New Drug Sales Forecasting in a Competitive Market

The Client

The client is a global pharmaceutical company developing and commercializing innovative therapies. Their success depends on accurately forecasting market adoption of new drugs. As competition intensified in the Bulgarian market, they needed a robust, data-driven approach to benchmark and improve their existing forecasting models.
 

The Challenge

Forecasting the adoption of a new pharmaceutical product is inherently complex, particularly in competitive markets with multiple existing treatments and new entrants. In this case, two competing drugs were already established, while an additional biosimilar product was entering the market simultaneously.

The client needed to account for multiple interacting factors, including disease epidemiology, patient flows, treatment switching behavior, and competitive dynamics. Traditional forecasting approaches lacked the flexibility to model these interactions in a realistic and dynamic way.

Additionally, the business required scenario-based forecasting to understand potential revenue outcomes under different market conditions — including best-case and worst- case adoption trajectories.

Without a robust simulation framework, the client risked inaccurate forecasts, suboptimal market strategy, and misaligned resource planning.
 

What We Did

Approach

We developed a simulation-based market demand model to capture the dynamics of drug adoption in a competitive environment. The approach combined epidemiological insights with market behavior modeling to create a realistic representation of patient and treatment flows.

During the discovery phase, we identified that static forecasting methods were insufficient to capture the complexity of the system. Instead, a state-based modeling approach was required to simulate transitions between treatment options over time.

A key decision was to implement a Markov state model, enabling the simulation of disease progression and treatment switching behavior on a monthly basis.
 

Methodology

• Data assessment:
  Analysed epidemiological data, disease prevalence, and historical market behaviour across existing treatments
• Approach selection:
  Selected a simulation-based framework using a Markov state model to capture patient transitions and market dynamics
• Model development:
  Built a model with 40+ input parameters, incorporating treatment adoption, switching rates, and competitive interactions
• Validation framework:
  Benchmarked model outputs against historical data and tested multiple market scenarios for consistency
• Integration:
  Delivered a flexible simulation tool enabling monthly forecasts and scenario analysis
• Compliance:
  Ensured alignment with pharmaceutical industry standards for data usage and modelling practices
   

The Outcome

Robust monthly forecasts of drug demand across all market participants

The simulation model provided detailed forecasts of expected sales volumes for the new drug and its competitors on a monthly basis.

Secondary outcomes:

• Scenario-based forecasting supporting best- and worst-case revenue planning
• Improved understanding of competitive dynamics and treatment switching behaviour
• Data-driven benchmarking of existing forecasting models
• Scalable framework adaptable to other markets and drug launches
   

Facing a similar challenge?

If you're launching a new product in a complex, competitive market, we can help build simulation models that provide clarity on demand, risk, and revenue potential.

Book a Technical Consultation