Data Scientist
Current• Achievements:o Promoted to a Data Scientist to work on advance data science projects. o Developed production level machine learning solutions using many models like linear regression, logistic step-wise regression and random forrest.o Successfully gave 2+ R&D project demos to company CTO, 1 demo to company CEO.o Successfully shipped BlackLine's first AI platform "Intercompany Predictive Guidance". o Developed a fully-functional UI interface giving AI predictions to the user.o Developed a robust data-engineering infrastructure for our team.o Developed a hierarchical clustering model which can create profiles of financial transactions and their likelihood group of billing cycle.o Developed a matching algorithm to match past financial transactions with their future versions.• Role Background:o Part of the Research and Development team within the Engineering org where I am working with internal senior stakeholders, process owners and subject matter experts for our projects.o My role is of a 'Full-stack' Data scientist, where I am doing data exploration, data collection, designing and developing ETL pipelines from multiple databases, doing EDA on collected data, designing and developing web interfaces using Gradio and R Shiny. Last but not the least developing machine learning models and deploying them in the web application for on-the-fly predictions. • Tech-stack:o Programming languages: Python, R, SQL. o Databases: Oracle RDS, and PostgreSQL RDS. o Devops and cloud services: AWS Lambda, AWS S3, AWS EKS, AWS ECR, AWS EC2, Jenkins, Hashi-Corp Vault.o Data Visualization: Tableau, Gradio, Shiny. o Code repository: GitHub.o IDE: Visual Studio Code, Jupyter Notebook and R Studio.