excelsiordata
Kelly
Recently Published
CT Opioid Overdoses: An Exploratory Analysis
This project explores data containing the details regarding individuals who overdosed on opioids between the years of 2012 and 2017 (inclusive) in the state of Connecticut. Primarily exploratory data analysis.
Kaggle Housing Prices Competition
Advanced regression using a random forest model with XG boost to predict that sale price of homes.
Recommendation Algorithms Enhanced with Serendipity
5 types of recommendation algorithms built and tested for performance, then enhanced with serendipity to improve user experience. Types of recommeder systems built: random, popular, item based collaborative filtering, user based collaborative filtering, and singular value decomposition.
Recommendation Algorithms: User-Based Collaborative Filtering versus Item-Based Collaborative Filtering
Comparing the user based and item based collaborative filtering approaches to recommendation algorithms. Predicting user ratings for a given movie.
Recommendation Algorithms: User-Based Collaborative Filtering versus Item-Based Collaborative Filtering
Comparing the user based and item based collaborative filtering approaches to recommendation algorithms. Predicting user ratings for a given joke.
World Happiness Report Analysis: EDA and Linear Regression
Analyzed the details of the world happiness report. Generated hypotheses and tested them against the data.
Grading the Professor: A Multiple Linear Regression Model
Using backward-selection and p-value as the selection criterion to determine the best model to predict professor evaluation score.
Spam/Not Spam Email Classification Algorithms
Support-vector machine, random forest, and maximum entropy models built and tested.
Node.js Web Scraping, SQL Database Building and Subsequent Analysis
Scraped data from monster, kaggle, and kdnuggets to outline the soft and hard skills required of data scientists in the job market.
XML JSON and HTML Data Frame Building
Data frames of book text using XML JSON and HTML.
