Forecasting Techniques and Financial Modelling

Dr Liam Bastick, Director of Corality (Melbourne) was invited to deliver a series of presentations and workshops during the CPA Congress, which was held in New South Wales, Queensland and Tasmania in October 2010.

Presentation: Forecasting Techniques and Financial Modelling

In his presentation, “Forecasting Techniques and Financial Modelling”, Liam Bastick discussed common methods of financial forecasting, difficulties in forecasting and how to assess the accuracy of forecasts.

“It was almost like a stats course, but people seemed to like it! I discussed useful Excel functions that can help management accountants and other finance professionals forecast objectively from historical data” - Liam Bastick

Importance of understanding forecasting methods

Almost all managerial decisions are based on forecasts of future conditions. Managers are required to make decisions under uncertainty about the future. In order to make those decisions, it is necessary to forecast key variables. 

Forecasting is a continuous process. The impact of forecasts on actual performance is measured and the original forecasts are updated.

The choice of forecast models can have a significant impact on the accuracy of forecasts. It is necessary to understand forecasting methods (and their limitations) in order to make reliable and timely business decisions.

Below is an overview of what was covered in the presentation.

Presentation snapshot

Liam’s presentation “Forecasting Techniques and Financial Modelling” offers an overview of the forecasting techniques used industry-wide:

• Regression analysis
• Rolling forecasts
• Simple moving average
• Weighted moving average

Regression analysis is used to establish linear relationships between variables. It has different applications, such as predicting sales and consumption on the basis of various variables such as advertising and income.

Rolling forecasts allow budgets to be revised on a regular basis throughout the year. They are useful, for example for cash-strapped companies.

Moving averages represent averages over specified consecutive periods, whereby the moving average is “updated” with new information. Weighted moving averages are useful when it is necessary to assign greater weights to more recent events. Some applications of moving averages include inventory costing.

Forecasting errors

Common measures of forecast errors, essential in assessing accuracy of forecasts:

• Mean Squared Error (MSE)
• Mean Absolute Deviation (MAD)
• Cumulative Forecast Error (CFE)
• Mean Absolute Percentage Error (MAPE)

Difficulties encountered in forecasting:

• Nature of data
• Historical bias
• Choosing appropriate forecasting models
• Validating usefulness and appropriateness of forecasts

Key findings

Make sure to:

• Understand the applications and limitations of forecasting methods
• Assess accuracy of forecasts
• Test and validate models

Download presentation

Click here to view and download a condensed version of the presentation.

COMMENTS