The analysis project’s target audience is any employee who may be considering a move from the hustle and bustle of life in Dublin. The Covid-19 pandemic has led to a number of big employers like Indeed, Siemens, Twitter, Salesforce & Spotify now allowing their employees to work remotely on a more permanent basis. As more companies recognise the benefits of large-scale remote working (both for the employee & employer), this list will grow as companies move from forced remote working to smarter working in a post Covid-19 environment. Large numbers of employees now no longer must live in Dublin near their employer and are looking for alternative locations to call home.

The aim of my project was to identify which county in the Republic of Ireland would offer the best quality of life, based on variables that a typical family would be interested in, including crime rate, classroom size, property prices / monthly rent costs, distance to an emergency department etc.

These datasets are the most current at the time and are sourced from the CSO, EasyGo, Property Services Regulatory Authority, Failte Ireland, Residential Tenancies Board, Pharmaceutical Society of Ireland and Ordnance Survey Ireland.

The primary language used for the analysis is the R programming language, with various libraries within R required. The IDE of choice for use with R, is R Studio, and the database used to store the data is SQLite. The machine learning element of the analysis, includes the use of decision trees and random forest algorithms. This was to compare the actual number of crimes versus the forecasted number of crimes using these methods. I also compared these methods to each, and looked at the variables for correlations.

The results from the analysis and associated charts/graphs shows the top counties an employee could consider moving to, plus identifies the relationships between my variables and some interesting observations. In addition to the report, which will include details of the analysis and the identity of the top counties using the identified variables, to give the audience a better understanding of the data.

Developed an R Shiny app, allowing the audience to get a detailed summary of each of the variables and a summary of each county, and where they rank for each of the variables. The audience is also able to select the variables they are interested in, and identify the counties that are most suitable for them using these selected variables.