(Press-News.org)
Fashion trend forecasting helps companies predict which clothes will be popular in upcoming seasons. Traditionally, this has relied on experts’ intuition, experience and creativity. More recently, big-data analysis has been incorporated, offering deeper insights into consumer behavior. However, such methods pose technical barriers and remain out of reach for fashion students or small brands.
Recent developments in artificial intelligence (AI) can balance the scales. Large language models (LLMs) like ChatGPT have made big data analysis readily available to the public. LLMs draw from vast societal and cultural data and can potentially be used for predicting fashion trends. However, given their current limitations, such as hallucinations and factual errors, it is imperative to verify their suitability and to develop structured prediction methods.
In a new study, Assistant Professor Yoon Kyung Lee and Master’s student Chaehi Ryu, from the Department of Clothing and Textiles at Pusan National University, South Korea, developed a new approach for predicting fashion trends using ChatGPT. “Rather than simply asking ‘What fashion will be popular in the future?’, we designed a systematic strategy for prompting the AI for more specific and consistent answers,” explains Dr. Lee. “We also compared ChatGPT's predictions to an actual trend agency’s report.” Their findings were published in the Clothing and Textiles Research Journal on September 26, 2025.
The researchers first verified ChatGPT’s characteristics in fashion trend prediction using general prompts about 2023 fall/winter men’s fashion trends. Based on the results, they developed a new Top-Down Prompting (TDP) technique based on the Lotus Blossom (LB) brainstorming approach, for more accurate and specific forecasting.
TDP starts with a central problem prompt, a general query to predict ‘Fashion Trends’, and then expands into sub-problem prompts, including queries on “Silhouette,” “Materials,” “Key Items,” “Garment Details,” “Decorative Elements,” “Color,” “Moods,” and “Prints and Patterns.”
The researchers used this approach to predict men’s fashion trends for fall/winter 2024 using ChatGPT-3.5 and ChatGPT-4 Classic. The responses were compared and validated against the fall/winter 2024 men’s fashion trend predictions by the Official Fashion Trend Information Company (OFTIC), and the analysis was reviewed by two fashion experts.
Analysis showed that ChatGPT’s predictions mostly reflected established or generalized fashion ideas, rather than forward-looking or innovative designs. Moreover, it accurately identified only 9 out of 39 trends predicted in OFTIC’s report. Notably, however, both models predicted emerging themes, including gender fluidity and statement coats.
“While the prediction accuracy of ChatGPT is low, what's intriguing is that it captured new trends not found in existing data,” notes Dr. Lee. “AI can sense cultural shifts and open up new creative directions.”
Although ChatGPT should not yet be viewed as a definitive forecasting tool, it can effectively complement expert-led analysis. This is especially valuable for fashion students and small brands, helping them achieve more accurate and nuanced trend forecasts. For fashion education, the researchers also developed a TDP-based hybrid conceptual framework for fashion trend forecasting, integrating both AI-analysis and expert-knowledge.
Overall, this study shows how AI tools can make fashion trend forecasting more systematic and accessible.
***
Reference
DOI: 10.1177/0887302X251371969
About Pusan National University
Pusan National University, located in Busan, South Korea, was founded in 1946 and is now the No. 1 national university of South Korea in research and educational competency. The multi-campus university also has other smaller campuses in Yangsan, Miryang, and Ami. The university prides itself on the principles of truth, freedom, and service and has approximately 30,000 students, 1,200 professors, and 750 faculty members. The university comprises 14 colleges (schools) and one independent division, with 103 departments in all.
Website: https://www.pusan.ac.kr/eng/Main.do
About Assistant Professor Yoon Kyung Lee
Dr. Yoon Kyung Lee is an Assistant professor of Fashion Design for Dept. Clothing and Textiles at Pusan National University. Her research interests include Sustainability in fashion, Creativity, Innovative design education, Digital fashion technologies, AI & neuroscience in fashion. Before coming her current position, she worked as an Assistant research professor at Seoul National University. She completed the Postdoctoral training at DeLong’s lab at University of Minnesota. She received a PhD in Aesthetics in Dress from Seoul National University and an MFA in Fashion and Textile Design from the Institute European of Design (IED) Milan, Italy.
END
Sinking land is quietly destabilizing urban infrastructure in India’s largest cities, putting thousands of buildings and millions of people at risk, according to Virginia Tech scientists.
Groundwater overuse is a critical driver of the problem, said Susanna Werth, assistant professor of geosciences who co-authored the paper published Oct. 28 in Nature Sustainability.
