For many decisions made by companies, it is important to estimate future demand as accurately as possible and thus to incorporate (long-term) trends into the decision. Material procurement, production planning or planning of sales promotion measures are based on this demand forecast. The less clear demand planning is, the more uncertain the decisions based on it will be.
At its core, the benefit of data-based demand forecasting is that it combines a wealth of primarily historical data. This allows patterns to be identified that provide information about future sales events and changes in demand. Data analyses thus create scenarios with probabilities of occurrence that provide support for decision-making. Various forecasting methods can be used. They differ in their costs, time horizons (longer- or short-term) and suitable application areas. In any case, it is important that the data quality is as high as possible.
The Nestlé food group uses business analytics software to evaluate market data, customer data, prices and costs, and sales trends. This helps improve demand forecasting and demand planning for the product range.
The combination of sales data and geographic data enables the multi-technology group 3M to make differentiated statements about the company’s performance and the global distribution of sales.
Pest control company Groli collects historical data to better estimate upcoming operations and timing of pest emergencies.
Forecasting future demand has an impact on the value chain. Material flows and production capacities are aligned with expected demand. Prices can also be adjusted to the forecast. If demand is optimally served, both internal value creation processes and sales can be improved.
Sources: Nestlé (2019), 3M (2017), Groli (2019)
