Data Science Machine Learning

YARRABOLU NAGA PAVANA PRIYA

Amherst, MA

ï linkedin.com/in/priya-yarrabolu 413-***-**** # **********@*****.*** § github.com/yarrap Education

University of Massachusetts, Amherst Amherst, MA

Master’s in Computer Science September 2023 – May 2025 (Expected) Relevant Coursework: Advanced Machine Learning, Responsible AI, Systems for Data Science. Indian Institute of Technology, Bhubaneswar Bhubaneswar, Odisha Bachelor of Technology in Mechanical Engineering July 2017 – May 2021 Relevant Coursework: Introduction to Programing and Data Structures, Linear Algebra, Calculus. Experience

Tiger Analytics Hyderabad, Telangana

Senior Analyst - Data Science July 2022 – July 2023

• Collaborated closely with the Vice President of a Fortune 500 client in the USA, playing an instrumental role in a high-priority Omni-Channel Data Harmonization project.

• Exerted PySpark to standardize columns in a massive 40-billion-record uncleaned data source, employing fuzzy matching techniques.

• Engineered an entity matching pipeline for a 5-billion-record data source, exerting Natural Language Processing (NLP) techniques like fuzzy matching, semantic matching with sentence transformers and BERT embeddings, and the DeepER model.

• Achieved a remarkable 95% mapping success rate for the top 90% selling UPC records with 89% accuracy. Analyst - Data Science July 2021 – June 2022

• Contributed to a Trade Promotion Optimization (TPO) project for a leading CPG client in Russia and France.

• Undertook full-cycle data preparation for 6 diverse sources, starting from raw data acquisition to data cleaning, transformation, and integration. Streamlined and automated the entire process, reducing manual efforts by 40%.

• Employed advanced modeling techniques, including Lasso and Bayesian regression, implemented using Azure Databricks for precise sales prediction.

• Collaborated in an agile manner with a 7-member team, closely aligning with the business to deliver models covering 90% of the client’s market share.

• Generated a remarkable revenue increase of 35% from 2020 to 2021. Projects

Customer Churn Prediction Python, Sklearn, Seaborn, Jupyter Notebook April 2021 – July 2021

• Developed an advanced machine learning classifier to accurately forecast customer churn.

• Performed thorough Exploratory Data Analysis (EDA) and Churn Cohort Analysis. Utilized predictive modeling techniques, employing Decision Tree, Random Forest, and AdaBoost classifiers. Applied hyperparameter tuning and chose the best-fitting model.

• Achieved the highest accuracy of 83% using the AdaBoost classifier. CIA Country Analysis and Clustering Python, Google Colab, Plotly December 2020 – February 2021

• Developed a robust KMeans Clustering model to identify similarities among more than 200 countries. Experimented with different cluster counts to optimize grouping accuracy and gain valuable insights.

• Undertook comprehensive data cleaning and subsequently employed feature engineering techniques. Utilized elbow plot method to determine the optimal number of clusters as 3 and carried out model interpretation. Penguin Species Prediction Python, Jupyter Notebook September 2020 – November 2020

• Implemented a Decision Tree Classifier to predict 3 penguin species with high accuracy, leveraging their physical attributes.

• Conducted exhaustive EDA, focusing on visualization methods like cat, pair, and scatter plots to reveal crucial patterns and applied feature engineering.

• Attained an outstanding 92% accuracy by harnessing the capabilities of the Decision Tree Classifier. Technical Skills

Programming Languages: Python, Java, SQL, C.

Python Libraries: Pandas, NumPy, Matplotlib, Seaborn, scipy.stats, Sklearn, Plotly, TensorFlow, Keras, xgboost. Software Tools: Pyspark, Microsoft Azure, Git, Microsoft Excel, Microsoft Word. Certifications: Statistics for Data Science and Business Analysis, Microsoft Excel from Beginner to Advanced.

Contact this candidate