Predicting site alerts in future at HCP level for effective planning of HCP targeting strategies

  • Develop an advanced machine learning algorithm to predict the potential site alerts for all the HCPs in the MCM target universe and forecast the alerts in the future 4 weeks period
  • Built an efficient recommendation model to help plan the HCP engagement journey


increase in site alerts coverage


improvement in site alerts address rate


lift in engagement

“D Cube Analytics had supported greatly in setting up and measuring the impact of the site alerts strategy.

Their innovative approach to predict site alerts has helped our teams to intervene proactively to help make treatment decisions.

This work puts us in an advantageous position by enabling our sales and marketing teams to reach out to HCPs more effectively with well-timed and tailored messaging.”


Pharma brand teams can leverage alerts in a multitude of ways. Besides sales rep deployment, alerts are also being used to direct their non-personal promotion like email and digital advertising.

The customer had partnered with third-party vendors to receive alerts data for different brands but it did not provide the complete coverage of all the HCPs in the target universe. Also, there was no visibility into upcoming alerts into the future which would have made the engagement journey more efficient.


  • Leverage claims data, EMR data, and other sources for incoming site alerts to improve data coverage and expand the existing HCP list. Identify the drivers of site alerts at the HCP level to predict and forecast the number of incoming sites into the future
  • Develop the right channel recommendation algorithm for each HCP and create a prioritized list of HCP’s based on phase 01 data


Phase 01:

  • Identified potential data sources such as claims/EMR data to identify the potential HCPs which were not a part of the existing HCP list
  • Create business rules to identify the incoming site alerts data from additional HCP lists to ensure better coverage of the site alerts and make the existing list more comprehensive
  • Identified the key drivers prescribing behaviour of HCPs and developed a regression model to estimate the future number of alerts from HCPs

Phase 02:

  • Created a channel and content recommendation algorithm for the updated HCP universe using Phase 01 output
  • Different data sources such as MCM activity, sales data and call activity was leveraged in creating recommendation algorithm and was sent across various channels for effective targeting
  • High-value HCPs were identified and HCP prioritization was done based on previous output and opportunistic value at each HCP


  • Enrichment of HCP universe and site alerts prediction helped in improving the coverage of total alerts
  • Forecasting site alerts in the future and taking informed decisions was helpful in better planning of HCP targeting and design tactics to manage the brand share
  • ~20% improvement in site alerts address rate and better utilization of sales reps & channel communications
  • Proactive engagement with high-value HCPs list by sending site alerts communications through the right channels. Call activity planning was realigned to help the sales reps in optimizing their efforts in turn increasing sales


Related Case Studies

Data Management That’s Truly Next-Gen

Data Management That’s Truly Next-Gen

PRODUCTData Management That’s Truly Next-Gen A large pharma company might require highly customized data warehouses with reporting capabilities to support a multitude of teams. A smaller company about to launch an asset might require a subset of these capabilities...

read more
Leveraging Full Potential of the Data Lake

Leveraging Full Potential of the Data Lake

PRODUCTLeveraging Full Potential of the Data Lake Geared to serve a large biopharma team with a wide range of data transformation and wrangling functions to slice and dice the data. “The visual wrangling feature and ability to save workflows greatly improved...

read more