Latest news with #QueenslandUniversityofTechnology
Scoop
2 days ago
- Business
- Scoop
Can Reading The News Make You Richer?
Press Release – University of Auckland While ChatGPT shows some ability to extract information about volatility from news headlines, the study finds its forecasting power is inferior to the researchers' approach at longer horizons. Researchers have uncovered a novel way to forecast stock market volatility using daily business news. Business news can do more than report on financial markets; it can predict where they're headed. That's the finding from a new study by University of Auckland finance lecturer Dr Justin J. Case and Queensland University of Technology's Professor Adam Clements, who show that utilising business news articles, specifically those published in The Wall Street Journal, can more accurately forecast stock market volatility than other commonly used methods. 'Volatility is a common proxy for financial risk,' says Dr Case. 'By accurately forecasting this risk, investors can take strategic steps to protect their investments before market shifts occur.' Using more than 1.1 million Wall Street Journal articles published between January 2000 and December 2022, the researchers analysed the language used in business reporting and linked it to fluctuations in the S&P 500 – the world's most-watched equities index. Their study shows that news text offers a forward-looking, real-time lens on market conditions, delivering more accurate signals about risk than the retrospective data typically used in economic forecasting. The researchers applied a machine learning algorithm to news articles, sorting the text into topics and analysing these alongside high-frequency data on the S&P 500 index. 'We're looking at the world's biggest equities market, and the biggest business newspaper in the US, and asking whether the news explains stock market volatility,' says Case. 'We find that news coverage is strongly related to stock market volatility movements. And by analysing business news articles, we can identify both the topics and specific events influencing stock market volatility.' Additionally, the researchers found incorporating their news-based measures into benchmark volatility forecasting models reduced forecast errors by over 40 percent at the monthly horizon. They also found significant reductions in forecast errors at weekly horizons. To show how this could be applied in practice, the researchers used their news-enhanced forecasts in a simulated investment strategy. The strategy saw more invested when the market was expected to be stable and less when it was expected to be volatile. This approach, utilising the news, improved investment performance, with risk-adjusted returns higher than both a traditional buy-and-hold strategy and a strategy using standard volatility forecasts. 'If you're able to forecast volatility more accurately with our news measures, you can decrease your risk exposure, and therefore, increase your portfolio performance.' Among the news topics the researchers analysed, stock market activity, financial institutions, economic shocks, and government policy were most related to stock market volatility. 'Interestingly, we also identify several news topics associated with a less volatile stock market. In particular, news attention to corporate mergers and acquisitions is associated with reduced volatility. This suggests that increased mergers and acquisitions news coincides with greater confidence in economic conditions.' The study also finds that sports news is related to a less volatile market. 'This could be interpreted as a distraction effect, where increased attention to non-economic news coincides with lower stock market volatility,' says Case. Finally, the researchers explore whether the large language model, ChatGPT, can forecast the impact of news on market volatility. While ChatGPT shows some ability to extract information about volatility from news headlines, the study finds its forecasting power is inferior to the researchers' approach at longer horizons. 'Our method allows for a more granular analysis of news text, capturing term frequencies that provide more nuanced volatility-relevant information.'
Scoop
2 days ago
- Business
- Scoop
Can Reading The News Make You Richer?
Press Release – University of Auckland Researchers have uncovered a novel way to forecast stock market volatility using daily business news. Business news can do more than report on financial markets; it can predict where they're headed. That's the finding from a new study by University of Auckland finance lecturer Dr Justin J. Case and Queensland University of Technology's Professor Adam Clements, who show that utilising business news articles, specifically those published in The Wall Street Journal, can more accurately forecast stock market volatility than other commonly used methods. 'Volatility is a common proxy for financial risk,' says Dr Case. 'By accurately forecasting this risk, investors can take strategic steps to protect their investments before market shifts occur.' Using more than 1.1 million Wall Street Journal articles published between January 2000 and December 2022, the researchers analysed the language used in business reporting and linked it to fluctuations in the S&P 500 – the world's most-watched equities index. Their study shows that news text offers a forward-looking, real-time lens on market conditions, delivering more accurate signals about risk than the retrospective data typically used in economic forecasting. The researchers applied a machine learning algorithm to news articles, sorting the text into topics and analysing these alongside high-frequency data on the S&P 500 index. 'We're looking at the world's biggest equities market, and the biggest business newspaper in the US, and asking whether the news explains stock market volatility,' says Case. 'We find that news coverage is strongly related to stock market volatility movements. And by analysing business news articles, we can identify both the topics and specific events influencing stock market volatility.' Additionally, the researchers found incorporating their news-based measures into benchmark volatility forecasting models reduced forecast errors by over 40 percent at the monthly horizon. They also found significant reductions in forecast errors at weekly horizons. To show how this could be applied in practice, the researchers used their news-enhanced forecasts in a simulated investment strategy. The strategy saw more invested when the market was expected to be stable and less when it was expected to be volatile. This approach, utilising the news, improved investment performance, with risk-adjusted returns higher than both a traditional buy-and-hold strategy and a strategy using standard volatility forecasts. 'If you're able to forecast volatility more accurately with our news measures, you can decrease your risk exposure, and therefore, increase your portfolio performance.' Among the news topics the researchers analysed, stock market activity, financial institutions, economic shocks, and government policy were most related to stock market volatility. 'Interestingly, we also identify several news topics associated with a less volatile stock market. In particular, news attention to corporate mergers and acquisitions is associated with reduced volatility. This suggests that increased mergers and acquisitions news coincides with greater confidence in economic conditions.' The study also finds that sports news is related to a less volatile market. 'This could be interpreted as a distraction effect, where increased attention to non-economic news coincides with lower stock market volatility,' says Case. Finally, the researchers explore whether the large language model, ChatGPT, can forecast the impact of news on market volatility. While ChatGPT shows some ability to extract information about volatility from news headlines, the study finds its forecasting power is inferior to the researchers' approach at longer horizons. 'Our method allows for a more granular analysis of news text, capturing term frequencies that provide more nuanced volatility-relevant information.'
