• Goal with this implementation was to construct a model that predicts whether an individual makes more than $50,000.
• In a non-profit setting, where organizations survive on donations, this helps in determining how large of a donation to request.
• Employed several supervised algorithms to model individuals' income using 1994 U.S. Census data.
• Then chose the best candidate algorithm from preliminary results. Further optimized this algorithm to best model the data.

• Trained an image classifier to recognize different species of flowers.
• This is somewhat similar to a phone app that tells you the name of the flower your camera is looking at. In practice you'd train this classifier, then export it for use in your application.

This was done using this dataset of 102 flower categories and transfer learning (a deep learning model trained on hundreds of thousands of images) as part of the overall application architecture

o The primary challenge was to provide a way for disaster response organizations then becomes to filter out the relevant and most important messages from millions of messages they receive following a disaster.
o Used NLP techniques like Count Vectorizer, TF-IDF to process this data and then train a supervised machine learning algorithm to classify disaster messages to appropriate categories.
o Used various optimization techniques to achieve ~95?curacy in prediction
o Using this application, an emergency worker can input a new message and get classification results in several categories and then route the problems to appropriate organizations.

• The goal for this project was to automate the loan eligibility process based on customer details provided during the online application.
• Performed Feature Engineering and various machine learning techniques to identify key features and create additional predictive features.
• Used Exploratory Data Analysis to draw important insights about the data.
• By implementing the solution, most eligible customers can be identified so that businesses can specifically target those segments of customers.

• The objective was to analyse the employee’s attritions by looking at historical HR attritions dataset.
• Used Exploratory Data Analysis to identify important insights about the data.
• Performed Feature Engineering and different machine learning techniques to identify key features.
• By implementing the solution, HR professionals can identify employee attrition and manage their organization’s manpower.