We attempted to apply a novel approach to stock market predictions. The Logistic Regression machine learning algorithm (Joseph Berkson) was applied to analyze news article headlines as represented by a bag-of-words (tri-gram and single-gram) representation in an attempt to predict the trends of stock prices based on the Dow Jones Industrial Average. The results showed that a tri-gram bag led to a 49% trend accuracy, a 1% increase when compared to the single-gram representation’s accuracy of 48%.

In the age of growing technology, Computer Science (CS) professionals have come into high demand. However, despite popular demand there are not enough computer scientists to fill these roles. The current demographic of computer scientists consists mainly of white men. This apparent gender gap must be addressed to promote diversity and inclusivity in a career that requires high creativity and innovation. To understand what enforces gender stereotypes and the gender gap within CS, survey and interview data were collected from both male and female senior students studying CS and those who have left the CS program at Arizona State University. Students were asked what experiences either diminished or reinforced their sense of belonging in this field as well as other questions related to their involvement in CS. Interview and survey data reveal a lack of representation within courses as well as lack of peer support are key factors that influence the involvement and retention of students in CS, especially women. This data was used to identify key factors that influence retention and what can be done to remedy the growing deficit of professionals in this field.