Handbook home
Predictive Analytics (BISY90016)
Graduate courseworkPoints: 12.5On Campus (Parkville)
Overview
Availability(Quotas apply) | September |
---|---|
Fees | Look up fees |
Predicting key business variables has become increasingly important, as it drives both objective decision-making and improved profitability within organisations. This subject covers the main methods used to predict business variables, based on historical data. These include traditional regression, time series analysis, forecasting models, survival analysis, data mining, support vector machines and sentiment analysis. Throughout the subject, the focus will be on understanding how these methods are applied in various business problems, and identifying which predictive approach is the most appropriate to use, given a specific context. The importance of benchmarking different methodologies, as well as the use of prediction in decision-making frameworks, will also be emphasised.
Intended learning outcomes
On completion of this subject, students should be able to:
- Understand a wide range of models and methodologies relevant to predicting business outcomes.
- Apply appropriate modelling skills to business contexts such as resource allocation, product development and consumer behaviour.
- Develop forecasting techniques to identify potentially attractive market and investment opportunities.
- Translate forecasting outputs into insights that form the basis of recommendations addressing relevant business problems.
- Determine which metrics to use in critiquing and comparing competing predictive methodologies.
- Identify what additional data would be required to create more robust prediction models, given a certain business context
Last updated: 8 November 2024