Experienced Data Analyst with strong analytical skills specializing in data visualization, reporting, and manipulation. Seeking to leverage expertise in data engineering to design and optimize large-scale data pipelines.
Programming: Python, AWS, AWS Quicksight, Java Big Data: PxSpark, Hadoop, Hive, Sqoop
Database-SQL
Cloud - Amazon Web Services
Others: Machine Learning, Data Structure, Data Science, Data Warehousing, Data Modelling, Data Visualization, PowerMax, Power BI, Excel, Tableau, GIT, Google Spreadsheet, Pandas, HTML, CSS,Structure streaming ,Scala
1.Capacity Planning:Developed a predictive model to optimize capacity planning and resource allocation., Designed and implemented a data science model using Python and Pandas to predict capacity requirements. The model achieved 75 percent accuracy in forecasting resource needs, significantly improving planning accuracy., Enabled the organization to determine the exact number of personnel required for various tasks, optimizing workforce allocation and reducing operational costs., Improved capacity utilization by accurately predicting resource needs., Enhanced operational efficiency by aligning personnel deployment with actual requirements.
2.Developed an unofficial Brewdog Punk API application to programmatically access Brewdog's beer catalog with search functionality (HTML, CSS, JavaScript, React, Sass). Created 'The Dog Page App,' a single-page site using intricate CSS grid structures (HTML, CSS). Built a responsive Pickrr Dashboard Page with multiple reusable HTML and CSS components. GitHub: Brewdog Punk API, The Dog Page App, Pickrr Dashboard Page
3 Capstone Project: Multi-class classification of Alzheimer’s disease
○ Using MRI scans for early detection of Alzheimer’s; improved accuracy of existing model from 90% to 97.56% on the test dataset.
○ Classifies inputs into 4 broad stages of Alzheimer’s disease accurately, for pinpointing the severity of the disease.