This result has not been obtained by a survey or an existing list of criteria, but by a mere set of objective data. 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 data objects from 1.124 data sources has their say, 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 on World of Analytics.
In a next phase - 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 will be assessed as good places to live. These eight groups of criteria 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.
So, now you know where the objectively speaking ;-) best place in the world is, according to our analytical assessment. But obviously not everybody assigns the same value to 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 most noteworthy aspect of Paradise Found? Normally, we start from our customer's requests when we embark on an analytical journey. This time, we came up with the assignment ourselves — to find the best place in the world. We were trying to demonstrate that machine learning is not a black art, but also that it doesn't happen by simply waving a magic wand that powers 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 visualization, data management, and analytics work together seamlessly.
Is SAS entering the tourism industry or becoming a B2C company? Not at all. We just wanted to showcase what big data analytics and machine learning can do using an example that would be meaningful and appealing 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 optimize production processes. 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 gladly pass along contact information of my Australian colleagues. ;-)