Neha Saluja

• Spearheaded end-to-end web analytics for Samsung US, a Fortune 100 company, leveraging Adobe Analytics and Tableau to identify business opportunities and drive data-driven decision-making.
• Conducted customer journey mapping and pathing analysis, identifying key friction points and optimizing user flows, contributing to a 24% revenue uplift for new product launches.
• Led weekly stakeholder reviews, translating complex analytical insights into strategic recommendations for business and technical teams, ensuring seamless execution of product launch strategies.
• Designed and implemented a data model using Vertica, replacing Adobe Analytics for direct data extraction via queries, significantly reducing manual effort in Excel-based reporting.
• Recreated Adobe segments in Vertica, translating them into SQL queries, validating key metrics (visits, continuation rate, SPV rate), and building a Tableau dashboard for real-time insights, improving efficiency and data accessibility.

Credit & Collections Analytics for Utilities

• Provided data-driven consulting, leading to a $6.2M reduction in payment arrears within 5 months.
• Developed time-series forecasting models using ARIMAX in Python, achieving >95% accuracy.
• Conducted customer segmentation using K-means clustering to improve collections strategy.

Market Mix Modeling for Pharma & CPG Clients

• Delivered actionable insights via Market Mix Models (MMM), optimizing marketing efficiency.
• Performed exploratory data analysis (EDA) on sales & marketing data and built Power BI dashboards to visualize MMM results

Predictive Analytics for CPG Clients

• Built Market Mix Models using multiple linear regression, estimating marketing impact.
• Identified key sales drivers, quantifying the effect of advertising channels, pricing, and competition on product sales.
• Developed time-series forecasting models for sales/revenue prediction, aiding strategic planning.

Commodity Forecasting for Pharma Clients

• Provided market intelligence & procurement strategies using regression-based price forecasting, factoring in demand, supply, and economic trends.