agsandrew - Fotolia

Researchers use AI, big data and machine learning to find best place in the world to live

West Perth in Australia and Hebden Bridge in the UK are among the top locations ranked by machine learning tool in SAS project

Researchers at analytics firm SAS claim to have created an artificial intelligence (AI) program that can rank the best places to live in the world using a range of publicly available data sources.

Drawing on more than five million data points sourced from social media sites, trip review websites, geodata and international agencies, SAS’s Paradise Found project ranked 150,000 places across 193 countries – and Hebden Bridge, West Yorkshire, emerged top in the UK.

The AI’s algorithm used the characteristics of each location in eight categories: healthcare, environment, culture, education and employment, living expense, safety and infrastructure, restaurants and shopping, and attractiveness for families.

The program also factored in quality-of-life indicators within these categories, such as the price of common food items, to gauge how expensive it is to live in a location, and the number of trees as an environmental measure. Other indicators included time spent in traffic per year by citizens and width of footpaths.

John Spooner, head of data science at SAS UK & Ireland, said the use of machine learning made the results as fair as possible. “When putting together a conventional survey, it’s all too easy for unconscious bias to creep in when selecting the criteria to use when determining which data should be collected and analysed,” he said.

“For Paradise Found, however, we processed all the available data and allowed machine learning algorithms to decide which criteria are truly important. This way, no aspect can be ignored simply because no one was looking for it.”

The tool named West Perth in Australia as the best location globally, with Feijenoord in the Netherlands and New York in the US making up the rest of the top three.

Read more on machine learning

Along with Hebden Bridge, Hale in Greater Manchester and Richmond and Harrow in Greater London also ranked highly in the UK.

Spooner said the program could help prospective house buyers uncover some overlooked places that might be nice to live in.

To this end, the technology could also be used by estate agents or by travel websites to help holidaymakers find nice areas that might be a little more off the beaten track.

“This [project] allowed us to demonstrate what analytics and machine learning are capable of – namely, finding patterns of data from a completely impartial perspective,” said Spooner.

“In this particular case, it showed how analytics can come up with a list of places that are different to what people might first think of, based on their own opinions and preferences.”

Read more on Artificial intelligence, automation and robotics

Data Center
Data Management