Srimathi K

Data Science professional with expertise in Python and SQL, specializing in data preprocessing, exploratory analysis, and model tuning. Experienced in implementing MLOps best practices, including artifact version control and reproducible pipelines. Committed to collaborating with cross-functional teams to leverage data insights for strategic decision-making.

Red Bus Booking Streamlit app

• Scrapped Bus details from red bus website using Selenium to automate the extraction of Redbus data including routes, schedules, prices, and seat availability.
• Stored the scrapped data in SQL database
• Developed a Streamlit application to display and filter the scraped data.
• Implemented various filters by selecting route name, sorting by price (Low to high, High to Low), Bus Type and Star rating.

Data Spark – Exploratory Data Analysis for Global Electronics

• Executed end-to-end EDA on multi-dimensional datasets (sales, customers, products, stores) to uncover business insights for a global retail enterprise
• Performed extensive data cleaning, preprocessing for accurate trend identification, analysis and reporting
• Visualized key performance metrics with Python libraries (Matplotlib, Seaborn), and generated actionable recommendations to guide sales, marketing, and operational decisions

Gold rate predictor (USD → INR → gold price in INR/g)

• Collected historical USD to INR exchange rate and gold price data using yfinance, enabling automated data ingestion
• Performed exploratory data analysis (EDA) to detect outliers and ensure model robustness
• Built and trained a linear regression model, applying hyperparameter tuning (e.g. regularization, cross-validation) to optimize performance.
• Packaged pre-trained artifacts (scaler.pkl and regressor.pkl) to ensure reproducibility and consistency across deployed predictions
• Deployed a Gradio-based web interface, wrapping the prediction function for seamless user interaction and rapid deployment
• Integrated basic MLOps practices (artifact versioning, automated pipelines, scalability planning) to support future model retraining and operational readiness

• Master Data Science Program - Guvi
• Job simulation involving data analysis and forensic technology, Deloitte
• Microsoft Power BI - Guvi