These are data analysis projects that I've worked on using Python, SQL and excel, utilizing visualization and various statistical analysis techniques to pull insights from data sets. Projects are ordered by most recently added.
To view my Kaggle profile, you can use this link: https://www.kaggle.com/thealongsider
To view my work with Tableau, you can use this url: public.tableau.com/profile/brandon.massaro/
Featured
Advertising Predictions using Logistic Regression (python) -- Used Logistic Regression to predict whether users would click on an ad based on user data and to understand what are the leading factors to why users click on ads. I completed this project as part of an online data science course.
Recently Added
K-Means Clustering for Determining Public vs. Private Universities (python) -- Performed K-Means clustering to see how K-Means clustering would categorize public and private universities. I completed this project as part of an online data science course.
Bank Authentication Classifier with Tensorflow (python) -- Used tensorflow to create a classifier that used image data from the Bank Authentication Data provided by the UCI repository to determine if a bank note was real or not. I completed this project as part of an online data science course.
sql-ex.com SQL Exercise Solutions.md (SQL) -- Added the SQL query exercises I have been completing on sql-ex.com as a way to include more SQL code into this repository.
Predicting Species of Iris Data Set using Support Vector Machines (python) -- Used Support Vector Machines to classify famous Iris dataset. I completed this project as part of an online data science course.
Projects [A-Z]
911 Calls -Capstone Project (python) -- An exploratory analysis of the dataset including descriptions of findings using the Montegomery County 911 Calls dataset available on Kaggle. I completed this capstone project as part of an online data science course.
AB Testing Retention Rate for Mobile Games Company (python) -- Used the dataset from an A/B test for a mobile game to determine whether changing a game element to a different level improved user retention. I completed this project provided by DataCamp.
Advertising Predictions using Logistic Regression (python) -- Used Logistic Regression to predict whether users would click on an ad based on user data and to understand what are the leading factors to why users click on ads. I completed this project as part of an online data science course.
Bank Authentication Classifier with Tensorflow (python) -- Used tensorflow to create a classifier that used image data from the Bank Authentication Data provided by the UCI repository to determine if a bank note was real or not. I completed this project as part of an online data science course.
Bank Debts Recovery Analysis (python) -- Used Linear Regression, Chi Squared tests, and Kruskal-Wallis statistical test to confirm the validity of different levels of debt recovery strategy spending based on user expected return value. I completed this project provided by DataCamp.
Choropleth Mapping (python) -- Created geographical maps using plotly
Decision Trees & Random Forest to Predict Borrower Payback (python) -- Created decision tree and random forest models to predict loan payback using Lending Club data. I completed this project as part of an online data science course.
Ecommerce Analysis using Linear Regression (python) -- Used Linear Regression to give insight into ecommerce company's decision on whether to focus on their mobile app or website. I completed this project as part of an online data science course. The data and company are fictional.
Financial Crisis Bank Data - Capstone Project (python) -- An exploratory analysis of stock market data for 6 major banks throughout the 10 year period surrounding the financial crisis. I completed this capstone project as part of an online data science course.
Funnel Analysis for Springboard Case Study (SQL, excel) -- Created a Funnel Analysis to identify growth opportunities for online retailer. I completed this project as a part of Springboard's Business Analytics course with the results approved by a mentor.
K-Means Clustering for Determining Public vs. Private Universities (python) -- Performed K-Means clustering to see how K-Means clustering would categorize public and private universities. I completed this project as part of an online data science course.
K Nearest Neighbors For Anonymized Data Set (python) -- Created a K Nearest Neighbors classifier to predict target variable of an anonymized data set. I completed this project as part of an online data science course.
Predicting Credit Card Approvals Using Logistic Regression (python)-- Used Logistic Regression to create a model that predicts credit card removal. Utilized Grid Search to tune the model for better performance. I completed this project provided by DataCamp.
Predicting Species of Iris Data Set using Support Vector Machines (python) -- Used Support Vector Machines to classify famous Iris dataset. I completed this project as part of an online data science course.
Root Cause Analysis for Springboard Case Study (excel) -- Performed a root cause analysis (RCA) on manufacturing and sales data to identify the source of sudden rate of returns increase. I completed this project as a part of Springboard's Business Analytics course with the results approved by a mentor.
sql-ex.com SQL Exercise Solutions.md (SQL) -- Added the SQL query exercises I have been completing on sql-ex.com as a way to include more SQL code into this repository.