Created statistical models to determine whether or not to grant loan to a customer based on many different variables. Performed EDA, Decision Tree, Random Forest & Logistics Regression modelling with an accurancy of 85%

To ease the home buying experience, I created a python web-scrapping program which uses BeautifulSoup and HTML to scrap the Zillow website and locate the important parameters like price, address, sq ft, etc. and creates a tabular output.

Worked with R language and Tableau software on the dataset of more than 260k entries and 29 variables. Predicted the future possibility of a severe incident using various models like GBM, rpart, Random Forest with 80% accuracy.

• Predicted whether a tweet depicts a real disaster or not by building and training various ML models using Python, 79?curate. Various techniques were used like Tokenization, Stemming and Lemmatization, Autocorrect, Vectorization, etc.