SNEHA KONDAPALLI

Mobile Number: 425-***-****

Email: ad3bfi@r.postjobfree.com

Current Location: New Jersey

LinkedIn: https://www.linkedin.com/in/sneha-kondapalli/ GitHub: https://github.com/snehakondapalli

As a Data Science Graduate Student, I am seeking opportunities to leverage my broad background in programming, analytical skills, and database development. With proficiency in SQL, Python, and Power BI, I aim to contribute my skills and knowledge to drive impactful data-driven solutions in a professional environment. TECHNICAL PROFICIENCIES:

Applications – Microsoft tools like Excel, Word, PowerPoint, Outlook, Google Sheets, Visual Studio Code, Jupyter, Google Collab, Databricks, GitHub

Hadoop/Bigdata: HDFS, Spark

Cloud Technologies: AWS, EC2, ECS, S3, EMR, Lambda, Apache Airflow, AWS Redshift, AWS Glue, Data bricks Programming Languages: Python(NumPy, Pandas, SciKit-Learn, Matplotlib, Plotly Express, Seaborn, geo pandas, Sci- Py, TensorFlow, Keras), SQL, HTML, CSS.

Real-time streaming: Apache Spark streaming

Databases: MySQL, SQL Server.

Operating Systems: Windows, Linux.

Visualization Tools: Power BI, Tableau.

SDLC: Agile

Machine Learning: Clustering, Regression, Classification. WORK EXPERIENCE:

BEPEC Solutions, India Aug 2022 –Till Now

Data Science Intern

§ Worked on Projects involving Advanced Analytics & Predictive Modeling with a proven ability to formulate and solve complex analytical problems.

§ Skilled in extracting and analyzing data from multiple systems, summarizing key insights, and creating impactful visual representations with actionable recommendations.

§ Create and deliver reports using Tableau and presentations to explain and document your results.

§ Built ML Model using Logistic Regression & Decision Tree Classifier and Apply Feature Selection Techniques, Feature Scaling & Label Encoding Techniques using Python. Tech Mahindra, India, Hyderabad

Data Engineer, Verizon Jan 2020- Dec 2021

Optimized ETL Processes for Cloud Environment:

§ Maintaining 99.8% data pipeline uptime while ingesting streaming and transactional data across distinctive major data resources utilizing Spark, S3, and Python.

§ Using Apache Spark, I designed and constructed a scalable and fault-tolerant large data processing pipeline, lowering processing time by 70% and increasing data accuracy by 20%.

§ For quicker performance, I appraised the SQL scripts and built them with Spark SQL.

§ Reduce processing times and improve scalability using parallel processing, distributed computing, and caching techniques.

§ Experience with setting up and operating data pipelines (batch and real-time) and data wrangling procedures using Python or SQL in a cloud environment.

Data Analyst, Verizon Feb 2017 – Jan 2020

Call Center Analysis Project,

§ Worked on call transfer processes for timely analysis and reporting within the call center environment and reduced the transfer percentage by 40%.

§ Developed strategic reports for call center leadership, enhancing decision-making and quality improvement initiatives.

§ Conducted root cause analysis on client escalations, contributing to service enhancement by 80%.

§ Collaborated cross-functionally and built interactive dashboards to provide data-driven insights for key business decisions in the call center.

§ Demonstrated predictive analytics models to forecast future incoming call trends with an accuracy of 85%. Employee Performance Analytics Using Python & MySQL

§ Robust data-cleaning processes to ensure accuracy and consistency.

§ Utilized Python scripts for preprocessing, addressing missing values, and standardizing data formats.

§ Set benchmarks to measure individual and team-based performance and reduced the call handling time by 50%.

§ Engineered individual employee scorecards, providing a comprehensive view of performance metrics.

§ Generated team-based performance reports to evaluate collaborative achievements and areas for improvement for the employees.

Academic Projects:

Sentiment Analysis Using Tensor Flow on IMDB data with BERT model.

• The trained sentiment analysis model can be applied to analyze the sentiment of textual content, such as resumes. By adapting the model to understand positive and negative sentiments in text Transfer Learning from the VGG19 pre-trained model to the Tensor Flow Flowers dataset to identify the training loss, accuracy, and Validation loss.

• The skills demonstrated in this project, including transfer learning, model fine-tuning, and evaluation metrics tracking, showcase proficiency in adapting pre-trained models for specific image classification tasks. This expertise can be applied to various domains, including analyzing and classifying images, enabling a more detailed understanding of the visual content.

Data analysis using Python, specifically with the Netflix titles data.

• Applied advanced data transformation techniques to handle multi-country and multi-genre entries, enhancing dataset quality. Thorough data aggregation to count movies/shows by release year, unveiling insightful trends since 2000.Identified and visualized the top 30 directors, contributing to strategic decision-making. Utilized geo-pandas to create a map plot illustrating countries producing more than 50 movies/shows, showcasing proficiency in geographic data visualization.

Exploratory Data Analysis on Covid dataset.

• Thorough data cleansing was conducted, identifying the countries and states most severely impacted and determining elevated mortality rates. The exploratory data analysis (EDA) yielded a holistic comprehension of the COVID-19 dataset, delivering valuable insights into its temporal, geographical, demographic, and socioeconomic dimensions. Certifications:

1. Tata Data Visualization: Empowering Business with Effective Insights Job Simulation on Forage - January 2024 EDUCATION:

Montclair State University (MSU), Montclair, NJ

Master of Science in Data Science Aug 2022- Expected Graduation May 2024 Auroras Engineering College, India

Bachelor of Technology in Mechanical Engineering May 2016 Minor in Mathematics

Contact this candidate