Subhash Anagalabylu Ramachandra
Masters student at University of Texas at Dallas
About Me
Hello, I'm Subhash, a dedicated data enthusiast set to complete my Masters in Business Analytics in May 2024. Equipped with 4 years of work experience in Marketing Science and Web Analytics, I derive immense satisfaction from leveraging science and technology to solve growth challenges driving business value. Currently interning at Informativ LLC as a Data Analyst working on a Data Engineering Project tasked with building data piplines for lead management. Simultaneously, I collaborate with the Marketing Team to craft Power BI Dashboards and offer strategic insights.
My proven track record includes delivering impactful results in projects covering ETL reporting, data analysis, web analytics, and data visualization. As a perpetual learner, I am deeply interested in growth strategy, Machine Learning, Data Engineering, A/B testing, classification, regression, and maintain an unwavering commitment to continuous learning, particularly in areas that drive business growth through data-driven technologies. I am dedicated to making noteworthy contributions to the ever-evolving realms of technology.
Skills
Programming Languages
Frameworks/Libraries
Cloud Softwares
Analytics and Visualization Tools
Work Experience
- Executed table mapping techniques through stored functions and joins within MS SQL Server, enhancing the integration of 80 GB of customer information from three distinct company databases.
- Retrieved over 70K+ rows and developed six automated KPI tracking Power BI dashboards utilizing information sourced from Salesforce, Google Analytics, CRM, web scraping, and ad platforms for the executive leadership team.
- Automated monthly profit and loss reports using VBA Macros in MS Excel to reduce the report creation time by 50%.
- Boosted sales by 43% through upselling via Frequent Item Sets built using association rules and modeled pricing strategies for catalog management.
- Consulted on Dominos India account for strategic planning and API integration. Improved sales forecast accuracy by 18% using statistical analyses of Google Analytics and App data reports.
- Conducted A/B testing for vernacular banners on landing pages of a banking product, and provided recommendations that reduced bounce rates by 36%. This customer-centric initiative resulted in doubling the growth in visibility.
Education
Projects
Pandas / Python
Classification of Used Electronics Categories Using Machine Learning Algorithms
Category Classifier: This classification project focuses on utilizing advanced machine learning techniques, specifically Random Forest (RF), XGBoost, and Support Vector Machine (SVM), to categorize used electronics into two distinct classes: Budget-Friendly and Feature-Intensive.
sklearn / Python
Telecom Churn-Predictor with Random-Forest Using Python
Telecom Churn Predictor: A Python project implementing a Random Forest model to predict customer churn in the telecommunications industry. It aims to predict whether customers of a telecommunications company will churn or not, helping the company proactively identify customers at risk of switching to another provider.
Apache Spark / Hadoop
Flume Ingestion for Real-Time Finance Analysis with Spark and Hive
Stock Market Analysis: This project presents a comprehensive data analysis workflow within the Hadoop ecosystem, incorporating various ingestion methods, including API-driven approaches. The project covers direct file transfer, stream ingestion via Flume, and API-driven data ingestion using Sqoop.