Data Scientist with expertise in big data analytics and processing with keen interest in finance, currently an Assistant Manager in the Audit & Assurance (A&A) division at Deloitte India. Developed Spark SQL scripts for Expected Credit Loss (ECL) calculations for a major Indian NBFC, streamlining audit review processes. Created commission recomputation scripts for a large insurance firm and implemented advanced analytics for NBFCs and banking clients, achieving a 70% reduction in time and cost overheads. Developed an analytical tool for Deloitte India’s Talent Team using Spark, SQL, and Python, and designed an ETL pipeline to process over 500 raw financial data files for more than 100 clients using Spark. In previous experience an automated system was developed for extracting user details from policy bonds using EasyOCR, PyMuPDF, and Tabula, and a model was created to summarize policy benefits using NLP techniques with Spacy and Gensim. Personal projects include “StockedIT,” a Heroku-hosted website that recommends long-term investment stocks using real-time data and fundamental analysis, and a geo-spatial analysis and temperature prediction project using time series data and the ARIMA model. Technical skills include Python, MySQL, Spark Scala, Apache Impala, Apache Hive, Google BigQuery, MongoDB, Web Scraping, MS Excel, Databricks, machine learning models, NLP, neural networks, time series models, feature engineering, ensemble learning, SKlearn, Matplotlib, Seaborn, Folium, Tableau, PowerBI, DAX, and Google Sheets AI900 & DP900 certified. Received several awards for performance at Deloitte.