When the horses lined up for the 2013 Kentucky Derby, one of America’s most prestigious horse races, a small group of researchers watched on with quiet confidence of the outcome.
A horse named Nyquist crossed the line first, followed by Exaggerator, then Gun Runner, and then Mohaymen. It was the exact sequence the researchers had predicted.
Bookies had the odds of such an outcome at 540-1. Louis Rosenberg and his team at Unanimous AI, a US tech firm, thought the odds "could have been in the order of 5-1", he told me at the time.
After conducting a tipping exercise with people who identified as avid horseracing fans, the company used what it called "swarm intelligence of human groups" to make its prediction on the outcome.
Unanimous AI passed its prediction to tech journalist Hope Reese who published it the day before the race, and later boasted on Twitter after she placed a single dollar on the superfecta to win $540.
It was just one example of how new approaches to data mining and data analytics are impacting sports gambling.
When the main race of the Melbourne Cup kicks off today, no doubt some of the same forces will be in play.
Data mining and real-time analytics can be used to predict the outcome of horse races "in a manner very similar to the stock market," said associate professor Richi Nayak, from the Faculty of Science and Technology at QUT.
She told Yahoo Finance The abilities of predictive technologies had "changed drastically" in recent years.
"There have been advancements in machine learning and deep-learning techniques ... but there have been even more advancements in data collection technology."
That combination has changed the predictive abilities of odds makers, as well as the more sophisticated punters.
"Most analysts would use historical information to predict future events but now with the advancements in technology, you’re talking about real-time analytics and real-time predictions," Nayak said.
"We are recording now every movement the horse is making."
Writing in The Conversation this morning, she explained how the marriage of historical data and real-time variables could be leveraged to rank horses on any given day.
"Every year, when the Melbourne Cup happens, it could be a scenario where all the possible values, all the variables, that affect the race and its outcome are being recorded," she wrote.
"We would collect all possible details about the horse, what the ranking was for that horse, so now the data-mining software would try to find out the relationship between the attributes of the variables that we have collected about the race, the horses, and the environmental detail, the ground detail, today’s weather.
"So all those details are recorded and combined with the historical data.
"So now we know what the ranking is for a particular horse."
So, when you're having a punt today, just remember who you might be up against.