Multimodal Quasi-AutoRegression: forecasting the visual popularity of new fashion products

Abstract

Estimating the preferences of consumers is of utmost importance for the fashion industry as appropriately leveraging this information can be beneficial in terms of profit. Trend detection in fashion is a challenging task due to the fast pace of change in the fashion industry. Moreover, forecasting the visual popularity of new garment designs is even more demanding due to lack of historical data. To this end, we propose MuQAR, a Multimodal Quasi-AutoRegressive deep learning architecture that combines two modules: (1) a multimodal multilayer perceptron processing categorical, visual and textual features of the product and (2) a Quasi-AutoRegressive neural network modelling the “target” time series of the product’s attributes along with the “exogenous” time series of all other attributes. We utilize computer vision, image classification and image captioning, for automatically extracting visual features and textual descriptions from the images of new products. Product design in fashion is initially expressed visually and these features represent the products’ unique characteristics without interfering with the creative process of its designers by requiring additional inputs (e.g. manually written texts). We employ the product’s target attributes time series as a proxy of temporal popularity patterns, mitigating the lack of historical data, while exogenous time series help capture trends among interrelated attributes. We perform an extensive ablation analysis on two large-scale image fashion datasets, Mallzee-P and SHIFT15m to assess the adequacy of MuQAR and also use the Amazon Reviews: Home and Kitchen dataset to assess generalization to other domains. A comparative study on the VISUELLE dataset shows that MuQAR is capable of competing and surpassing the domain’s current state of the art by 4.65% and 4.8% in terms of WAPE and MAE, respectively.

Evaluating the sales potential of new products using machine learning techniques and data collected from mobile applications

“…In another approach, the extracted features enable the generation of time series from different social media or Internet sources, such as Google Trends (Skenderi et al, 2021). In Papadopoulos et al (2022), a comprehensive model is developed with an image captioning model to extract attributes from images, associated with a Quasi-Autoregressive model for the time series prediction of this attributes. Another method described in Santosh et al (2018) proposes a new popularity index based on sales review volume on Amazon.…”

“…, 2021). In Papadopoulos et al. (2022), a comprehensive model is developed with an image captioning model to extract attributes from images, associated with a Quasi-Autoregressive model for the time series prediction of this attributes.…”

Application of Computer Vision on E-Commerce Platforms and Its Impact on Sales Forecasting

“…4. Literature #4 (Papadopoulos et al, 2022) propose MuQAR, a Multimodal Quasi-AutoRegressive deep learning architecture that combines two modules: (1) a multimodal multilayer perceptron processing categorical, visual, and textual features of the product and (2) a Quasi-AutoRegressive neural network modelling the "target" time series of the product's attributes along with the "exogenous" time series of all other attributes. 5.…”

Achieving Sales Forecasting with Higher Accuracy and Efficiency: A New Model Based on Modified Transformer

“…Yang and Lu introduced Foreformer, an augmented Transformer-based model that includes a static covariate processing module and a multiple-time-resolution module for in-depth extraction of time patterns at various scales [38]. Papadopoulos et al proposed MuQAR, a multimodal quasi-autoregressive deep learning architecture based on the Transformer, combining a multimodal multilayer perception module with a quasi-auto regression neural network [39]. Going beyond standard Transformers, Wu et al introduced the Autoformer model, which employs a novel decomposition architecture featuring an auto-correlation mechanism to enhance efficiency and accuracy in long-term forecasting scenarios [40].…”