Untitled @bloomingbiz - Tumblr Blog

What is the Best Water Heater to Purchase: Data Mining Water Heater Permits 2026

Michael Segaline Data Scientist and Media LION be Relevant. April 24, 2026 Abstract: This study analyzes 20,018 residential water heater permits issued by the City of Spokane, Washington between January 2005 and January 2025. Permit data was merged with Spokane County voter registration records and voting precinct shapefiles to produce demographic and geospatial analyses. Spokane residential…

View On WordPress

Principal Component Analysis

Aug 15 Written By Michael Segaline Bottom Line Up Front: Customer yearly bandwidth may not impact Churn. A major telecommunications company is in a very competitive industry where every variable my matter to customers leaving to a different provider. The company intends to minimize customer churn overall. Given the dataset intended to explore and mitigate customer churn: How much variance is…

View On WordPress

#ai #artificial-intelligence #data-science #data-visualization #machine-learning

Market Basket Analysis for Prescription data.

Written By Michael Segaline Bottom Line Up Front: Abilify is the most associated drug amongst patient prescriptions. A major hospital chain has a loss of revenue issue due to the fines imposed as a result of readmitting patients. The overall goal is to understand the patient base through their prescriptions data; Specifically, to identify common pairs, groups, or associations of drugs that are…

View On WordPress

Which Category is Best for YouTube: An Insider's Guide to Leveraging Data Insights (2023)

Jun 28 Written By Michael Segaline Abstract Bottom Line Up Front: While the Audience prefers ‘Gaming’, ‘Entertainment’, and ‘Music’; YouTube appears to reward only these categories: “How to”, “Science & Tech”, and “Education”. A media company wants to explore the best category to upload videos to YouTube. The study takes a YouTube trending videos dataset for the United States and explores…

View On WordPress

eXPLORING eLECTION SCANDALS OF THE wASHINGTON STATE GOVERNOR'S RACE

Abstract This presentation applies exploratory data analysis and machine learning to the 2024 Washington State gubernatorial campaign finance dataset — comprising over 6.3 million donation records spanning 2007–2026 — to investigate patterns of potential donation fraud among current and past candidates. Using probability distribution analysis, Benford’s Law, and the Kruskal-Wallis…