Projects

* Global Recovery Analysis: Link to heading

https://dre-at8865.github.io/global_recovery_analysis/ Analysis of the drivers of economic crisis recovery across countries since 1980. The dashboard explores the central question: What separates countries that recover from crisis in 2 years from those that stagnate for decades? Data: Global Macro Database

* Subscription Analytics dbt Project: Link to heading

https://github.com/dre-at8865/subscription-analytics-dbt An example of a dbt project modeling and analysing membership, subscription, invoice, refund, and season data for a subscription-based business.

* Strategy to Fix Slow Queries: Link to heading

/posts/strategy-fix-slow-queries/ A comprehensive case study analysing database performance issues using Snowflake query history data. Investigation of slow query root causes and strategic solutions to improve end-user experience while optimizing costs. Includes systematic analysis of query performance metrics, warehouse utilization, and data access patterns.

* Data Science Capstone Text Predictor: Link to heading

http://rpubs.com/TheLoneBrit101/503450 Capstone of Data Science Specialization by John Hopkins University via Coursera sponsored by Swiftkey

* Analysis of EV impact on conventional fuels: Link to heading

http://rpubs.com/TheLoneBrit101/540345 A small 2-page analysis/thought-piece answering the question: to what extent will electric vehicles impact the demand for conventional fuels?

* Dashboard of Retailer Analysis: Link to heading

https://thelonebrit101.shinyapps.io/Retailer_Analysis/ An analysis of transactional data of 6 fictitious retailers

* Analysis of Most Harmful US Storm Events: Link to heading

http://rpubs.com/TheLoneBrit101/471344 This project involves exploring the U.S. National Oceanic and Atmospheric Administration’s (NOAA) storm database. This database tracks characteristics of major storms and weather events in the United States, including when and where they occur, as well as estimates of any fatalities, injuries, and property damage.

* Analysis of churn rate of bank customers (Tableau): Link to heading

https://public.tableau.com/profile/andr.5417#!/vizhome/DataScienceAZ_15641726497600/CreditScore

* Predictive model of type of people to survive the Titanic: Link to heading

https://github.com/at8865/Titanic-Kaggle-

* Practical Machine Learning Project: Link to heading

https://at8865.github.io/Practical-Machine-Learning-Prediction-Assignment-Writeup/ The goal of this project was to predict the manner in which participants lifted barbells, from data that was taken from accelerometers on the belt, forearm, arm, and dumbell of 6 participants. Two models were analysed: Decision Tree and Random Forest. It was shown that the Random Forest model had the highest accuracy of the two models, and by extension, the lowest out of sample error.