# Module 7: Machine Learning Models for Predictive and Prescriptive Modelling OVERVIEW This module introduces learners to machine learning models and their practical use in business forecasting, risk assessment, project planning and financial decision-making. Learners will explore how different machine learning techniques work, when to use them and how to select a suitable model based on a business requirement. The focus is on applying these models to real-world business scenarios rather than learning the theory alone. Through practical case studies, learners will work with forecasting methods, build simple predictive models, identify potential project bottlenecks and develop financial models to support planning and budgeting. By the end of this module, learners will understand how to use machine learning outputs to support everyday business decisions and improve operational planning. > Tools Covered:Linear Regression | ARIMA | SARIMA | Decision Tree | K-Nearest > Neighbours (KNN) | Regression Models WHAT WILL BE COVERED 7.1 ANALYTICS PROMPTING USING MACHINE LEARNING MODELS – TYPES AND FUNCTIONS Understand how to use AI tools and well-structured prompts to explore machine learning models and interpret their outputs. Topics include: * Introduction to machine learning and its role in business analytics. * Understanding different types of machine learning models and their functions. * Difference between predictive and prescriptive modelling. * Using prompts to identify suitable models for specific business problems. * Interpreting model outputs, predictions and recommendations. * Understanding the importance of data quality and relevant business information before applying a model. Practical example: Use an AI assistant to identify suitable machine learning approaches for predicting monthly sales, estimating project delays or analysing customer behaviour. 7.2 PREDICTIVE ANALYTICS AND FORECASTING USING DIFFERENT MACHINE LEARNING MODELS – WHY, WHEN, WHERE AND HOW Explore how different machine learning models can be used to forecast future outcomes and support business planning. Topics include: * Understanding why businesses use predictive analytics. * Identifying situations where forecasting can improve decision-making. * Introduction to Linear Regression and its use in predicting numerical values. * Understanding ARIMA and SARIMA for time-series forecasting. * Exploring Decision Tree models for prediction and decision-making. * Understanding K-Nearest Neighbours (KNN) and its applications. * Introduction to different regression models and their business applications. * Selecting an appropriate model based on the available data and business requirement. Practical example: Compare forecasting approaches for monthly revenue, customer demand and operational workload to understand which model is suitable for each situation. 7.3 APPLY MACHINE LEARNING MODELS BASED ON BUSINESS CASE STUDIES Learn how to select and apply machine learning models to practical business problems. Topics include: * Understanding the business problem before selecting a model. * Identifying the data required for model development. * Selecting suitable machine learning techniques based on the business case. * Applying regression and forecasting models to business datasets. * Reviewing model predictions and comparing them with actual results. * Understanding prediction accuracy and the limitations of model outputs. * Interpreting results and presenting findings in a business-friendly format. Practical example: Use historical sales data to estimate future sales, analyse customer trends or predict changes in business demand. 7.4 BUILD SIMPLE MODELS FOR PROJECT TIMELINE FORECASTING Understand how machine learning models can support project planning by estimating completion dates and identifying possible delays. Topics include: * Understanding the relationship between project history and timeline forecasting. * Identifying relevant project data, such as planned duration, actual duration, task dependencies and completion status. * Building simple models to estimate task and project completion timelines. * Using historical project data to forecast possible delays. * Comparing planned timelines with predicted completion dates. * Interpreting forecasting results for project planning and resource allocation. Practical example: Use historical project data to estimate whether ongoing projects are likely to meet their planned completion dates and identify activities that may require additional attention. 7.5 DEVELOP RISK PREDICTION TOOLS TO IDENTIFY POTENTIAL BOTTLENECKS Explore how machine learning can help identify potential risks and operational bottlenecks before they affect business performance. Topics include: * Understanding risk prediction in business operations. * Identifying factors that contribute to project delays and operational bottlenecks. * Using historical data to identify recurring risk patterns. * Applying suitable machine learning models to predict potential risks. * Interpreting risk indicators and prediction results. * Using predictions to prioritise corrective actions and preventive measures. Practical example: Develop a simple risk prediction approach to identify projects that may experience delays based on resource availability, task completion rates and previous project performance. 