HEMANTH GANESH CHINTALA

Dedicated Data Science graduate student with a strong foundation in Electrical Engineering and extensive hands-on experience in software testing and embedded systems. Proficient in Python, R, SQL, and Machine Learning, demonstrating success in optimizing database operations and automating system processes. As a Graduate Assistant at Lewis University, contributed to research on software testing frameworks while previously enhancing system performance at Tata Consultancy Services through backend issue resolution and predictive analytics. Aiming to leverage data-driven solutions for innovative AI and data science initiatives that drive technological advancements and operational efficiency.

• SQL Online Course, Successfully completed a hands-on SQL online course organized by Frontlines EduTech Private Limited (FLM), recognized by the Government of India.
• Python with Data Structures and Algorithms (DSA), Completed an advanced online course on Python and DSA, certified by Frontlines EduTech Private Limited (FLM), recognized by the Government of India.
• Digital Skills: Artificial Intelligence – Accenture (FutureLearn)
  Issued February 2025 | https://www.futurelearn.com/certificates/myjpq82

- Achieved 90% overall score in an AI-focused course covering Generative AI, Automation, AI in Industry, and Human-AI Collaboration.

-Developed expertise in AI-driven problem-solving, industry applications, and future workplace adaptation strategies.

• Optimized SQL and PL/SQL scripts to enhance database performance, leading to a 25% improvement in query execution time.
• Implemented proactive monitoring and predictive analytics to identify potential system failures in advance, preventing major revenue losses.
• Saved significant time and revenue for the company by automating critical processes, minimizing downtime, and ensuring business continuity.

1. Chicago Crime Data Analysis,

In this project, I conducted an in-depth analysis of the Chicago Crime Dataset to identify crime patterns, hotspots, and trends using Python, SQL, and Power BI. Applied Machine Learning algorithms like Random Forest, KNN, and XGBoost for crime prediction and risk assessment. Developed data visualization dashboards to enhance public safety strategies and resource allocation. Utilized geospatial analysis, clustering (K-Means, DBSCAN), and predictive modeling to generate actionable insights. Focused on data preprocessing, feature engineering, and model evaluation to ensure robust crime forecasting.

2. Cirrhosis Patient Survival Prediction Using Machine Learning

• Developed a machine learning model to predict liver cirrhosis survival using classification algorithms like Logistic Regression, Decision Trees, and Random Forest.
• Performed data preprocessing, handling missing values, outlier removal, and feature engineering, improving model accuracy by 15%.
• Conducted Exploratory Data Analysis (EDA) to uncover key disease risk factors, identifying age, hepatomegaly, and albumin levels as primary indicators.
• Implemented 10-fold stratified cross-validation, achieving 86% accuracy and an AUC-ROC score of 0.94, ensuring robust model performance.