On December 11, 2024, around 20 managers from the area of sales forecasting in production met at the end of the “PrABCast” project (predictive sales and demand planning in customer-oriented contract manufacturing using machine learning methods) in our port room to learn about and discuss the most important results.
Sales planning is equally relevant for production, sales, purchasing and logistics. Right at the beginning of the workshop, it became clear that artificial intelligence will not replace the often-used “crystal ball” any time soon – but with the helpful tool presented, which was developed as part of the project, sales forecasting can be improved with the help of analyses and data enrichment. After a round of introductions, Marius Syberg and Lucas Polley from RIF – Institut für Forschung und Transfer e. V. first presented the project approach and objectives, guided by the question: “How can AI be used sensibly in sales forecasting?”
They shared some key findings: Very good data quality is crucial for all analyses. The variety of different products and markets requires individual model approaches. These do not necessarily have to include AI. In any case, it makes sense to use external data. Market and economic data can significantly improve forecasts. Forecasts are based on the analysis of past events. This is why AI models do not look into the future, but learn from the past. The aim is to achieve comparability in order to be able to react better to certain developments and optimize production capacity utilization.
Last but not least, the comprehensibility and efficiency of AI models play an important role. They must be easy to explain and understand and require reasonable computing times. In the second step, the speakers presented the tool to the participants in detail. It tests different forecasting methods, can automate sales analyses, integrates external indicators and calculates their influence on sales. It can also be used securely and locally. This means that machine learning methods can be integrated into sales forecasting in the long term. Companies can use the tool free of charge. If you are interested in using the tool or require further information, please contact the speakers Marius Syberg and Lucas Polley directly.
