Advantage
Improve the accuracy of sales forecasts by up to 35%.
Data
Historical order histories and other internal and external data sources.
Method
Scalable machine learning approach based on time series analyses.
Challenge
As a leading global specialist for photovoltaic system technology, SMA offers solutions for private solar systems, commercial photovoltaic installations and solar power plants in the megawatt range. With a large portfolio of system technology and energy solutions as well as worldwide target markets, a reliable sales forecast is a key element for SMA's sales, resource and material planning. The previous forecasting process required a great deal of manual effort and resources. The information basis for the responsible employees was primarily a retrospective view of selected internal data such as historical sales. SMA therefore sees great potential in increasing the accuracy and process efficiency of the sales forecast
Goal
SMA wants to use machine learning to increase the quality of sales forecasts and support sales.
Solution
SMA has commissioned the data science experts at eoda to implement the AI approach in the sales forecast. In order to achieve an optimal forecast for each product in each target market, eoda chose an approach in which the machine learning models they developed automatically adapt to the individual product/market combinations and their special features.
In addition to historical order histories, eoda has also incorporated other internal and external data sources into the forecast.
Result
Early on in the proof-of-concept phase, the machine learning models were able to achieve a significant improvement in the accuracy of the sales forecasts. Specifically, the reference values of the machine learning model are up to 35% better than the existing expert estimates (measure: MAPE - Medium Absolute Percentage Error).
These results support sales and serve as a better planning basis for a large number of business areas. The scalable eoda approach with tailor-made machine learning models can be rolled out to the entire portfolio and all target markets within a short space of time following the successful PoC.
Get started now:
We look forward to exchanging ideas with you.
Your expert on Data-Science-Projects:
Lutz Mastmayer
projects@eoda.de
Tel. +49 561 87948-370
