CUSTOMER STORY // STEINEMANN

Significant Improvements in Production Planning With AI-Supported Forecasting

With Qlik and SLA, Steinemann is revolutionizing data analysis and using AI to achieve a new level of corporate success.

A Steinemann building illuminated against a clear blue sky at night.

90%

more accurate forecasting

Forecasting of planned production quantities is now more than 90% accurate.

>1,000 tons

of food waste avoided

Eliminating food waste reduces storage capacity and costs while boosting Steinemann’s sustainability incentives.

Real-time

production figures

More accurate figures can now be used for planning, reducing error rates.

CHALLENGE

Production guided by past order volumes

Accurate raw materials planning is a significant challenge in meat production as decisions often have to be based on past order volumes. It can be difficult to make predictions as orders often come in last minute and factors such as weather, promotions and storage costs all impact the planning process.

Steinemann decided to take a data-based approach by combining machine learning (ML) with historical production data. Together with Qlik OEM partner SLA, the team investigated how these technologies could make planning more efficient and accurate.

A herd of cows grazing in a lush green pasture under a clear blue sky.

APPROACH

Data analysis meets artificial intelligence

The company used historical sales data to develop a prototype for predicting its raw materials requirements. Initial tests saw forecasts prove more than 90% accurate when compared to the actual sales data – far better than manual estimates.

This accuracy was improved further by incorporating additional factors such as days of the week, product numbers and promotions. The Qlik results are integrated into the existing ERP system via an interface.

Illustration of a dashboard using Qlik's Associative Engine for exploring 'what-if' scenarios, test different parameters, determine the best course of action, and automate decision-making processes based on predictive insights.

RESULTS

An industry pioneer – thanks to AI

The accurate forecasts generated with Qlik AutoML are significantly improving raw materials planning for the company’s meat production processes. Machine learning can handle complex variables such as market size and stock inventories.

The system also optimizes logistical aspects – such as the purchase of packaging materials and seasoning – and reduces error rates. Integrating it into the existing ERP system has led to greater efficiency, cost savings and boosted Steinemann’s sustainability credentials. Unnecessary storage and waste are reduced, thereby elevating animal welfare and helping to conserve the environment.

A man dressed in a white apron prepares rows of sausages on a table.

WHAT THIS MEANS FOR YOU

Precise requirements forecasts optimize operations

With Qlik AutoML, the company can generate in-depth analysis to help it make well-founded business decisions. Precise requirement forecasts support the company in increasing its efficiency and reducing error rates and costs, which in turn has a positive impact on sustainability.

A software interface displaying SHAP importance scores, customer churn prediction influencers, current data, deployed model, and a selected territory marked as CT.
Steinemann logo in white
When we compared the AI-generated forecasts with our actual sales data, even I couldn’t quite believe how close the figures were.
Ralf Lenger
Head of IT, Steinemann Holding GmbH & Co. KG

Get started now