Scientists at United Arab Emirates University (UAEU) have designed and patented an invention that uses science to predict the future.
The invention aims to predict when a machine might break down, when a traffic jam might occur, or which new customer might prove to be the most profitable.
Developed by Dr Jose Berenqueres, assistant professor at UAEU’s IT College, the tool currently - called System for Forecasting Future Events – uses data-mining algorithms to make forecasts based on historical information.
While its patent is targeted at the aviation industry and the growing focus of airlines on predicting customer behaviour, he said in a statement that the potential for it to be used for other purposes - including healthcare - is already clear.
"Reducing waste, increasing asset utilisation rates, and increasing delivered value to customers are key activities of any organisation with global aspirations,” he said. “Now that collection of data from customers is economical and widespread, companies that keep doing nothing with that data will, basically, slowly die, because the companies that do something with it will be one percent or two percent more efficient.
With his team, Berenqueres built a tool related to airlines’ customer management and air-miles programs, containing two methods of processing data that allow a computer to make accurate predictions.
The first – dummy-variable generation – converts ‘categorical’ data, such as gender, into numbers that a computer can quickly understand. The second employs a technique known as ‘blending’, reflecting the belief that the ‘average’ opinion will be closer to the truth if a larger number of opinions are analysed.
SCROLL TO CONTINUE WITH CONTENT
The team has also used ‘time-shifting’, where an airline passenger’s data stream – akin to an air-travel fingerprint, detailing the flights they have taken, their purchase history, website interactions and other information – is reset to the first time they used the airline, allowing behavioural trends and developments to be identified.
“The combination of these three techniques yielded such good results that, when we showed them to airline executives, they were stunned and even we were surprised,” said Berenqueres.
"In this project, we spend about three months analysing the business logic, and one month developing the mathematical model. But what usually takes more time is finding companies that have interesting problems to solve and the courage to share their data with research centres,” he added.
There are ongoing discussions between the university and some well-known airlines to commercialise this technology and Berenqueres said the interest it has attracted illustrates increasing attention surrounding data science.
“The number of patents related to data science has exploded in the last five years. Since this project began, we have started helping other companies which have the same problem: a lot of data, but not the knowledge of how to analyse it,” he added.