yarrap,Priya Yarrabolu,github

About

Hey, there! I am a master’s student currently majoring in Computer Science at the University of Massachusetts, Amherst. I am passionate about Artificial Intelligence, particularly in the realms of Natural Language Processing (NLP), Machine Learning, Deep Learning, and Information Retrieval.

I come equipped with 2 years of experience as a Senior Analyst at Tiger Analytics, where I engaged across diverse domains, including e-commerce, omnichannel, retail, and prominently in CPG. During this tenure, I gained expertise in Python, PySpark, and Azure, putting into practice advanced statistical analysis, predictive modeling approaches like Lasso and Bayesian Regression, as well as various NLP techniques. My recent projects at UMass have focused on enhancing the robustness of Large Language Models in Out-of-Distribution settings, developing an automated model selection framework for tabular data, and building a real-time tag recommendation system for Stack Overflow.

Connect with me:

Priya Yarrabolu's Projects

cia-country-analysis-and-clustering

Gain insights into similarity between countries and regions of the world by using clustering techniques.

cracking-the-data-science-interview

A Collection of Cheatsheets, Books, Questions, and Portfolio For DS/ML Interview Prep

customer-churn-prediction

Predicting whether a customer will churn or not based on machine learning models

ds-career-resources

Compilation of resources for aspiring data scientists

fuzzywuzzy

Fuzzy String Matching in Python

heart-disease-prediction

Utilizing Logistic Regression to determine the likelihood of heart disease presence in an individual.

mine-prediction-using-sonar-frequency

Built a machine learning model which is capable of detecting the difference between a rock or a mine using KNN Classification.

modelselection

This the repository for Model Selection algorithm on Tabular Dataset

opportunity-pipeline-forecasting

The probability of a customer buying a product was forecasted based on several business decision features. Performed Data Preparation, EDA and ran statistical conclusions, prior to fitting Logistic Regression, Decision Tree, Random Forest and XG Boost based models. Chose the best-fitting model according to model performance evaluation metrics.