Warehouse Management System Modernization: • Utilized data-driven strategies and optimized Snowflake SQL procedures to improve the fill rate, achieving a remarkable 12% increase in order fulfillment accuracy. This enhancement not only bolstered customer satisfaction but also led to an 8% reduction in order processing errors, significantly improving overall supply chain operational efficiency. • Played an integral role in the successful transition of over 50 procedures from the old warehouse management system to new one, resulting in a 15% reduction in order processing time and a 10% improvement in inventory accuracy.

● Designed and executed a sentiment analysis pipeline utilizing natural language processing (NLP) techniques to classify tweets into positive, negative, or neutral categories with a precision of 85% and recall of 90%. ● Conducted exploratory data analysis & processing of tweets including text cleaning, tokenization, and feature extraction, achieving a 20% increase in model accuracy compared to baseline models. ● Utilized data visualization tools such as Tableau to create interactive dashboards and deliver meaningful data insights, enabling informed data-driven decision making and continuous improvement of system through data storytelling.

● Designed and implemented a machine learning based recommendation system employing K-means clustering for songs and genres, focusing on metrics such as coverage, personalization, and diversity to enhance the user experience. ● Developed and maintained data warehousing and data processing infrastructure, integrating SQL and R for data manipulation and analysis, reducing the data processing time by 30% through time series analysis. ● Conducted comprehensive data analysis, visualization, and modeling to extract meaningful insights, utilizing business intelligence techniques to track and improve the system's performance.

1. Development of Data Quality Tool: • Designed, coded, and built a software tool for Data Quality checks on incoming data through the creation of data pipelines and ETL processes with the help of a team - The tool was able to successfully clean and analyze data from over 10,000 records in just 10 minutes, improving the accuracy of the data by 95%. • Developed and designed ADF pipelines to automate trigger for Azure Databricks notebook, which incorporated data warehousing techniques and big data technologies like Hadoop and Spark - The ADF pipelines successfully processed over 100 GB of big data in just 30 minutes, reducing the manual processing time by over 70%. • Eliminated human errors by automating the pipeline, resulting in a 100% accuracy rate in processing the data. • Conducted sessions with clients to understand business requirements and used data modeling and data visualization techniques to provide business intelligence using Google Charts & Microsoft Power BI. • Maintained a CI/CD platform for the tool using Git version control system and deployed it to the Azure cloud computing platform, ensuring scalability and performance optimization. 2. Development of Snowflake Data Extraction Scheduler: • Implemented a secure and interactive user interface on Microsoft Power Apps. The interface enabled users to trigger the extraction of data from databases such as MS SQL Server, and dynamically build Azure Logic Apps. • Developed an Azure function app to extract data from multiple relational databases and perform data migration to the user-defined cloud platform like AWS S3 and Azure Blob Storage. • Ensured data security and privacy by integrating the tool with Azure Active Directory, providing role-based access control and data governance capabilities, resulting in a 40% decrease in data breaches. • Followed Agile Methodology to meet client requirements and improve the tool's performance and scalability, resulting in a 25% increase in tool performance and a 30% reduction in development time.