Ever dream of living somewhere that has free public transportation? Or the highest concentration of self-made millionaires? Maybe an area where every resident has the equivalent of five tennis courts of green space, and there are 84,274.6 km of walkways? You can have it all in West Perth! At least from an analytics perspective, this small district in the Western Australian boomtown of Perth is the best place in the world to live.

No surveys or existing list of criteria determined this result, but rather objective data alone. SAS examined no less than 148,233 locations in 193 countries for the Paradise Found project, without predetermined aspects to investigate or even a hypothesis. Instead, we let the data speak for themselves. Over 5 million pieces of data from 1,124 data sources spoke up, including both structured and unstructured data (for instance, in the form of texts from statistics agencies). Overall, 1,060 international data services, three online geodata services, four social media services, and 57 urban studies contributed to the project. Data wrangling and powerful data management software from SAS helped cleanse, structure and prepare the data. More information on how we dealt with the challenge of the diversity and volume of the data will soon be appearing in a blog entry by my colleague Andreas Gödde .

Next step: Using machine learning provided by the powerful, flexible and open SAS®  analytics platform, the missing values for the individual locations were determined. A forecasting model was then developed that predicts locations that would be assessed as good places to live. These eight groups of characteristics surfaced that make a residential area attractive: Education and Career, Family, Culture, Nature, Safety and Infrastructure, Cost of Living, Restaurants and Shopping, and Health. SAS Visual Data Mining and Machine Learning and SAS Visual Analytics were used for the analysis and to prepare visual representations of the data.

SAS Visual Data Mining and Machine Learning and SAS Visual Analytics were used for the analysis and to prepare visual representations of the data.

So now you know where the objectively 😉 best place in the world is, according to our analytical assessment. But maybe you don't place the same value on career opportunities, family friendliness, hours of sunshine, income or cultural offerings. That's why we created the Paradise Configurator. It allows anyone to easily and quickly determine where their own personal paradise is located by weighting the characteristics according to personal preferences or custom search criteria.

The interesting thing about Paradise Found? Normally, we concentrate on our customers’ questions when we begin an analytical journey. This time, we came up with the assignment ourselves – find the best place in the world. We were trying to demonstrate that machine learning is not a black art, but also doesn't happen by simply waving a magic wand to start up the self-learning machine. What it actually involves is a bunch of algorithms that learn from data instead of using a model assumption. And it's only effective when visualisation, data management and analytics work together seamlessly.

Is SAS entering the tourism industry or becoming a B2C company? Not at all. All we were trying to do is show what big data analytics and machine learning can do using an example that would be meaningful to as many people as possible. Our mission remains working together with you to find solutions for your unique business challenges – whether that involves finding the best place or best customer, uncovering potential fraudulent financial transactions, or identifying opportunities to optimise production processes. Because practically any company can benefit from big data analytics and machine learning, regardless of the industry. And if you should happen to be sitting in the "best place in the world" right now, I'm glad to pass along contact information for my Australian colleagues. 😉