7.6 CREATE FINANCIAL MODELS FOR PLANNING AND BUDGETING Learn how machine learning and predictive modelling can support financial planning, budgeting and forecasting. Topics include: * Understanding the role of predictive modelling in financial planning. * Identifying historical financial data required for forecasting. * Using regression models to estimate revenue, expenses and financial trends. * Applying forecasting techniques to support budget planning. * Analysing actual financial performance against forecasted values. * Identifying possible financial risks and deviations. * Using model outputs to support budgeting and resource allocation decisions. Practical example: Build a simple financial forecasting model to estimate future revenue and expenses using historical financial data and use the results to support budget preparation. 7.7 INTEGRATE FORECASTING INTO DAY-TO-DAY BUSINESS OPERATIONS USING MACHINE LEARNING MODEL INSTRUCTIONS Understand how forecasting can become part of regular business activities rather than remaining a one-time analytical exercise. Topics include: * Identifying routine business activities that can benefit from forecasting. * Preparing structured instructions for using machine learning models. * Using updated business data to generate regular forecasts. * Interpreting forecast results for operational planning. * Monitoring actual performance against predicted outcomes. * Reviewing and updating models when business conditions change. * Using forecasting insights to support daily and monthly business decisions. Practical example: Establish a regular forecasting process for sales, inventory, project progress or operational workload, allowing managers to review expected outcomes and take action when necessary. SKILLS YOU WILL GAIN By completing this module, learners will develop the ability to: * Understand the purpose and functions of different machine learning models. * Identify suitable models for specific business problems. * Use AI prompting techniques to explore analytics and forecasting requirements. * Apply regression and time-series forecasting techniques. * Work with Linear Regression, ARIMA, SARIMA, Decision Tree and KNN concepts. * Build simple predictive models using business datasets. * Forecast project timelines and identify possible delays. * Develop risk prediction approaches for business operations. * Create financial forecasting models for budgeting and planning. * Interpret model outputs and communicate findings to business stakeholders. * Integrate forecasting into regular business planning and decision-making. LEARNING OUTCOMES After completing this module, learners will be able to apply predictive and prescriptive modelling concepts to practical business situations. * Improved business forecasting: Estimate future sales, revenue, expenses and operational demand using historical business data. This helps teams prepare for upcoming requirements rather than relying only on past performance. * Better project planning: Use project history and task information to estimate completion timelines, identify possible delays and improve resource allocation. * Early risk identification: Recognise patterns that may indicate operational issues, project bottlenecks or financial risks. This allows managers to investigate potential problems before they affect business results. * More informed financial decisions: Use financial forecasting to support budgeting, expense planning and revenue estimation. Compare predicted results with actual performance to identify areas that need attention. * Improved operational planning: Bring forecasting into routine activities such as inventory planning, workload management, sales reviews and project monitoring. * Better use of business data: Understand how to select relevant datasets, choose suitable models and interpret predictions in the context of actual business requirements. * Stronger decision-making: Move beyond descriptive reports and use predictive insights to evaluate possible future outcomes and plan appropriate actions. AB-731 EXAM ALIGNMENT Learning area Relevance Understanding AI and machine learning Builds an understanding of how machine learning models support business problems and decision-making. Identifying business use cases Helps learners recognise opportunities to apply predictive analytics in finance, project management and operations. Evaluating AI business value Demonstrates how forecasting and risk prediction can improve planning, efficiency and resource utilisation. AI-driven decision-making Develops an understanding of how predictive insights can support business strategies and operational decisions. Responsible use of AI outputs Highlights the importance of data quality, model limitations and human review when using predictions. CONTINUE TO THE NEXT MODULE You have now explored how machine learning models can support business forecasting, project planning, risk prediction and financial decisions. In the next module, you will explore AI-powered tools for creating graphics and videos, and learn how generative AI can support visual communication and content development. Next Module 8: Graphics & Video Generation Using AI [https://teamacademy.help.center/article/1306-module-4-graphics-video-generation-using-ai] Explore how AI tools can help create visual content, graphics and videos for different business and communication requirements.