The goal of this project was to create a convolutional neural network (CNN) model that can recognize handwriting from the first five letters in the alphabet (A,B,C,D,E). We had to use transfer learning in order to create a model that can do that. Transfer learning is when a machine learning model that is trained to solve one problem is applied to solve a different but related problem. In this scenario we used a CNN that was trained to recognize handwritten digits and applied it to recognizing handwritten letters.

In this project we try to predict income and gender using US Census Data. We will use classification models to try to predict both variables. Before we try out the different classification models there was some data exploration and processing that had to occur first: 1 - Since income data was a numerical variable, we changed it to a categorical variable where the income was either <= 50k or >50k. 2 - We deal with missing and duplicate values 3 - Removal of outliers 4 - Correlation between features 5 - One-hot-encoding categorical variables 6 - Splitting data into training and test Data