What's Happening?
Sigma Healthcare has implemented machine learning models within SAP's integrated business planning (IBP) system to improve demand forecasting accuracy for medications. The company initially achieved a 5-10%
increase in forecast accuracy by using SAP's response and supply planning module. With the addition of machine learning models, Sigma Healthcare has further enhanced accuracy by at least another 10%. These models, including extreme gradient boosting and automatic outlier correction, help optimize inventory management and reduce inefficiencies in supply planning processes. Sigma Healthcare plans to leverage SAP Joule, a generative AI copilot, to further optimize forecasting and planning.
Why It's Important?
The use of machine learning in demand forecasting is crucial for pharmaceutical companies like Sigma Healthcare, as it enables more accurate predictions of medication needs and optimizes inventory management. This approach reduces waste, improves supply chain efficiency, and ensures the availability of essential medications. The integration of AI technologies in business planning reflects a broader trend in the healthcare industry towards data-driven decision-making and operational efficiency. By adopting advanced forecasting tools, Sigma Healthcare can maintain a competitive edge and better serve its customers.
What's Next?
Sigma Healthcare plans to continue exploring the capabilities of SAP Joule to enhance its forecasting and planning processes. The company aims to keep pace with quarterly upgrades of IBP and the rapid advancements in AI technology. By staying at the forefront of AI integration, Sigma Healthcare can further improve its operational efficiency and maintain its competitive advantage in the pharmaceutical industry. Collaboration with technology partners like EY will be essential to optimize the IBP environment and ensure the successful implementation of AI-driven solutions.
