Data Analyst Big

Vishnu Vardhan Keerthi

Data Analyst

561-***-**** ******.*@***********.*** LinkedIn

S U MMARY

Results-driven Data Analyst with 4+ years of experience in advanced analytics, machine learning, and big data technologies, proficient in extracting actionable insights from complex datasets using Python, SQL, and R. Experienced in developing ETL pipelines, implementing CI/CD practices, and leveraging cloud platforms for scalable solutions. Skilled in data visualization and dashboard creation, adept at collaborating across teams to drive process improvements and support data-driven decision-making. Strong background in statistical analysis and predictive modeling. S K I L L S

Methodologies: Agile, SDLC, Waterfall

Programming Languages and Libraries: Python, SQL, R. SCALA Database: Microsoft SQL Server, Oracle Database, MongoDB, NoSQL, CASSANDRA, PostgreSQL Data Visualization: Tableau, Power BI, Microsoft Excel (advanced) Big Data Technology: Hadoop, Apache Spark, Apache Kafka, Apache Airflow, Databricks Packages: Pandas, NumPy, Pytorch, TensorFlow, Scikit-Learn, seaborn, Matplotlib, SciPy, Plotly Cloud Platforms & DevOps: AWS, Microsoft Azure, Snowflake, Docker, Kubernetes, Jenkins Version Control: Git, GitHub

Soft Skills: Critical thinking, problem-solving, Attention to detail, Data storytelling, Collaboration with cross-functional teams E D U C A T I O N

Master of Science in Data Science and Analytics May 2024 Florida Atlantic University Florida, US

Bachelor of Technology in Computer Science and Engineering May 2020 Jawaharlal Nehru Technological University Hyderabad, India W O R K E X P E R I E N C E

Data Analyst BNY Mellon Florida January 2024 - Current

• Utilized Python (pandas, NumPy) and SQL (MySQL, PostgreSQL) to clean and analyze operational data, enabling the team to identify process improvement opportunities.

• Utilized advanced data mining techniques and Databricks for big data processing to uncover hidden correlations and anomalies, enhancing the accuracy of predictive models and decision-making processes.

• Applied Python, Microsoft SQL Server and Apache Kafka for real-time data streaming and analysis of wealth management system data, generating operational insights that streamlined transaction processing, reducing errors by 30%.

• Partnered with the Technology team to design and deploy an ETL framework using dbt and Snowflake, integrating CI/CD pipelines via Jenkins for automated testing and deployment. This enhanced data integration and significantly strengthened Operations reporting.

• Collaborated with the Operations team to enhance and manage Tableau dashboards, effectively tracking crucial operational KPIs.

• Identified key trends and patterns within large datasets, implementing efficient data structures for optimized analysis resulting in actionable insights and strategic recommendations for business improvements.

• Conducted statistical analysis and time series forecasting using R and Jupyter Notebook, developing predictive models for client behavior and attrition risks in the Private Wealth Management segment, supporting the Operations team's efforts to anticipate future trends Data Analyst Trigent Software India March 2019 - July 2022

• Utilized Azure Cloud and Hadoop ecosystem for large-scale data storage and analysis, collaborating with the IT team to ensure secure data access and processing from 100+ dermatology clinics across the network.

• Developed and optimized Apache Spark applications using PySpark to process and standardize large volumes of CSV files from diverse clinic management systems, improving data consistency and reducing processing time by 70% compared to previous Python scripts.

• Created and maintained SQL queries for regular and ad-hoc reporting, delivering timely insights to stakeholders on key performance indicators such as patient visits and resource utilization.

• Designed interactive Power BI dashboards to visualize clinic performance metrics, incorporating timeseries forecasting models to predict patient visit trends, this enhanced reporting capability contributed to the transition from monthly to more frequent reporting cycles and improved operational planning.

• Conducted data scraping to gather valuable information from various sources, enriching datasets and expanding analytical capabilities.

• Participated in data process improvement initiatives, identifying areas for automation in routine operations and suggesting solutions to enhance data quality and analysis efficiency, including the implementation of Docker containers for consistent development and deployment environments.

P R O J E C T S

Customer Churn Prediction

• Developed a Random Forest model to predict customer churn for a major telecom company, achieving 88% accuracy and 0.92 AUC-ROC score, conducted comprehensive data preprocessing and exploratory data analysis (EDA) to clean and understand the dataset.

• Created visualizations to identify and communicate top churn predictors to stakeholders.

• Implemented targeted retention strategies based on model insights, contributing to a 10% reduction in overall churn rate. Sales Data Analysis and Forecasting

• Sales data analysis and ARIMA forecasting for a retail company.

• Developed an ARIMA model with 90% accuracy, identified key trends and seasonal patterns through comprehensive analysis, and provided actionable insights, optimized inventory management and stock levels, enhancing decision-making for sales and marketing teams. C E R T I F I C A T I O N S

Python for Data Science by IBM

Data Analysis with Python

Contact this candidate