Leveraging Multiple Relations For Fashion Trend Forecasting Based On Social Media

Abstract

Fashion trend forecasting is of great research significance in providing useful suggestions for both fashion companies and fashion lovers. Although various studies have been devoted to tackling this challenging task, they only studied limited fashion elements with highly seasonal or simple patterns, which could hardly reveal the real complex fashion trends. Moreover, the mainstream solutions for this task are still statistical-based and solely focus on time-series data modelling, which limit the forecast accuracy. Towards insightful fashion trend forecasting, previous work proposed to analyse more fine-grained fashion elements which can informatively reveal fashion trends. Specifically, it focused on detailed fashion element trend forecasting for specific user groups based on social media data. We tend to realize the design to improvise the different fashion trends, with LSTM model indicating the overall dataset from the Kaggle website with different user reviews. We improvise different features of Fashion model with indicating the different features of process with an approach is proposed to predict the future of fashion styles in different price ranges based on raw data and customer transaction data. We measure the popularity of fashion products based on statistics of past customer transactions, and predict the future trend of fashion styles in different price ranges based on consumer transactions. Finally, we compare with different machine and deep learning algorithms with its performance metrics.