A Private Equity firm needed to predict quarterly pharmaceutical revenue for the next quarter in terms of doctors and pharmacies. The problem here is that the data contains a lot of seasonality because some doctors are not regular in their services, the same happens at the pharmacy level. The challenge is to create a robust model to overcome these gaps in the information.
Vertical: Forecast revenue
Model: Ensemble learning
Model: Time Series Analysis with FB Prophet
The biggest challenge is the incomplete data from doctors, pharmacies and other entities. Cold Bore wants to predict the revenue for the next period of time (weekly, monthly, quarterly, yearly.)
The approach was to utilize all the six algorithms that AWS Forecast provided in 2019: npts, prophet, arima, ets, deeparp, and automl.
On the other hand, experimentation on pure ML methods with Ensemble Learning was carried out.
Finally, we integrated Prophet and LSTM.
At the pharmacies level, Ensemble Learning shows a better approximation. Conversely, at the doctor level, the Prophet library returns the best model.
In all the cases the new models were outperforming the previous results for weekly, monthly and quarterly predictions.
In all the scenarios, accounting for national holidays in different regions of the world was probably the most challenging part to forecast.