What Can Be Forecast?
Forecasting is required in many situations, and the forecasts can be years in advance, or only a few minutes.
Some things are easier to forecast than others - take the time of tomorrow’s sunrise versus tomorrow’s lotto numbers. The predictability depends on several factors including:
- How well we understand the factors that contribute to it.
- How much data is available.
- Whether the forecasts can affect the thing we are trtying to forecast.
Forecasting, Planning and Goals
Forecasting is frequently confused with planning and goals:
Forecasting is about predicting the future as accurately as possible, given all information available. This includes historical data and knowledge of events in the future that may impact the forecasts.
Goals are what you would like to have happen. Goals should be linked to forecasts and plans, but this does not always occur. Too often they are set without any plan to reach them, and no forecasts to determine whether they are realistic.
Planning is a response to forecasts and goals. It involves determining the appropriate actions that are required to make your forecasts match your goals.
Forecasting is an integral part of the decision-making activities of management.
- Short-term forecasts for scheduling of personnel, production, and transportation.
- Medium-term forecasts to determine future resource requirements in order to purchase raw materials, hire personnel, or buy machinery and equipment.
- Long-term forecasts for strategic planning.
Determining What To Forecast
Consider a manufacturing environment, the questions are whether forecasts are needed:
- For every product line, or for groups of products?
- Every sales outluet, for outlets grouped by region, or only for total sales?
- Weekly, monthly, or annual data?
The forecasting horizon also needs to be determined: one month, six months, ten years? Different types of models are necessary depending on this horizon.
It’s worth spending time talking to the people who will use the forecasts to ensure you meet their needs, and how the forecasts are to be used.
It will then be necessary to find or collect the data on which the forecasts will be based. It may already exist, and the majority of time may be spent trying to find where the data is located.