Deep Learning Model Implementation: Embeddings for Categorical Variables

Using embeddings to explore US house prices and migration patterns

For many complex prediction problems, Deep Learning (DL) methodologies such as CNNs, NLP, and fully-connected networks offer the highest levels of performance. This typically comes at the cost of understanding the role of the explanatory features in prediction outcomes. While Machine Learning (ML) methodologies based on statistical methods offer a variety of techniques including variable selection…