Challenge

An internationally active food retailer wants to automate the sales forecasts of its products and introduce an automatically controlled value chain. The software used so far is to be replaced by the development of a solution that can be adopted and further developed internally.

Solution

Forecast models are developed and optimised specifically for certain requirements (e.g. introduction of new products). The procedures are then integrated into an automated process for expansion to any markets and product groups.

Result

The forecasting quality can be increased compared to the software used so far. The process is automated and can be controlled and further improved by the customer.

Challenge

An automotive company would like to visualise various market-specific data in order to create a Competitive analysis for the US market.

Solution

There will be a interactive and Flexible application, including of different maps with two different views implemented.

Result

Relevant markets are identifies, analyses and visualises. The dealer or the respective sales department have the possibility to compare the direct competition with their own product and to visualise the relevant data.

Demand forecasting in supply chain management

With the help of sales forecasts and demand forecasting, the entire supply chain is to be optimised for a beverage company.

Challenge

Out-of-stock situations and excess inventory exist at all levels of the supply chain and need to be reduced. Whip effects should be identified in the historical sales data and countermeasures implemented. Increasing product variety should be managed without the need for manual intervention.

Solution

The data silos are broken down by establishing an overarching data lake for centralised control of the entire supply chain. Automated sales forecasts for all stages of the supply chain are implemented with machine learning algorithms based on historical sales data. Forecasting unknown demand by modelling demand data from historical sales data.

Result

A universal, automated forecasting environment is available that can be used flexibly at all stages of the supply chain. Whip effects are reduced through shorter response times and reliable forecasts at all stages.

Challenge

An automotive company would like to visualise various market-specific data in order to create a Competitive analysis for the US market.

Solution

There will be a interactive and Flexible application, including of different maps with two different views implemented.

Result

Relevant markets are identifies, analyses and visualises. The dealer or the respective sales department have the possibility to compare the direct competition with their own product and to visualise the relevant data.

Demand forecasting of spare parts through machine learning

A parts distributor uses machine learning to improve the accuracy of demand forecasting, increasing parts availability and reducing lost sales by 50 %.

Challenge

A dealer of construction machinery spare parts would like to forecast the demand quantities for its products in the next few months at various locations in order to stock its warehouses according to demand.

Solution

Relevant predictive indicators were identified from internal data (e.g. historical demand quantities, product master data, master data on sales locations, ...) and external data sources (weather and economic data). With the help of a machine learning algorithm, the demand for spare parts at all locations for the next 12 months can be predicted more accurately than was previously possible.

Result

The increased forecasting accuracy means that retailers can manage their warehouses more efficiently. The added business value is reflected in key figures such as parts availability (service level), stock turnover and reduction of lost sales by avoiding empty warehouses.

Challenge

An automotive company would like to visualise various market-specific data in order to create a Competitive analysis for the US market.

Solution

There will be a interactive and Flexible application, including of different maps with two different views implemented.

Result

Relevant markets are identifies, analyses and visualises. The dealer or the respective sales department have the possibility to compare the direct competition with their own product and to visualise the relevant data.