cbrightly1 Goto Github PK

36-650

Statistical Computing Repository

capital-bikeshare-data-mining

Data mining process for a group project about the Capital Bikeshare data. Developed in Python using Jupyter Notebook.

cbrightly1

My personal repository

fnb-customer-segmentation

This project used a Kmeans after PCA model to segment retail customers to optimize marketing efforts. When the model repeatedly returned a single cluster, the model was used to prove the customers' homogenous characteristics. Influenced the bank's marketing strategies and initiatives. Developed in Jupyter Notebook with Python for FNB.

fnb-leadgen

This project uses a logistic regression model to develop a cross-sell list with current mortgage customers. Developed in Jupyter Notebook using Python for FNB.

ggplot-project

This project was a replication of a FiveThirtyEight Visualization using R's ggplot package.

housing-prices-project

Predicting market housing prices by testing algorithms taught in an intermediate data science course. Developed in R.

latex-test

permutations-experiment

This was an experiment of a 2-sample permutation or randomization T-test with a small pre-and post-survey. The client had a small sample (n<30) and the experiment informed the research results.

stackoverflow-time-series

A time series analysis of the StackOverflow question counts for popular data science topics. Includes SARIMA and VARMA modeling for mulitvariate time series in R.

text-analysis

Collection of research projects developed in R for a text analysis course. Projects focus on core text analysis methods such as keyness, dispersion, MDA, etc.