SERVICE

Developed hyper-personalized recommendations for HCPs with relevant content, channel, and sequence

Creating a parameterized Brand agnostic model with incremental training enabled which adapts to changing prescriber behaviour and provide optimal recommendations

deployment time

%

increase in engagement rate

“We are happy with the way D Cube Analytics has built this, better way to describe this solution is – it’s a Re-configurable White Box Solution.

Several man-hours that usually go in other projects are avoided here due to parameterization and config creations. Most of all, being able to change the rules without help from the development team at any point is very helpful with quick changes in requirements and Ad hoc analysis”

Objective

Increase the Market Share of target prescribers by creating custom-tailored recommendations using an AI solution

  • Needs parameterized/clients should be able to change any input metrics
  • Complete automated solution

Introduction

Used an analytical approach to develop a brand agnostic data engineering pipeline/data model for downstream applications. This data was further used AI-driven deep learning model to generate rich content and channel recommendations for target HCP.

Solution

  • Collaborated and driven business rules discussions with customer team in finalizing the standardized business rules to be used for making brand-agnostic data and KPI definitions
  • Developed master datasets by applying business rules and automated monthly PySpark code refreshes using data bricks notebook scheduler
  • Applied state of the art machine learning algorithm like reinforcement learning and deep neural network with dynamic recalibration, automated hyperparameter tuning for enriching recommendation for HCPs
  • Automated data engineering pipelines appends the recent data to master data set at regular interval scheduled by Airflow
  • Sequential Content – Channel combination is recommended for each HCP at timely interval without any manual intervention

Outcome

  • Seamless data flow to and from channel partners
  • Lift in engagement rate in short term rewards and Rx for long term rewards cleaned up and variables required are already present
  • Re-usable and modularized codes help in quick enhancements and easy refreshes to reduce the additional effort
  • Implementation Of Business Rules – Ensuring to implement any rules provided by the business
  • Self Learning Enabled in final recommendations – Results will be updated based on recent engagement
  • Ensemble All Previous Modules To Generate Final Recommendations

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