Managing Production Risk When Demand Is Uncertain

The Planning Problem

In this case, a pharmaceutical manufacturer was preparing production plans for a high-value product with long lead times and strict manufacturing constraints. Production occurred in large batches, and changing course once manufacturing began was costly and slow. At the same time, demand for the product varied significantly across regions due to changes in prescribing patterns, supply chain delays, and regulatory differences between markets.

The company’s operations team relied on traditional demand forecasts to guide production planning. These forecasts provided single predicted values for future demand, typically based on historical sales trends and recent market data. While the forecasts were often directionally reasonable, they did not provide a clear sense of the uncertainty surrounding those predictions.

This created a difficult situation for planners. A forecast might suggest that demand would increase over the next quarter, but the team had little insight into how confident they should be in that prediction. If production was increased too aggressively, the company risked producing excess inventory for a product that was expensive to store and had a limited shelf life. If production remained too conservative, shortages could occur, potentially disrupting supply to hospitals and pharmacies.

In practice, the challenge was not simply forecasting demand more accurately. The real problem was making production decisions in the presence of uncertainty.

QSC’s Modeling Approach

To address this, QSC’s modeling approach focused on estimating the range of plausible demand outcomes, rather than producing a single point forecast. Using historical sales data and market indicators, a probabilistic forecasting framework was developed to estimate how demand might evolve over time. Bayesian forecasting techniques were used to incorporate uncertainty directly into the model, producing probability distributions for future demand rather than single predicted values.

These forecasts allowed the team to evaluate multiple possible demand scenarios and quantify the likelihood of each outcome. Instead of asking whether demand next quarter would be, for example, 10,000 units, planners could examine the probability that demand would exceed certain thresholds relevant to production decisions.

This shift in perspective proved important. Production planning decisions could now be evaluated in terms of risk. For example, the team could estimate the probability that planned production levels would lead to shortages, or alternatively the probability that excess inventory would accumulate if demand fell below expectations.

Decision Support in Practice

To support these decisions, simple scenario simulations were developed that connected demand uncertainty to operational constraints such as batch sizes, manufacturing lead times, and inventory policies. These simulations helped the team explore questions like:

• What is the probability that demand will exceed available inventory before the next production cycle?
• How sensitive is this risk to changes in production timing?
• Under what conditions would increasing production by one batch meaningfully reduce shortage risk?

Rather than relying on a single forecast, the operations team could now see how different production strategies performed across a range of plausible demand outcomes.

This approach did not eliminate uncertainty. Demand for products will always involve factors that cannot be predicted precisely. What changed was the ability to reason about that uncertainty in a structured way.

Outcome

With probabilistic forecasts and scenario analysis in place, the production planning process shifted from attempting to predict the future exactly to managing operational risk more explicitly. Decisions about production increases, delays, or inventory buffers could be tied directly to the likelihood of different demand outcomes.

For the operations team, the most valuable outcome was not simply a more sophisticated model, but clearer visibility into the risks associated with each production decision. Instead of debating whether a forecast was “correct,” planners could focus on how different decisions performed under uncertainty.

This shift, from point forecasts to decision-focused modeling, allowed the team to plan production with greater confidence and fewer surprises as demand evolved.