Facebook’s analytics currently provide reach metrics for fixed intervals (1-day, 7-day, and 28-day periods), limiting the ability to track reach progression over custom timeframes. To address this gap, our project develops an XGBoost model to estimate reach for any arbitrary number of days, incorporating transformations to handle non-linearity in the data. Model performance is evaluated using common metrics such as Mean Squared Error (MSE) and Mean Absolute Error (MAE). Additionally, we introduce validation intervals and a reach ratio—defined as the reach for any arbitrary period divided by the cumulative reach of previous days—to further validate model effectiveness. For a range of k values from 1 to 365, our approach achieves between an 80-99% validation score, successfully capturing reach progression while maintaining alignment with expected regression trends and ratio patterns.
Mentor: David Banks