This data science project focuses on building an AI/ML model to predict the 52-week price performance of a stock based on financial data extrapolated from the S&P 500 list of companies. The data are explored, visualized and processed. Then a support vector regression (SVR) is implemented and refined. Finally, the results are covered alongside the conclusion.
It is challenging to predict a stock’s 52-week price performance with accuracy. The financial experts use certain criteria to predict performance, but that skill is tacit and difficult to learn. This project will aim to teach a machine how to make a prediction with 70%+ accuracy. The data set is gathered from Fidelity.com. …
Problem solving is a key skill needed for software developers/programmers. In this blog, we used the CRISP-DM process to build a predictive model for software developers’ salaries based on their attitudes towards problem solving.
CRISP-DM is a cross industry process for data science. It has the following six steps: (1) Business understanding, (2) Data understanding, (3) Data preparation, (4) Data modeling, (5) Result evaluation, and (6) Deployment of model. We followed this process in order to build a model that can predict a software developer’s salary based on their love for problem solving. Figure 1 is a depiction of CRISP-DM.