The traditional forecasting approach had several limitations:

• Manual effort: Time-consuming
• Multiple influencing factors: Sales quotas were shaped by historical sales, competitor activity, physician prescribing behavior, and market dynamics.
• Data fragmentation: These variables were stored across different tables, making integration complex.

The client needed a data-driven, automated solution that could integrate multiple data tables and provide accurate, granular forecasts

Implemented best AI/ML model approach in the forecasting solution using the following steps:

‍

Data Integration:

Pulled data from IQVIA, including:

• Historical sales
• Physician data
• Market trends
• Competitor performance

‍

Data Preparation:

• Cleaned and structured the data
• Engineered drug-specific features to improve model relevance

‍

Modeling Techniques:

• Used a combination of SARIMA (for time series), Random Forest, and XGBoost (for pattern recognition and prediction) - selected the best fit model
• Trained models to forecast monthly sales at the MSA level