Implemented a single-shot instance segmentation algorithm from this research paper by assigning instance categories to each pixel based on location and size of instance. Achieved a mean average precision of 66.3% with a dataset consisting of vehicles, humans and animals
Implemented the YOLO algorithm for the purpose of object recognition of cars, humans and traffic lights from a dataset of more than 3000 images.
Performed regression to predict the amount of money a project can get funded for, and classification analysis to predict whether the project could successfully raise the quoted funding target given the project details. Combined dataset from Kaggle and data scrapped from Kickstarter website to obtain a dataset of 69210 projects, which contained new features like the number of pictures, textual description of projects, etc.