🎓 Data Science and Applied Statistics Graduate (GPA: 4.00/4.00)
📍 Michigan Technological University
🔍 Passionate about using data to automate repeatitive tasks, find insights, and build Machine Learning models that help businesses to maximize the revenue!

I specialize in Data Science Life Cycle — from collecting raw data to building real-world solutions.
Here’s what I do best:

• ⚙️ ETL Pipelines: Build and deploy scalable ETL workflows using Apache Airflow and Docker to automate data extraction, transformation, and loading in Database

• 📊 Data Analysis & Visualization: Reveal hidden insights using Descriptive & Inferential Statistics, Hypothesis Testing, and A/B Testing, and create dynamic dashboards in Tableau, Power BI, and Excel

• 🤖 Machine Learning & Modeling: Strong mathematical and algorithmic understanding across forecasting, regression, classification, clustering, deep learning with suitable pre-processing steps for each predicitve model and hands-on experience with building and optimizing ML models.

• 🧠 Problem Solving: Passionate about asking the right questions, interpreting trends, and driving decision-making with data

• Languages: Python, SQL (Advanced), R
• Libraries & Frameworks: Scikit-learn, PyTorch, TensorFlow, Pandas, Numpy, BeautifulSoup, Matplotlib, Seaborn, Streamlit
• Core Competencies: Time Series Forecasting, Machine Learning, Predictive Modeling, Natural Language Processing
• Statistical Methods: Inferencial Statistics, Descriptive Statistics, A/B Testing, Hypothesis Testing
• Data Tools: Apache Airflow, Docker, PostgreSQL, Tableau, Power BI, Excel
• Big Data: PySpark
• AI: Retrieval-Augmented Generation (RAG), LangChain, Hugging Face, ChromaDB, Prompt Engineering

Courses Assisted:

• CS5821 / CS4831: Advanced Data Mining
• MA5781 / MA4781: Time Series Analysis and Forecasting
• UN5550: Introduction to Data Science
• DATA2210: Foundations of Data Science
  🔹 Mentored 100+ students in Python, R, SQL, and core statistical concepts
  🔹 Led labs, graded assignments, and clarified complex data science topics

• Developed geospatial clustering models to optimize fiber network cabinet placements
• Built ML pipelines to automate analysis and reduce training time by 80%
• Fine-tuned image classification models using TensorFlow, improving accuracy to 82%

• Resolved 3+ daily classroom tech emergencies across 50+ classrooms
• Trained faculty/staff on using A/V systems, reducing downtime significantly

Explore my featured projects that span across ETL pipelines, forecasting models, NLP applications, and AI systems:

• ETL-Stock-and-Financial-News-Analysis - End-to-end pipeline for extracting, transforming and analyzing financial news data.
• End-to-end-loan-funnel-Analysis - Data-driven optimization of loan application conversion rates.

• User-Expanse-Forecasting-using-XGBoost - Gradient boosted models for predicting user spending patterns.
• Housing-Index-Forecasting - ARIMA modeling to predict US housing price trends.
• Predicting-Student-Dropout-Rate - Machine learning models to identify at-risk students and predict dropout probability.

• RAG-IT-Chatbot-GPT3.5-LangChain - Advanced retrieval-augmented generation chatbot for IT support using GPT-3.5 and LangChain.
• Rubber-Duck-Chatbot - Interactive debugging assistant for Python developers using regex, AST parsing and NLP techniques.
• IT-Ticket-Classification - Automated classification system for IT support tickets using text mining and NLP.

• California-Wildfire-Data-Analysis - Comprehensive analysis of wildfire patterns in California from 2014-2025.
• Streamflow-Prediction - Regression analysis to predict extreme streamflow events.

• Movie-Release-Date-Analysis - Optimizing release timing for animated films to maximize box office returns.

• Self-Solver-Wordle-Game - Algorithmic approach to optimally solve Wordle puzzles.

If you’re working on exciting problems where data can make a difference, I’d love to collaborate or contribute.

📫 Email: [email protected]
🔗 LinkedIn: SriAishwaryaMahimaGade
📎 Resume: View Here