Enabling sales reps to target relevant physicians to increase brand awareness and sales

Next Best Sequence of Marketing Activities

The Client

Pharma Giant

One of the world’s largest biopharmaceutical giants with over 7000 employees providing effective medicines to millions was looking for a custom AI solution to automate the selection process of the next best series of communication channels to transmit with healthcare professionals about their medicines and drugs effectively.

Akaike’s edge-cloud agnostic solutions offer great flexibility.

Flexibility 0%
Cost 0%

Executive Summary

Industry Overview

Disruption

The health care industry is a sector that provides goods and services to serve patients with curative, preventive, rehabilitative, or palliative care. While global healthcare sector continues to rise to the new challenges presented by the ongoing pandemic, dominating healthcare systems’ attention and resources. Also, they thrive to elevate the human experience of their workforce and reshape what, how, and where work is performed, swiftly scaling virtual health services for patients, and forging partnerships to produce and procure the required vaccines, treatments, and supplies. At the same time, health information technology presents numerous opportunities for improving and transforming healthcare which includes; reducing human errors, improving clinical outcomes, facilitating care coordination, improving practice efficiencies, and tracking data over time.
Business Challenge

Customer Experience

Knowing which marketing channels lead to effective communication is a win-win situation for pharma companies and doctors as the best treatments can be offered to patients. The pharma customer wanted to streamline the marketing channels decisively to send the required information to the physicians. They wanted us to lay out a detailed 3-6 months strategy for a series of marketing activities to execute, such as email, Telephonic conversations, or face-to-face meetings which would help them get more prescriptions for their effective drug against deadly diseases. The tailor-made next-best sequence model was optimized to fulfill the aforementioned pointers with just the right channel at the right time to increase brand awareness and sales.

The Akaike Edge

Inbuilt libraries, DL models with transfer learning capabilities

Experienced ML and DL Ops teams

Efficient Deployment 0%
Integration 0%
Ongoing Maintenance 0%

Solution

Inbuilt libraries, DL models with transfer learning capabilities
Step 1.

Collect the marketing and claims data from different sources

We gathered data on physicians and patients from a variety of sources in order to better understand the actions of physicians and the medical claims made by patients. We compiled statistics on physician engagement in marketing, prescriptions, demographics, medical and insurance claims from patients, and patient treatments. Marketing data was further fragmented into PP(personalized promotion) data, such as in-person visits, and NPP (non-personalized promotion) data, such as emails to make the solution even more effective.

Step 2.

Feature engineering and model building

Using deep learning algorithms, a complex sequential AI model was trained from relevant physicians’ features such as patient treatment history, active patients count, treatment and prescriptions behavior, marketing activity engagement patterns, and more. Features were designed using historical data for a specific time to predict the Next-Best-Sequence of marketing activities.

Step 3.

Transfer the model output to the omnichannel dashboard

Next-best sequence activities were rolled out to the customer’s omnichannel dashboard for effective utilization by sales representatives and marketing teams. Later, the model was also improved for marketing expenditures to obtain the best return on investment for each marketing activity by a dollar. The customer profited from this strategy both from a budgetary and effectiveness perspective, making it the optimal sequence of marketing activity.

Research shows that 87% of Vision AI
projects do not yield expected results

either owing to training data insufficiencies stalling the project, or being too slow to deploy. Our AI experts can help you accelerate in data sparse environments.

We use cookies to give you the best experience.

Get in Touch