Depression is expensive to all nations in the world. How the causes of depression are understood is constantly evolving. This paper looks at socioeconomic contributors to depression with care for current understandings of the problem along with recent data. Previous understandings of an inverse relationship between income and depression are bolstered here along with other mental health symptoms. The analysis is conducted with an ordinal logistic regression model assuming proportional odds, implemented in this regression are two unique instruments for personal and family income. The results in this paper are relevant to public policy professionals who aim to minimize depression’s cost to their society.

This project aimed to forecast various exchange rates utilizing a RNN with the Keras library. Of note is the ability of the model to forecast exchange rates more effectively than index funds such as the S&P 500. Code for this project can be seen on my github. here!