New Fashion Products Performance Forecasting: A Survey on Evolutions, Models and Emerging Trends

TL;DR

This survey addresses New Fashion Products Performance Forecasting (NFPPF), a problem of forecasting sales for newly released fashion items under rapidly shifting consumer preferences and limited historical data. It adopts a PRISMA-based systematic review to categorize learning-based NFPPF approaches into five modalities—tabular, visual, Google Trends, generative, and visual-search models—and evaluates them on the VISUELLE dataset family, highlighting the pivotal role of multimodal data. Key findings indicate that models combining image and tabular data often outperform those relying solely on external signals like Google Trends, while diffusion-based generative methods show promise for robustness to distribution shifts; the POP signal demonstrates scalable, web-driven exogenous information. The paper emphasizes future directions such as integrating human pose information and leveraging foundation-model knowledge to enrich representations and forecasting, with implications for reducing overproduction and advancing sustainable fashion practices.

Abstract

The fast fashion industry's insatiable demand for new styles and rapid production cycles has led to a significant environmental burden. Overproduction, excessive waste, and harmful chemicals have contributed to the negative environmental impact of the industry. To mitigate these issues, a paradigm shift that prioritizes sustainability and efficiency is urgently needed. Integrating learning-based predictive analytics into the fashion industry represents a significant opportunity to address environmental challenges and drive sustainable practices. By forecasting fashion trends and optimizing production, brands can reduce their ecological footprint while remaining competitive in a rapidly changing market. However, one of the key challenges in forecasting fashion sales is the dynamic nature of consumer preferences. Fashion is acyclical, with trends constantly evolving and resurfacing. In addition, cultural changes and unexpected events can disrupt established patterns. This problem is also known as New Fashion Products Performance Forecasting (NFPPF), and it has recently gained more and more interest in the global research landscape. Given its multidisciplinary nature, the field of NFPPF has been approached from many different angles. This comprehensive survey wishes to provide an up-to-date overview that focuses on learning-based NFPPF strategies. The survey is based on the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) methodological flow, allowing for a systematic and complete literature review. In particular, we propose the first taxonomy that covers the learning panorama for NFPPF, examining in detail the different methodologies used to increase the amount of multimodal information, as well as the state-of-the-art available datasets. Finally, we discuss the challenges and future directions.

Figures (4)

• Figure 1: a) A standard forecasting setup, where an evergreen item has past observations to exploit, e.g., # sales. b) problem, where no past observations are available, and exogenous data must be considered. The figure is from joppi2022pop.
• Figure 2: Examples of data in the VISUELLE 2.0 dataset. The figure reports (from left to right) the product’s image, textual tags, sales time series, restocking information, inventory time series, and discount time series. Figures are from skenderi2022multi.
• Figure 3: -based flowchart of the retrieval process. Due to space issues, the diagram has been reformatted into a horizontal rather than the standard vertical format.
• Figure 4: Our proposed taxonomy covers the available methodologies for addressing the task.