Sammy Shaw

Data Science Portfolio

Hi, I’m Sammy – Data Scientist and Researcher. My portfolio is a collection of recent data science projects - emphasis on data processing and analysis, machine learning, business problem solving, and programming. My statistics and research expertise comes from my PhD in Sociology, which also equips me with a unique perspective on social trends and patterns, crucial for interpreting social dynamics with data that are invaluable for predicting consumer behavior, identifying market trends, and addressing issues of equity and inclusion. Check out my Linked In profile, Github, and download my resume below!

35 minute read

Fantasy BBall Rankings using SHAW-Percentage Transformations

In this project I extract, transform, and load NBA player data for my own fantasy basketball ranking app. I construct a series of...

48 minute read

Deep Learning CNN Data Science Computer Vision Transfer Learning Python

Toy Robot: Toy Classification Using CNN

For this project I trained a Convolutional Neural Network to recognize distinct classes of toys from a bespoke, self-collected data ...

16 minute read

GSS Data Cleaning Visualization Tableau

GSS Dashboard

Summary & Context This project demonstrates 1. Visualization using Tableau, and 2. Preprocessing and analyzing a large public da...

13 minute read

Customer Segmentation Machine Learning Clustering Python

The "You Are What You Eat" Customer Segmentation

This project uses k-means clustering to segment up a grocery chain’s customer base in order to increase understanding of shopping be...

35 minute read

Customer Targeting Machine Learning Classification Python

Enhancing Targeting Accuracy Using ML

In this project, I use machine learning models for a classification task to solve another business problem for ABC Grocery: Logistic...

32 minute read

Customer Loyalty Machine Learning Random Forest Decision Tree OLS Multiple Regression Python

Predicting Customer Loyalty Using ML

This project applies machine learning regression models to predict customer loyalty scores for a subset of customers for a hypotheti...

Older projects