Stock market data mining leads the way for mining industry

6 June 2013

This research will look at geological data as far back as 1.5 billion years ago, before today's continents were formed.
This research will look at geological data as far back as 1.5 billion years ago, before today's continents were formed.

Analytical methods used to predict stock market movements will be applied to Australian geological data, collected over many decades, to model the evolution of the Australian continent and pinpoint new mineral deposits.

The strategy is part of the $12 million Big Data Knowledge Discovery project, in which computer scientists, financial analysts and natural scientists are combining their expertise in a groundbreaking effort to discover information hidden in massive, multi-layered data sets.

"In the past year, investment in high-risk mining exploration in Australia has plummeted. Any information that can improve the accuracy of such 'greenfield' exploration would obviously be highly valued," said Professor Dietmar Muller from the University of Sydney.

"Part of the exciting potential of this project is that by applying algorithms used to predict stock market movements to the detailed data sets we have on Australia's geology, we hope to be able to uncover regions which have the highest likelihood of having exploitable mineral deposits buried hundreds of metres under weathered surface rocks."

Professor Muller, a specialist in earth dynamics and tectonics from the University's School of Geosciences, is part of the multidisciplinary team working on the project.

Together with natural scientists from Macquarie University specialising in terrestrial ecology and complex lasers, Professor Muller will join experts in machine learning and analytics from NICTA and in software and big data from SIRCA.

NICTA is Australia's Information and Communications Technology Research Centre of Excellence and SIRCA's technology is used by over 400 leading institutions in the financial services industry worldwide. SIRCA technology, in partnership with Thomson Reuters, powers the largest and most comprehensive research database of historic financial markets data in the world.

"Working together we plan on developing a new space-time data mining approach, exploiting similarities with other research fields such as finance and taking a new look at huge geo-data sets to unravel the structure and evolution of Australia in a global context," Professor Muller said.

"At the University of Sydney we have previously had success in applying big data mining for earthquake hazard mapping and opal exploration."

The Big Data Knowledge Discovery project will use national geological data, made available by Geoscience Australia, to reach back up to 1.5 billion years into 'deep time'.

"At that time Australia was made up of at least five smaller continents separated by ancient ocean basins and volcanic arcs which are now destroyed or deeply buried in the crust. Some of the world's richest metal deposits were formed during this period, but the reasons are not fully understood," said Professor Muller.

"This project will explore a new and powerful paradigm for data intensive science, ranging from medical and health sciences to physics," said Professor Hugh Durrant-Whyte, CEO, NICTA.

"Motivated by the grand challenges of big data, this initiative brings together world leading experts in finance and geoscience - possibly for the first time. SIRCA is very excited by this opportunity for two such diverse disciplines to work collaboratively towards a common goal," said Dr Michael Briers, CEO, SIRCA.

This project is supported by $4 million from the Science and Industry Endowment Fund.

Follow University of Sydney Media on Twitter

Media enquiries: Verity Leatherdale, 02 9351 4312, 0403 067 342,