Identified the right data sources (example – Weekly/Monthly Sales, Call activity, Email engagement, Website, Speaker Bureau etc.) for each suggestion and model training.
Incorporated constraints like rep time-off, call/email capping, HCP consent, etc.
Trained the deep learning model (TCN & FCN) using the past 6 months data like Sales, Call, Email & HCP affinity.
An intelligent optimization algorithm – Monte Carlo Tree Search was used to minimize the number of iterations needed to identify the promotion sequence that returns the highest value for an HCP.
Predicted alerts were sent as suggestions on Veeva app using Veeva API integration.
IVA call utilization increased from 75% to 90% post suggestions launch
Based on control test analysis, product sales increased by ~4% within the first year of suggestions launch
Sales reps were able to have meaningful conversations with HCPs
