Data Analyst

• Mar 2021 - Present

Data Analyst

• Sep 2020 - Mar 2021

Data analyst Intern

• Nov 2019 - Jun 2020

Project Title: Anomaly Detection• Preparing an Azure ML pipeline to detect anomalies in consumption of Buckman chemicals at real time. Preparing PowerBI report to display the status of production and assisting Global team in creating Power Apps application.• Cloud Computing Platforms: Azure SQL, Azure Machine Learning Studio, Azure Data factory• Coding Languages Used: Python, R, Microsoft SQProject Title: Customer attrition preventor• Sales data of Buckman’s Performance chemicals for the past 3 years was used to predict the potential next resell that would happen in the future for a customer site and specific products.• Coding Languages Used: Python• Data Visualization: Power BI, Microsoft Excel.Project Title: Push Notification and Power BI Dashboard• A Power Apps API and Monthly Email push notification to keep the upper management up to date with the sales representative performance.• Cloud Computing Platforms: Azure SQL, Azure Machine Learning Studio, Azure Data factory• Coding Languages Used: Python, R, Microsoft SQL• Data Visualization: Power BI, Microsoft Excel• Automation tools: Power Apps, Microsoft FlowExploratory Data Analysis• Performed descriptive and inferential data analysis for various chemical industries (Such as Paper, Sugar, Leather etc.) for both the technical and financial aspects of the company. • Data Visualization: Power BI, Microsoft ExcelInternal Assistance• Preparing automated dashboard to for task tracking (for internal and global teams) • Data Visualization: Power BI, Microsoft Excel

Data Science Intern

• Jul 2019 - Nov 2019

Project Title: GRE Prediction Model• Students background data was from the past 2 years was used to predict the GRE score of students, in order to make a more informed decision during loan distribution phase.• Validated model had an accuracy of 86% with a standard error of 10 marks• Coding Languages Used: Python• Machine learning libraries used: Linear Regression, SVM, Random Forest Project Title: Default prediction• Data scraping information from multiple websites and automating tabulation of CIBIL details in order to accurately predict whether a customer would default or not on his re-payments. (cont.)• Machine learning libraries used: DT, CATBoost• Scraping libraries used: Selenium, Beautiful Soup• Text Manipulation: Regular ExpressionProject Title: Customer Information Dashboard• The outputs from the Default Prediction project were collated and displayed as a dashboard to the Credit Management team in the form of an excel on a regular basis.• UI Development: Tkinter, Excel

Marketing Executive

• Apr 2018 - Aug 2018

Responsibilities included to sought potential customer and initiate conversation to convert said client into a consumer. Also to maintain contact and perform the role of connection between the employer and the consumer. Responsibilities included to sought potential customer and initiate conversation to convert said client into a consumer. Also to maintain contact and perform the role of connection between the employer and the consumer.