• Written by Azhar Aliyar, Director

Demand forecasting is the process of using historical data to estimate future demand for a product or service, but in practice, it often falls short when the history contains stockouts, where the demand is not met due to lack of supply. A purchasing manager checks the purchase order table and finds that the sales data is incomplete, which makes it difficult to accurately forecast demand. This is a common problem in large organisations, where the complexity of the supply chain and the variability of demand can make it challenging to get an accurate forecast.

Definition

Demand forecasting is a quantitative method that uses statistical models to analyse historical data and make predictions about future demand. It takes into account factors such as seasonality, trends, and external factors that may impact demand. The goal of demand forecasting is to provide a accurate estimate of future demand, which can be used to inform production, inventory, and supply chain decisions.

The demand forecasting process typically involves collecting and analysing historical data, identifying patterns and trends, and using statistical models to make predictions about future demand. This can be done using a variety of techniques, including moving averages, exponential smoothing, and regression analysis.

Differences from other methods

Demand forecasting is often confused with sales forecasting, but the two are not the same. Sales forecasting is a broader process that takes into account factors such as market trends, customer behaviour, and competitor activity, in addition to historical sales data. Demand forecasting, on the other hand, is a more narrow process that focuses specifically on estimating future demand for a product or service.

Another key difference between demand forecasting and sales forecasting is the level of granularity. Demand forecasting typically involves forecasting demand at the product or service level, while sales forecasting involves forecasting sales at the customer or market level. This means that demand forecasting is often used to inform operational decisions, such as production and inventory management, while sales forecasting is used to inform strategic decisions, such as market planning and resource allocation.

Applications in a large organisation

Demand forecasting has a number of applications in a large organisation, particularly in the supply chain and operations functions. For example, a supply chain manager can use demand forecasting to inform decisions about inventory management, such as how much stock to hold and when to replenish it. A production manager can use demand forecasting to inform decisions about production scheduling, such as how much to produce and when to produce it.

In a large organisation, demand forecasting can be used to forecast demand for a wide range of products and services, from raw materials to finished goods. It can also be used to forecast demand at different levels of granularity, from the product level to the customer level. For example, a category manager can use demand forecasting to forecast demand for a specific product category, while a sales manager can use demand forecasting to forecast demand for a specific customer segment.

For more information on how demand forecasting can be applied in a large organisation, please visit our website.

Limitations

Demand forecasting is not a crystal ball, and it has a number of limitations. One of the main limitations is that it is based on historical data, which may not be representative of future demand. For example, if there has been a stockout in the past, the historical data may not reflect the true demand for the product or service.

Another limitation of demand forecasting is that it can be impacted by external factors, such as changes in market trends or customer behaviour. These factors can be difficult to predict, and they can have a significant impact on demand. For example, a change in government policy can impact demand for a specific product or service, while a change in customer behaviour can impact demand for a specific customer segment.

When to use alternative methods

There are some situations where demand forecasting is not the best approach, and alternative methods should be used instead. For example, if the historical data is incomplete or inaccurate, it may be better to use a different method, such as sales forecasting or market research. Additionally, if the product or service is new, and there is no historical data available, it may be better to use a different method, such as customer surveys or focus groups.

In these situations, it is often better to use a combination of methods, rather than relying on a single method. For example, a company may use demand forecasting to estimate demand for a existing product, while using market research to estimate demand for a new product. For more information on how to choose the best method for your organisation, please contact us.