data from Excel workbooks, CSV files and other supported sources.
- Understand fact tables, dimension tables, source tables and data structures.
- Power Query: remove duplicates, handle missing values, change data types, split/merge columns and replace values.
- Append and merge queries; pivot and unpivot data; create reusable transformation steps and refresh queries.
- Power Pivot Data Model and columnar storage concepts.
- Star schema design, primary/foreign keys, relationships, cardinality and filter propagation.
- DAX calculated columns versus measures; SUM, COUNTROWS, DISTINCTCOUNT and other basic calculations.
- Create PivotTables and PivotCharts from the Data Model.
- Use AI to draft Power Query M expressions, explain transformation steps and generate or debug DAX.
Practical exercise
Import sales, product, customer and date tables; transform data, build relationships and create a KPI report using Power Pivot.
Expected outcome
Learners can build a reusable Excel analytics solution with a structured data model.
4 Introduction to Power BI and Data PreparationObjectives · topics · practical exercise · 5 hours
Introduces the Power BI ecosystem and the PL-300 competency area of preparing data for analysis.
Learning objectives
- Navigate Power BI Desktop and connect to supported data sources.
- Prepare, profile, transform and load data into a semantic model.
Topics covered 5 hours
- Power BI Desktop, Power BI Service and the broader ecosystem.
- Connect to Excel, CSV, databases and other supported sources.
- Import, DirectQuery and introduction to Direct Lake.
- Power Query in Power BI; data profiling, column quality and distribution.
- Handle null values, errors and inconsistent records; merge and append queries.
- Parameters, data-source settings, query dependencies and refresh behaviour.
- Create fact tables, dimension tables and appropriate keys.
- AI-assisted transformation planning and validation.
Practical exercise
Connect Power BI to a multi-sheet Excel workbook, clean data using Power Query and load the prepared tables.
Expected outcome
Learners can create a repeatable data preparation workflow in Power BI.
5 Data Modelling and DAX in Power BIObjectives · topics · practical exercise · 8 hours
Develops the modelling and calculation skills needed to create accurate, efficient and scalable analytical models.
Learning objectives
- Design a semantic model and define appropriate relationships.
- Create reusable measures, time-based calculations and performance-aware models.
Topics covered 8 hours
- Relational and dimensional modelling; star schema design.
- Fact and dimension tables; one-to-many and other relationship cardinalities.
- Active and inactive relationships, cross-filter direction and relationship management.
- Date tables and time intelligence.
- DAX syntax, operators, row context and filter context.
- Measures, calculated columns and calculated tables.
- SUM, AVERAGE, COUNTROWS, DISTINCTCOUNT, DIVIDE and CALCULATE.
- Conditional measures using IF and SWITCH; year-to-date, previous-period and year-over-year analysis.
- Quick measures, visual calculations, model optimisation and Performance Analyzer.
- Use ChatGPT and Copilot to generate and debug DAX.
Practical exercise
Build a sales model with measures for revenue, cost, profit, profit margin, year-over-year growth and cumulative sales.
Expected outcome
Learners can build a reliable Power BI semantic model and develop business calculations using DAX.
6 Power BI Visualisation, Reports and DashboardsObjectives · topics · practical exercise · 6 hours
Transforms analytical models into interactive reports that communicate findings clearly to technical and non-technical audiences.
Learning objectives
- Select effective visualisations and design interactive report pages.
- Communicate trends and actionable insights through data storytelling.
Topics covered 6 hours
- Visualisation principles and choosing appropriate chart types.
- Cards, tables, matrices, bar charts, line charts and maps.
- KPI indicators, conditional formatting, filters, slicers and cross-highlighting.
- Drill-down, drill-through, report-page tooltips, bookmarks, buttons and navigation.
- Themes, layouts, accessibility, mobile layouts and report usability.
- Trend, outlier and anomaly analysis; forecasting, clustering and AI visuals where supported.
- Smart narratives and natural-language-assisted analysis.
- Power BI Copilot for report creation and summarisation where available.
- AI-assisted report titles, executive summaries and recommendations.
Practical exercise
Design a multi-page dashboard showing revenue, profitability, product performance, regional trends and monthly performance.
Expected outcome
Learners can build polished, interactive Power BI reports that answer real business questions.
7 GenAI-Powered Analytics and Data StorytellingObjectives · topics · practical exercise · 4 hours
Explores practical uses of Generative AI throughout the analytics lifecycle, including planning, formula development, interpretation and communication.
Learning objectives
- Use AI assistants to accelerate analytical workflows.
- Validate AI-generated formulas, interpretations and recommendations against evidence.
Topics covered 4 hours
- Prompt engineering for Excel, Power Query, DAX and Power BI.
- Ask AI to identify potential data-quality issues and propose KPIs or analytical questions.
- Generate Excel formulas, M code and DAX expressions.
- AI-assisted root-cause investigation and trend interpretation.
- Generate narrative summaries from verified analytical results.
- Natural-language querying and report generation.
- Python or other analytical tools with AI assistance where appropriate.
- Verify AI-generated claims against source data; understand hallucinations and limitations.
- Privacy, responsible AI, data governance and feature/licensing considerations.
Practical exercise
Use a verified dataset to generate measures, investigate a trend and produce an evidence-based executive summary.
Expected outcome
Learners can integrate AI into analysis without assuming AI-generated results are automatically correct.
8 Publishing, Managing and Securing Power BI SolutionsObjectives · topics · practical exercise · 3 hours
Covers publishing, sharing, refreshing and governing analytical assets in line with the PL-300 management and security competency area.
Learning objectives
- Publish reports and organise workspace content.
- Apply appropriate access controls and understand refresh and security practices.
Topics covered 3 hours
- Publish reports from Power BI Desktop to the Power BI Service.
- Workspaces, reports, dashboards, semantic models and apps.
- Sharing, distribution, workspace roles and permissions.
- Row-level security (RLS), sensitivity labels and data governance.
- Scheduled refresh and gateway concepts; refresh failure troubleshooting.
- Subscriptions, alerts and collaboration.
- Promoting or certifying trusted content where supported.
- Performance monitoring, maintenance, licensing and capacity considerations.
Practical exercise
Publish a report to a workspace, configure access, test row-level security and demonstrate a refresh workflow.
Expected outcome
Learners understand how to deploy, share, maintain and secure Power BI analytics.
9 Real-World Case Studies and Capstone ProjectObjectives · topics · practical exercise · 6 hours
Consolidates the course through an end-to-end business intelligence project based on a realistic organisational problem.
Learning objectives
- Translate a business problem into an analytical solution.
- Deliver a working dashboard, documented model and presentation of actionable insights.
Topics covered 6 hours
- Define the business problem and analytical requirements.
- Collect and document datasets; clean and transform data in Power Query.
- Build a star schema and semantic model.
- Develop DAX measures and KPIs.
- Design interactive Power BI report pages.
- Use AI to support analysis and documentation, with verification.
- Validate results, document assumptions and limitations.
- Publish and present the solution; communicate evidence-based recommendations.
Practical exercise
Choose a sales, HR, financial, customer or operations dataset and deliver a complete Power BI solution.
Expected outcome
Each learner produces a working dashboard, documented data model, business KPIs and an executive presentation.
