Creating hyper-accurate demand forecasts for one of the world’s largest medical device companies

Medical device company

We worked with a world-renowned medical device company to improve the accuracy of their demand forecasting, enabling better decision-making and facilitating critical trade-offs based on leading market indicators.

20%

Improvement in forecast accuracy (Weighted mean absolute percentage error)

Background

Medical device supply chains are highly complex, involving global sourcing, specialised manufacturing, and worldwide distribution. Even in stable times, they are challenging to manage. COVID-19-driven demand surges and high air freight costs further exposes their vulnerabilities. We worked with a leading medical device company who faced surplus inventory, rising logistics costs, and unmet demand, as off the shelf forecasting tools couldn't handle their business complexity and market volatility.They were using patchy sales data and manually adjusting them in Microsoft Excel – inviting human error and wasting valuable time. This led to reactive decision-making, surplus inventory and SKU fragmentation. We were chosen to help deliver more trustworthy demand forecasts in both mature and emerging markets to serve their customers better.

Solution

We seamlessly embedded our AI-powered simulation technology into their existing infrastructure to deliver accurate and actionable forecasts across their rapidly-changing, multi-tiered supply chains. An interactive dashboard allowed users to adjust forecasts and model different scenarios, with all changes approved by a financial planner to maintain controlled updates. Users could plan for scenarios, compare forecasts and understand why data-driven predictions were made, which fostered more confidence in decision-making.

Impact

We improved the accuracy of demand forecasting, empowering the medical device company to potentially save millions across inventory and logistics in just one region. Across the markets and product portfolio tested, forecasts exceeded the performance of existing software by an average of 20%. And most importantly, this new way of forecasting can boost product availability to key customers, driving top-line growth.