Praveen Dubba

Data Analyst

https://www.opentalent.in/praveen-dubba

Senior Data Scientist

Vanguard

Key Strengths

Extensive experience in Machine Learning and Data Analysis, demonstrated through multiple competition wins and project implementations.
Proficiency in various ML models (Logistic Regression, Random Forest, XGBoost, SVM, Naïve Bayes) and techniques (feature engineering, NLP, dimensionality reduction).
Experience with GenAI models (GPT-4, DistilBERT) for customer feedback analysis and feature prioritization, aligning with modern data science trends.
Strong project portfolio showcasing practical application of data science skills in diverse domains like healthcare, manufacturing, and customer behavior prediction.
Proven ability to beat existing company models and achieve high accuracy in competitive environments.

Cultural & Operational Fit

Cultural Fit Analysis

The candidate's project diversity, including hackathons and Kaggle competitions, suggests a proactive and continuous learning mindset. The transition from IT Analyst to Data Scientist, and then Senior Data Scientist, indicates career growth and adaptability. The experience with GenAI/ML at Oracle aligns well with innovative environments. However, the target role is 'Data Analyst', while the candidate's experience is heavily skewed towards 'Data Scientist' and 'Senior Data Scientist', which might indicate a potential mismatch in role expectations or a desire for a more advanced analytical role. The certifications are in older BI/ETL tools, which might not directly align with a modern Data Analyst role focused on advanced analytics.

Soft Skills & Operational Fit

The candidate's project descriptions indicate a results-oriented approach and problem-solving skills, particularly in competitive settings. The ability to present business insights suggests good communication of technical findings. However, without specific assessment data on soft skills, a comprehensive evaluation of operational fit is limited.

AI is analyzing your overall score…

Identifying your key strengths…

Evaluating your skill match against the job requirements…

Assessing your cultural and operational fit

About

Senior Data Scientist with 11+ years of experience building Machine Learning models and ETL data pipelines.

Top Skills

Gen AIaspect-based-sentiment-analysisgpt-4autoencodersApache Kafkasupervised-learningChatGPTPrompt EngineeringAWS SageMakeramazon-athenaData VisualizationWord EmbeddingsUnsupervised LearningSQLMachine LearningRData MiningData ModelingAgile MethodologiesData WarehousingEtlAnalyticsStatistical ModelingStatisticsData AnalysisPythonTableauMicrosoft ExcelInformaticaHadoopRelational DatabasesMongoDBUnixMysqlRegression AnalysisHypothesis TestingBayesian MethodsDimensionality ReductionNatural Language ProcessingText MiningTime Series AnalysishiveLogistic Regressionlinear regressionScikit LearnData scienceInformation RetrievalProbabilityPredictive Modeling

Skills

Education

University of Connecticut School of Business

Masters in Business Analytics and Project Management

January 1, 2017 – January 1, 2018

Jawaharlal Nehru Technological University

Bachelor of Technology (B.Tech.), Electrical, Electronics and Communications Engineering

January 1, 2007 – January 1, 2011

Experience

Vanguard

Senior Data Scientist

April 1, 2025 – Present

Oracle

Senior Data Scientist - GenAI/ML

October 1, 2022 – April 1, 2025

Cerner Corporation

Data Scientist

November 1, 2018 – October 1, 2022

Kansas City, Missouri Area

SecureHomeIoT

Data Science Intern

February 1, 2018 – April 1, 2018

Hartford, Connecticut Area

Romp n' Roll

Data Science Consultant (Capstone Project)

August 1, 2017 – December 1, 2017

Hartford, Connecticut Area

Tata Consultancy Services

IT Analyst

February 1, 2012 – January 1, 2017

Hyderabad Area, India

Projects

AI model for feature prioritization

November 1, 2024 – November 1, 2024

▪ Built and fine-tuned LLM prototypes using Gen AI models (GPT-4) and other BERT-based AI models for customer feedback analysis, sentiment analysis, and personalized recommendations, leveraging LLM embeddings to boost customer engagement and satisfaction ▪ Implemented Aspect-Based Sentiment Analysis using an LLM, DistilBERT AI model, to extract granular insights from customer feedback data, enabling targeted product improvements and driving business decisions for feature prioritization

Predicting probability of stroke happening to Patients - Analytics Vidhya Competition - McKinsey Analytics Online Hackathon - Healthcare Analytics (Won 3rd place out of 2,255 participants)

April 1, 2018 – April 1, 2018

Skills: Machine Learning · Data Analysis

Image classification using Random Forest

November 1, 2017 – December 1, 2017

• Built a Random Forest model to predict the type of fashion article from images • Applied clustering techniques to group similar pixel intensities of the images • Applied grid search technique to tune the hyperparameters • Performed cross-validation to evaluate the performance of the model Tools/libraries used: Python, Pandas, Scikit-learn

Predicting Gender using Profile information collected from websites

November 1, 2017 – December 1, 2017

• Applied NLP techniques and developed new features, and Bag of Words model from username and profile descriptions to predict users’ gender • Built Logistic regression model, Naïve Bayes model, Support Vector Machines and Random Forest model, and evaluated them to select the best model Tools/Libraries used: Python, Sklearn, NLTK

Predicting Customer Churn - Travelers Data Challenge

October 1, 2017 – November 1, 2017

➢ Achieved an accuracy 3.5% higher than the company’s best model, and presented business insights about the drivers of customer retention to the company ➢ Performed feature engineering, feature selection and built a simple Logistic regression model to beat the company's existing GBM model Tools/Techniques used: R, Decision Trees, Logistic Regression

Predicting customers' future purchases

July 1, 2017 – July 1, 2017

Predicting customers' future purchases ➢ Analyzed large dataset (32 million rows), prepared aggregated data and performed feature engineering ➢ Built xgboost model to predict future buys based on customers’ previous purchases Tools/libraries used: R, ff, dplyr

Mercedes Benz Greener Manufacturing - Kaggle Competition

June 1, 2017 – July 1, 2017

• Achieved an R Squared value of 0.546, to predict the time a car takes to pass testing; Winner scored 0.555 • Performed feature engineering, dimensionality reduction, custom-made backward elimination algorithm and feature selection

Quora Question Pairs - Kaggle Dataset

March 1, 2017 – May 1, 2017

• Built xgboost model to predict whether a question pair is a duplicate or not • Used NLP techniques to prepare Bag of Words model, performed POS tagging using parallel processing in R and developed new features based on words and their similarities Tools/Libraries used: R, data.table, NLP, tm, RDRPOSTagger, foreach, doParallel , doSNOW

Key Strengths

Extensive experience in Machine Learning and Data Analysis, demonstrated through multiple competition wins and project implementations.
Proficiency in various ML models (Logistic Regression, Random Forest, XGBoost, SVM, Naïve Bayes) and techniques (feature engineering, NLP, dimensionality reduction).
Experience with GenAI models (GPT-4, DistilBERT) for customer feedback analysis and feature prioritization, aligning with modern data science trends.
Strong project portfolio showcasing practical application of data science skills in diverse domains like healthcare, manufacturing, and customer behavior prediction.
Proven ability to beat existing company models and achieve high accuracy in competitive environments.

Cultural & Operational Fit

Cultural Fit Analysis

Soft Skills & Operational Fit

Praveen Dubba

Key Strengths

Cultural & Operational Fit

About

Top Skills

Skills

Education

Experience

Projects

Certifications

Key Strengths

Cultural & Operational Fit