Scoop
2 days ago
- Business
- Scoop
Can Reading The News Make You Richer?
Researchers have uncovered a novel way to forecast stock market volatility using daily business news. Business news can do more than report on financial markets; it can predict where they're headed. That's the finding from a new study by University of Auckland finance lecturer Dr Justin J. Case and Queensland University of Technology's Professor Adam Clements, who show that utilising business news articles, specifically those published in The Wall Street Journal, can more accurately forecast stock market volatility than other commonly used methods. "Volatility is a common proxy for financial risk," says Dr Case. "By accurately forecasting this risk, investors can take strategic steps to protect their investments before market shifts occur." Using more than 1.1 million Wall Street Journal articles published between January 2000 and December 2022, the researchers analysed the language used in business reporting and linked it to fluctuations in the S&P 500 - the world's most-watched equities index. Their study shows that news text offers a forward-looking, real-time lens on market conditions, delivering more accurate signals about risk than the retrospective data typically used in economic forecasting. The researchers applied a machine learning algorithm to news articles, sorting the text into topics and analysing these alongside high-frequency data on the S&P 500 index. "We're looking at the world's biggest equities market, and the biggest business newspaper in the US, and asking whether the news explains stock market volatility," says Case. "We find that news coverage is strongly related to stock market volatility movements. And by analysing business news articles, we can identify both the topics and specific events influencing stock market volatility." Additionally, the researchers found incorporating their news-based measures into benchmark volatility forecasting models reduced forecast errors by over 40 percent at the monthly horizon. They also found significant reductions in forecast errors at weekly horizons. To show how this could be applied in practice, the researchers used their news-enhanced forecasts in a simulated investment strategy. The strategy saw more invested when the market was expected to be stable and less when it was expected to be volatile. This approach, utilising the news, improved investment performance, with risk-adjusted returns higher than both a traditional buy-and-hold strategy and a strategy using standard volatility forecasts. "If you're able to forecast volatility more accurately with our news measures, you can decrease your risk exposure, and therefore, increase your portfolio performance." Among the news topics the researchers analysed, stock market activity, financial institutions, economic shocks, and government policy were most related to stock market volatility. "Interestingly, we also identify several news topics associated with a less volatile stock market. In particular, news attention to corporate mergers and acquisitions is associated with reduced volatility. This suggests that increased mergers and acquisitions news coincides with greater confidence in economic conditions." The study also finds that sports news is related to a less volatile market. "This could be interpreted as a distraction effect, where increased attention to non-economic news coincides with lower stock market volatility," says Case. Finally, the researchers explore whether the large language model, ChatGPT, can forecast the impact of news on market volatility. "Our method allows for a more granular analysis of news text, capturing term frequencies that provide more nuanced volatility-relevant information."
