Through this project, I conducted a comprehensive analysis of extensive loan data, scrutinizing 109,874 data points and analyzing 145 features. Leveraging various advanced ML algorithms, this analysis is crucial for assisting clients in deciding whether to invest in peer-to-peer loans and determining which loans to choose. The goal of using predictive models is to estimate the risk of default associated with each investment option, thus helping clients balance risk and return in their investment portfolio.

In this project, I have analyzed 47,000 Yelp restaurant reviews to understand customer sentiments using various advanced machine learning algorithms. This project carries significant importance for restaurant owners seeking to enhance their Yelp ratings and attract more customers. By analyzing the sentiment within these restaurant reviews, it provides actionable guidance for improving customer experiences and making informed decisions to boost their online presence.

The In-Flight Performance Analysis project explored United Airlines' 12-month performance using 2.5 million+ Bureau of Transportation Statistics' records. Interactive Tableau dashboards analyzed market share, flight frequency, delays, and reasons. The project identified the top 5 delay reasons, offering actionable recommendations for improvement. Data-driven performance analysis enhances operations and customer satisfaction.

The Twitter Sentiment Analysis project understood COVID-19's impact on mental health via 16,000 tweets. It revealed prevailing emotions and sentiments during this period, providing insights into people's well-being and Twitter's collective mood. This project highlighted the importance of understanding public sentiment during crises and gaining meaningful insights from social media data.