Machine Learning Data Analyst

Nitin Balakrishna Kandula

CUMMING, GA 469-***-**** **************@*****.*** linkedin.com/in/nitinkandula DATA ANALYST DATA SCIENTIST DATA ENGINEER

PROFESSIONAL SUMMARY

Data Analyst with over 3+ years of experience, specializing in Python, advanced SQL, and machine learning. Expert in statistical analysis, Root Cause Analysis and data analytics, using tools like Power BI for impactful data visualization and storytelling. Skilled in A/B testing and Ad hoc reporting, enhancing data-driven decision-making. Proficient in MS Office, enabling efficient data management and presentation. Committed to transforming complex structured and unstructured datasets into clear, actionable insights through innovative and meticulous analysis. AREAS OF EXPERTISE

ü Root cause analysis ü Python ü Storytelling ü MS Office ü SQL (Advanced) ü Data Analytics ü PowerBI ü A/B Testing ü Tableau ü Statistics ü Ad hoc Reporting ü Azure Cloud Services EDUCATION

Master’s in Business Analytics, Data Engineering and AI, University of Texas at Dallas, Richardson, TX Bachelor’s of Science in Computer Science and Engineering, Mahindra Ecole Centrale, India AI/ML

• NaturalLanguageProcessing • PySpark • Computer Vision • Spacy

• GroqAI

• TensorFlow

• Sckit-Learn

• ML Flow

• Neural Networks

• Streamlit

• NLTK

• Data Mining

PROFESSIONAL EXPERIENCE

Computer Programmer–AI/ML, R2 Technologies Corporation, Alpharetta, GA Jan 2025 – Present Developed and deployed a Resume Analyzer for performing Similarity Analysis and People Analytics using Python NLP and Streamlit, integrated with Azure Blob Storage for data management, and powered by Groq AI for analytical accuracy and hosted seamlessly on Azure Web App.

• Developed and deployed a Resume-JD Similarity Analyzer Chatbot using Streamlit, achieving 90% accuracy by leveraging Groq’s LLM for enhanced skill and context analysis.

• Leveraged NLP technologies (spaCy, NLTK, PDFminer) to achieve 85% precision in extracting skills and 80% accuracy in candidate screening analysis, significantly boosting job match accuracy.

• Integrated Azure Blob Storage to enhance system responsiveness and data processing scalability, cutting data retrieval times by 50%.

• Engineered sophisticated algorithms for detailed Similarity Analysis and scoring between resumes and job descriptions, enhancing precision in candidate-role matching and supporting informed decision-making.

• Configured a CI/CD pipeline by linking GitHub to Azure Web App automating build and zero-downtime deployment of the Streamlit-based Resume Analyzer and eliminating manual release steps.

• Tech Stack: Python (NLP), Streamlit, Azure Blob Storage, Groq AI, Azure Blob Storage, Azure Web App. Telecom Customer Churn Analysis, Richardson, TX Aug 2024 – Dec 2024 Led a Public Churn Analysis project utilizing Python,Azure Databricks and Blob Storage, employing Random Forest model and XGBoost model to predict and analyze transit patterns.

• Developed a Churn Analysis project using Boosted Tree Ensemble Model to predict Churn patterns based on wide range of features and understanding features that effected Churn the most.

• Engineered an end-to-end churn prediction pipeline using XGBoost with SMOTE balancing and Hyperopt tuning, achieving over 90% accuracy in classifying customer churn behavior.

• Performed deep exploratory data analysis using Power BI and Seaborn, uncovering key behavior patterns.

• Implemented automated ETL pipelines in Azure Databricks using PySpark, for data processing cutting time by 60%.

• Tech Stack: Python, XGBoost, Azure Blob Storage, Azure Databricks, MLflow and PySpark. PROFESSIONAL EXPERIENCE CONTINUED

Walmart Sales Project, Richardson, TX Jan 2024 – May 2024 Conducted root cause and statistical analysis on Walmart sales datasets using Python, developed predictive models

(Linear Regression), and created Power BI dashboards with KPI visualizations to support data-driven decisions. data.

• Sourced multiple Walmart sales datasets from online repositories spanning 3 years and prepared them for Data Modeling and Root Cause Analysis (RCA).

• Performed a RCA on Walmart dataset in using Python and statistical methods, identifying key metrics that impact sales.

• Developed predictive models (Linear Regression) in Python to forecast operational trends and anomalies, enabling proactive business strategies and operational enhancements.

• Designed a Power BI Dashboard with KPIs including % Revenue Change seasonal change for clear decision making

• Developed time-series line charts to visualize sales trends over monthly intervals, revealing seasonal patterns and performance dips improved forecasting accuracy by 18%.

• Tech Stack: Python(statistical analysis, root cause analysis), PowerBI (DAX). Data Specialist, CMS Computers Limited, Hyderabad, India Sep 2021 – Nov 2022 As a Data Specialist at CMS Computers Limited, I optimized data extraction, transformation and analysis from TS- iPASS web site using Microsoft SQL Server, Excel, and PowerBI.

• Engineered and executed complex SQL queries to optimize data extraction, improving data retrieval efficiency by 30% and enhancing report accuracy.

• Leveraged advanced Excel and PowerBI to analyze large datasets, creating pivot tables and interactive visualizations that drove strategic decisions and increased stakeholder engagement.

• Collaborated effectively with cross-functional teams to enhance data collection and integration processes, resulting in a 20% improvement in data quality and access.

• Innovated and implemented improved data processing workflows, cutting down reporting timelines by 40% for critical monthly and quarterly business reviews.

• Tech Stack: SQL Server, Excel, PowerBI.

Database Developer Intern, CMS Computers Limited, Hyderabad, India Jan 2021 – July 2021 As a Database Developer Intern at CMS Computers Limited, I streamlined data integration from multiple sources into a centralized SQL Server database and created dashboards in PowerBI.

• Streamlined data integration from multiple sources into a centralized SQL database, enhancing data consistency and accessibility.

• Maintained and Conducted Data Analysis in Excel, facilitating rapid ad-hoc data analysis to support the management.

• Utilized PowerBI to design and manage a dashboards tracking application rates for government issued TS- IPASS industrial setup approval.

• Tech Stack: SQL Server, Excel, PowerBI.

CAREER HIGHLIGHTS

• Engineered a Resume-JD Similarity Analyzer with 90% accuracy, enhancing recruitment efficiency using Streamlit, Python NLP, and Azure integration.

• Utilized machine learning models for Data Analysis and LLM powered applications to conduct Analysis.

• Designed and managed Power BI dashboards to track application trends for government-issued industrial setup approvals.

TRAINING & CERTIFICATIONS

• Databricks Certified Data Engineer Associate, Databricks Oct 2024

• Associate Data Engineer, DataCamp, Dec 2024

• Data Analyst in Power BI, DataCamp, Feb 2025

Contact this candidate