Nabaroon Acharjee

• Market Mix Modeling and Media Spend Optimization:

We conducted a Market Mix Modeling (MMM) analysis across multiple pharmaceutical brands in five geographies to optimize strategic marketing investments across various promotional channels, including calls, events, and rep-triggered emails. The goal was to determine the optimal level of promotion investment required to maximize revenue. The response variable (sales) was regressed against different types of promotional expenditures (PDEs and events), sales carryover, and brand equity. We utilized ad-stocking and variable transformations to better capture the effects of promotions. This analysis also enabled us to calculate both short-term and long-term sales impacts and ROI for each promotional channel, ultimately providing actionable insights for optimized marketing spend and strategy. Tool Used: DataBricks

• Hospital Promotion Effectiveness:

For a newly launched LLAI brand created a case study at account level for activity and performance for different time periods which showcases accounts with higher utilization has a higher growth-rate.

• Other Domain/Functional Areas:

Patient Analytics, Source of Business(SOB), Persitancy Analysis of patients for different drugs

• Propensity to Win

Developed an ML model using real-time data from Salesforce for a healthcare brand to understand the probability of an opportunity item winning the deal over its competitors. Going further with the output, I developed a real-time dashboard in SFDC to help the business leaders understand its most potential deals over different periods of time. This model is automated for a biweekly refresh to help the leaders take immediate action.

Tools Used: R,SQL,Knime,Salesforce

• Other roles and responsibilities:

Worked as a Lead Business Analyst and as a Scrum Master to develop new solutions based on the business input from stakeholders, developed wireframes using data from different sources (SFDC, SAP, and others) to build new KPIs to track the performance of the business across different levels.

• Worked as a Junior Data Scientist for retail CPG clients like Coca-Cola, Starbucks, and P&G, and worked on several machine learning and classification projects.
• Structural Equational Modeling, Time Series Forecasting, and MMiX are among the major techniques I have worked on.