Mohit Pandey

Currently leads the development of ETL pipelines and data models to provide critical insights for carbon market analysis and client compliance.

• Created robust ETL pipelines, integrating data from diverse sources including APIs, commit portals, and web scraping (Selenium) to power carbon market price analysis.
• Developed client-specific trend sheets and sophisticated models for carbon market analysis, enhancing predictive capabilities for multiple clients.
• Designed and implemented advanced Excel and Power BI tools to effectively track carbon market prices and compliance metrics across multiple clients.
• Reduced end-to-end reporting cycle from 3 days to just 4 hours by implementing Python, Selenium, Power Automate, and Zapier workflows, significantly boosting efficiency and accelerating decision-making.

Analyzed energy efficiency data and developed reporting solutions to optimize vessel operations and ensure regulatory compliance for a global shipping fleet.

• Designed comprehensive Power BI dashboards to monitor vessel CO2 emissions, fuel consumption per nautical mile, and EU-MRV compliance, enabling data-driven decision-making.
• Automated SEEMP II and EU-ETS monitoring plan reports using Python, reducing monthly reporting time by 40% and improving accuracy.
• Integrated Python scripts with vessel databases to proactively flag outliers in bunker data, preventing $72K in potential regulatory penalties.
• Analyzed fuel savings across 50+ ships, generating insights that contributed to optimized voyage planning and achieved 7% operational cost savings.

Collaborated with product and marketing teams to analyze user behavior, predict revenue, and enhance data quality to drive business growth.

• Collaborated with product and marketing teams to define key performance indicators (KPIs) such as churn rate, Average Order Value (AOV), and funnel drop-offs, aligning data initiatives with business goals.
• Designed and implemented real-time user behavior dashboards, which reduced churn by 12% through actionable insights.
• Developed predictive models to accurately forecast monthly revenue with 85% accuracy, supporting strategic planning and resource allocation.
• Cleaned and validated large datasets using Python, reducing data quality issues by 30% and improving data reliability for downstream analysis.

Developed and implemented an automated data pipeline for multi-source data integration, predictive analytics, and energy efficiency, enhancing data processing capabilities and enabling data-driven insights.