“When cities pump more water from aquifers than nature can replenish, the ground quite literally sinks,” Werth said. “Our study shows that this overexploitation ...
Key Messages
In May 2023, devastating floods hit Emilia-Romagna, causing deaths, displacement, and estimated damages of €8.5 billion.
Cul-de-sac effect: The CMCC research team described for the first time how a specific configuration of mountain topography and circulation patterns trapped moisture coming from the Adriatic, while a stationary cyclone fueled prolonged rains that lasted for several days over the same area, leading to extreme flooding.
From the analysis of the Emilia-Romagna case, the ...
ITHACA, N.Y. – Astronomers have generated the first three-dimensional map of a planet orbiting another star, revealing an atmosphere with distinct temperature zones – one so scorching that it breaks down water vapor, a team co-led by a Cornell expert reports in new research.
The temperature map of WASP-18b – a gas giant known as an “ultra-hot Jupiter,” located 400 light years from Earth – is the first applying a technique called 3D eclipse mapping, or spectroscopic eclipse mapping. The effort builds on a 2D model that members of the same team published in 2023, which demonstrated eclipse mapping’s potential ...
For the first time, a team of Inserm researchers from the Physics for Medicine Institute (Inserm/ESPCI Paris-PSL/CNRS) has succeeded in mapping the blood flow of an entire organ in animals (heart, kidney and liver) with great precision, in four dimensions: 3D + time. This new imaging technique, when applied to humans, could both improve our understanding of the circulatory system (veins, arteries, vessels and lymphatic system) and facilitate the diagnosis of certain blood circulation-related diseases. These results are published ...
Low oxygen levels in the blood can alter the genetic makeup of key immune cells, weakening the body’s ability to fight infection, new research shows.
Scientists found that oxygen deprivation – known as hypoxia – changes the genetic material of immune cells called neutrophils, reducing their capacity to destroy harmful microbes.
The team discovered that low oxygen appears to leave a lasting mark on the bone marrow cells that produce neutrophils, meaning the impact can persist after oxygen ...
A new UCLA study reveals that breast milk from women living with HIV contains significantly lower levels of tryptophan, an essential amino acid likely important for infant immune function, growth, and brain development. This discovery may help explain why children born to women living with HIV experience higher rates of illness and developmental challenges, even when the children themselves are not infected with the virus. The study appears in Nature Communications.
Why it matters
Approximately 1.3 million children are born to women living with HIV annually worldwide. Even with effective antiretroviral therapy that prevents HIV transmission, these children who ...
Cancer immunotherapy, especially using T cells, is showing a lot of promise in treating blood cancers. Bioengineered T cells, especially those equipped with chimeric antigen receptors (CAR-T cells), have revolutionized cancer treatment. But while they’ve delivered impressive results against certain blood cancers, they’ve struggled to make an impact in solid tumors, such as those in the breast, lung, and prostate.
The tumor microenvironment is the problem
A major problem is the tumor microenvironment (TME), which is a mix of cells and molecules ...
Photos: here
SAN DIEGO (Oct. 28, 2025) – A new study published in the scientific journal Oikos reveals for the first time the critical role polar bears play as carrion providers for Arctic species. Researchers from University of Manitoba and San Diego Zoo Wildlife Alliance, alongside researchers from Environment and Climate Change Canada, and the University of Alberta, have estimated that polar bears leave behind approximately 7.6 million kilograms of their prey annually, creating a massive and vital food source for a wide network of arctic scavenger ...
Statement Highlights:
Disruptions to circadian rhythms, the body’s internal clock, are strongly associated with increased risk of obesity, Type 2 diabetes, high blood pressure and cardiovascular disease. Factors such as rotating schedules or shift work, irregular sleep and meal times, or light exposure at night often cause these disruptions.
Body clock disruptions impair metabolic regulation, blood pressure control and hormonal balance, contributing to disease progression.
Optimizing circadian rhythms offers a promising preventive strategy for cardiometabolic health. Behavioral interventions to better regulate the body’s ...
In the 17th century, Francis Bacon described a simple experiment—scraping and fracturing hard sugar in the dark to see sparks of light. This phenomenon is called mechanoluminescence (ML) or triboluminescence (TL), the process of materials emitting light under mechanical stimulation, like grinding or crushing. Usually, ML properties of luminescent compounds are observed in rigid crystalline systems, which limits their real-world applications. Now, researchers at the Okinawa Institute of Science and Technology (OIST) have found a way to generate ML ...