The Independent
2 days ago
- Science
- The Independent
Researchers discover two new species after genetic testing
Australia is home to more than 60 species of carnivorous marsupials in the family Dasyuridae. Almost a quarter of those have only been scientifically recognised in the past 25 years. Other than the iconic Tasmanian devil, chances are most of these small, fascinating species have slipped under your radar. One of the rarest and most elusive is the kultarr (Antechinomys laniger), a feisty insect-eater found in very low numbers across much of the outback. To the untrained eye, the kultarr looks very much like a hopping mouse, with long legs, a long tail and a tendency to rest on its hind legs. However, it runs much like a greyhound – but its tiny size and high speed make it look like it's hopping. Kultarr or kultarrs? Until now, the kultarr was thought to be a single widespread species, ranging from central New South Wales to the Carnarvon Basin on Australia's west coast. However, a genetic study in 2023 suggested there could be more than one species. With backing from the Australian Biological Resources Study, our team of researchers from the University of Western Australia, Western Australian Museum, and Queensland University of Technology set out to investigate. We travelled to museums in Adelaide, Brisbane, Darwin, Melbourne, Sydney and Perth to look at every kultarr that had been collected by scientists over the past century. By combining detailed genetic data with body and skull measurements, we discovered the kultarr isn't one widespread species, but three distinct species. Three species of kultarrs The eastern kultarr (A. laniger) is the smallest of the three, with an average body length of about 7.5cm. It's darker in colour than its relatives, and while its ears are still big, they are nowhere near as big as those of the other two species. The eastern kultarr is now found on hard clay soils around Cobar in central NSW and north to around Charleville in southern Queensland. The gibber kultarr (A. spenceri) is the largest and stockiest, with an average body length of around 9cm. They are noticeably chunkier than the other two, more dainty species, with big heads, thick legs and much longer hindfeet. As its name suggests, the gibber kultarr is restricted to the extensive stony deserts or 'gibber plains' in southwest Queensland and northeast South Australia. The long-eared kultarr (A. auritus) is the middle child in terms of body size, but its ears set it apart. They're nearly as long as its head. It's found in patchy populations in the central and western sandy deserts, living on isolated stony plains. Are they threatened? All three species of kultarr are hard to find, making it difficult to confidently estimate population sizes and evaluate extinction risk. The long-eared and gibber kultarrs don't appear to be in immediate danger, but land clearing and invasive predators such as cats and foxes have likely affected their numbers. The eastern kultarr, however, is more of a concern. By looking at museum specimens going back all the way to the 1890s, we found it was once much more widespread. Historic records suggest the eastern kultarr used to occur across the entirety of arid NSW and even spread north through central Queensland and into the Northern Territory. We now think this species may be extinct in the NT and parts of northwest Queensland. What's next? To protect kultarrs into the future, we need targeted surveys to confirm where each species still survives, especially the eastern kultarr, whose current range may be just a shadow of its former extent. With better knowledge, we can prioritise conservation actions where they're most needed, and ensure these remarkable, long-legged hunters don't disappear before we truly get to know them. Australia still has many small mammal species that haven't been formally described. Unless we identify and name them, they remain invisible in conservation policy. Taxonomic research like this is essential – we can't protect what we don't yet know exists. And without action, some species may disappear before they're ever officially recognised. Cameron Dodd is a PhD Student in Evolutionary Biology and Taxonomy at the University of Western Australia. Andrew M. Baker is an Associate Professor in Ecology and Environmental Science at the Queensland University of Technology. Kenny Travouillon is a Curator of Mammals at the Western Australian Museum. Linette Umbrello is a Research Associate at the Western Australian Museum. Renee Catullo is a Senior Lecturer in the School of Biological Sciences at The University of Western Australia.
Perth Now
18-06-2025
- Science
- Perth Now
Robots set to conquer the final frontiers
Small robots may be able to roam the moon's surface, comb the sea floor, or undertake search-and-rescue missions for longer after a breakthrough by Australian researchers. Three scientists at the Queensland University of Technology released their findings on Thursday, outlining a method to create a camera that processes images in ways similar to the human brain. While there are further developments to unlock, they say neuromorphic computing could deliver a robotic revolution. The latest discovery, published in the Science Robotics journal, uses a camera and computer processor the QUT team called LENS, which stands for "locational encoding with neuromorphic systems". The system is inspired by the way the human brain works, author and QUT neuroscientist Adam Hines said, to save more than 90 per cent of power compared to a traditional robotic navigation system. "The brain is so energy-efficient, it only uses about 20 watts of power to do everything from keeping us alert and awake and talking to constantly navigating and predicting where we're going next," Dr Hines told AAP. "Traditional AI systems like ChatGPT use significantly more power than that so taking inspiration from the brain is a really great way to save on energy." The LENS camera sensor and processor work by registering changes, such as light and movement, rather than recording images the entire time it operates. The QUT research team, which included Michael Milford and Dr Tobias Fisher, tested the system on an eight kilometre journey and could make it work using 180 kilobytes or up to 300 times less storage than a traditional system. Saving so much energy and storage could let robots operate and navigate by themselves in new areas or for significantly longer durations, Dr Hines said. "The real use cases in mobile robotics... are search and rescue, underwater monitoring of places like the Great Barrier Reef, or even really extremely remote areas like space explorations," he said. Neuromorphic computing has been a target for previous research but QUT Centre for Robotics director Professor Milford said it was vital to translate theory into practical applications. "Impactful robotics and tech means both pioneering groundbreaking research but also doing all the translational work to ensure it meets end user expectations and requirements," he said.
