Too Long; Didn't Read
Tree-based models like Random Forest and XGBoost have become very popular in solving tabular data problems. We’ll try to use fast.ai’s tabular module on the Blue Book Bulldozers Competition on Kaggle and see how far this approach can go. Deep Learning is more for unstructured data like image, audio or NLP, but embedding layers for categorical data changed this perspective. We'll use the deep Learning and Embedding Layers to solve tabular(structured) data problems in a Pandas DataFrame.