Anthony’s Data Analysis Portfolio
By Anthony Marcolongo
Project 1: Can we predict bitcoin price based off daily volume traded?
Description: This was my graduate capstone project.
The purpose of this project was to use both linear regression and logistic regression to determine if there is a link between daily price and volume traded.
fig 1: Graph of Volume Traded versus Closing Price
fig 2: Graph of log(Volume Traded) versus Closing Price
Project 2: A Tableau Dashboard Analyzing the Effect of Volcanos on Humans
Description: This was a project that I put together for practice creating Tableau Dashboards.
The purpose of this project was to gain experience with Tableau.
fig 3: Tableau Dashboard
Project 3: Natural Language Processing with TensorFlow 2.0
Description: Natural Language Processing was used to predict if an Amazon user review would be classified as either positive, or negative.
The purpose of this project was to gain familiarity with NLP in Tensorflow 2.0.
fig 4: Mean Absolute Error by # of Epochs
Project 4: Analyzing Medical Readmittance with Principal Component Analysis
Description: Principal Component Analysis was used to determine the likelyhood of a patient being readmitted to the hospital.
The purpose of this project was to show that it is possible to create a model that calculates if a patient will be readmitted or not.
fig 5: Proportion of Variance Explained
fig 6: Scree Plot