Forecasting NYC Airbnb Housing Prices: Unveiling Trends and Insights from Open Data

Utilized ridge regression and gradient boosting techniques to predict NYC Airbnb prices, effectively uncovering critical pricing determinants. Evaluated model performance through robust metrics like Mean Squared Error (MSE), Root Mean Squared Error (RMSE), and R-squared, achieving notable accuracy.

Predictive Modeling of Titanic Survival Using Machine Learning

Utilizing Python, this project predicts passenger survival on the Titanic using machine learning. Through data preprocessing, feature engineering, and model selection, it achieves accurate predictions. Visualizations highlight insights and model performance.

Sales Performance Dashboard: Visualizing Profitable Trends and Product Insights

Developed a comprehensive sales analytics dashboard using Power BI, showcasing detailed insights for the years 2020 and 2021 across all months. Effectively tracked cash and online transactions, analyzing profit margins, quantity sold, and performance across various product categories.

HR Analytics Dashboard Creation using Power BI

Developed a comprehensive HR analytics dashboard using Power BI to provide deep insights into key HR metrics. Leveraged DAX functions and advanced Power Query to integrate and visualize data, enabling HR managers to track employee performance, retention rates, and recruitment efficiency.

Amazon Fine Food Sentiment Analysis: NLP Model Comparison (Vader vs Roberta)

Explore sentiment analysis techniques like VADER Sentiment Scoring, Roberta Pretrained Model, and the Transformers Pipeline on Amazon Fine Food Reviews dataset, showcasing diverse NLP methodologies in Python.

Smart Loan Approval with Machine Learning Models

This project leverages Decision Tree and Naive Bayes algorithms to predict loan eligibility. By analyzing customer data, the models classify applicants into eligible and non-eligible categories.

Laptop Price Prediction: Pandas EDA & Machine Learning in Jupyter Notebook

Implemented a complete workflow for predicting laptop prices using multiple machine learning models, including Linear Regression, Ridge, Lasso, KNN, Decision Trees, and ensemble methods, achieving robust accuracy through comprehensive evaluation.