Nitin Chauhan

Developed and deployed a scalable data infrastructure platform for the German electricity market (Strommarkt) and Volume Forecasting (UK), facilitating the migration of volume forecasting models from legacy systems to E.ON's Energy Market Data Platform (EMDP). Developed custom software applications and REST APIs using Python, FastAPI, and Azure Databricks, with data warehousing on Snowflake and insights visualized in Power BI. Currently testing and refining optimization algorithms for Flexibility Trading in the German balancing energy and intraday markets (e.g., aFRR/mFRR, EPEX SPOT). Focused on enhancing short-term trading strategies by aligning asset dispatch with market signals and grid requirements, using near-real-time data to improve bidding accuracy and asset utilization across decentralized energy assets (Batteries, CHP, etc.). E.ON Corporate Influencer focusing on the niche of Energy Markets on representating Energy Intelligence department with ongoing project development, market analysis and future outlook.

Demonstrated exceptional proficiency in forecasting energy consumption models, consistently exceeding accuracy benchmarks by 10%. This achievement resulted in a 5% reduction in fuel-related expenses and an impressive 12% decrease in unplanned maintenance costs. Optimized models to identify opportunities for energy savings, revenue generation, and sustainability improvements. Drove initiatives focused on accurate energy forecasting to optimize resource allocation and mitigate risks. Developed and maintained rigorous data quality standards and governance processes, ensuring the accuracy, integrity, and security of maritime data. Utilized AWS Sagemaker to deploy end-to-end pipelines for MLOps, enhancing monitoring capabilities to identify any model decays and improving transparency in data operations.

Incorporated sophisticated techniques, including customer clustering and classification, to group similar customer behavior and transactional activities. This approach aids in detecting unusual or fraudulent conduct by identifying patterns and trends. Additionally, this technique enables the analysis of relationships and linkages between customer behavior, transaction volumes, and other variables to flag potential risks.