Snehashish Chatterjee

Data Analyst with 4+ years of experience driving data-driven decision-making through statistical analysis, predictive modeling, and time-series forecasting. Proficient in Python and SQL, with applied experience in Machine Learning, NLP, and Generative AI for business forecasting, root cause analysis, and KPI development. Skilled in building interactive BI dashboards and data visualizations that turn complex data into clear, actionable insights for stakeholders.

Software Engineer 1 at Bank of America (2023-09 – Present)

• Optimized infrastructure capacity planning by analyzing 2 years of weekly storage utilization data across 40+ internal teams using Python, Pandas, Exploratory Data Analysis (EDA), and Trend Analysis, identifying 60% unused provisioned capacity and enabling stakeholders to optimize resource allocation and infrastructure planning.
• Developed a 90% accurate Machine Learning forecasting solution by integrating Time Series Analysis with LLM-based sentiment analysis on historical commodity and market news data using Python, SQL, and scikit-learn, enabling proactive business planning.
• Reduced manual reporting effort by over 10 hours per month by designing 15+ interactive Business Intelligence (BI) dashboards that consolidated operational KPIs, infrastructure health, and reconciliation insights using Power BI, Tableau, and Grafana, enabling Data-Driven Decision Making through executive reporting, real-time SLA monitoring, and actionable business recommendations.
• Enabled data-driven infrastructure capacity planning by integrating Data Lineage with server performance metrics and performing Correlation Analysis, Hypothesis Testing, and Time Series Analysis using Python, SQL, and Dynatrace, identifying seasonal workload patterns that informed proactive resource allocation and optimized infrastructure readiness for uninterrupted business operation.

Academic Tech Intern at Bank of America (2022-09 – 2023-09)

• Reduced debugging effort by over 8 hours weekly by designing an end-to-end Data Lineage and log-based trade tracking solution using Python, Microsoft SQL Server, Splunk, SSIS, Tableau and Grafana, enabling cross-functional teams to accelerate Root Cause Analysis and improve operational efficiency across a multi-stage reconciliation pipeline.
• Improved reconciliation volume forecasting accuracy to 90% by performing end-to-end Time Series Analysis on five years of global reconciliation data across APAC, EMEA, and AMRS using SQL and Python, enabling cross-functional teams to build scalable Predictive Analytics solutions for future reconciliation volume planning.

Master's in Computer Science Engineering - Specialisation in Big Data Analytics – Vellore Institute of Technology (VIT) (2021-07 – 2023-07)

Bachelor's in Computer Science Engineering – H.M.R Institute of Technology & Management (GGSIPU) (2017-07 – 2021-07)