Used SQL queries to analyze historical baby name trends, identifying top names by year. Grouping, ordering, and aggregating data yielded insights into naming trends over time.

Employed Python and pandas to manipulate and analyze data, preparing it for SQL querying. This involved filtering, joining, and summarizing data to efficiently extract key metrics like a name's peak popularity duration.

Evaluated various Machine Learning models (Logistic Regression, SVM, KNN, Random Forest, Decision Tree, XGBoost) through rigorous hyperparameter tuning and cross-validation, achieving 95% precision and 92% recall.

Implemented a comprehensive model evaluation strategy, utilizing key metrics to identify the best-performing model, enhancing predictive accuracy by 20% compared to baseline models.

Created a machine learning classifier to forecast loan approval status using applicant data, achieving 85% accuracy on test data.

Optimized the data preprocessing pipeline by encoding categorical variables and reshaping input data, improving the model's loan status prediction accuracy and efficiency.

Performed comprehensive financial analysis using Python, Pandas, and Plotly, focusing on risk-return analysis for major tech stocks (AAPL, GOOG, MSFT, NFLX). Quantified and visualized daily returns and volatility, offering actionable insights on investment stability and profitability.

Utilized data manipulation techniques to analyze vast datasets, pinpointing AAPL as the stable, low-risk investment and NFLX as the most volatile. This analysis guided strategic investment choices by presenting risk and return metrics for each stock.

Created a sentiment analysis algorithm for Tinder reviews in Python, categorizing feedback as Positive, Negative, or Neutral. Analysis showed overwhelmingly positive sentiment, indicating high user satisfaction.

Used Python's data tools to process thousands of user-generated pieces, revealing a sentiment score distribution. Most experiences were neutral or positive, with positive reviews significantly outnumbering negatives.

A DES (Discrete Event Simulation) project to model and simulate a small scale manufacturing system which produces a single product using necessary assumptions.

Using ARENA software, production throughput of the given system was achieved.