论文标题
将客户评论纳入时尚电子商务的尺寸和适合建议系统
Incorporating Customer Reviews in Size and Fit Recommendation systems for Fashion E-Commerce
论文作者
论文摘要
随着电子商务领域的巨大增长，产品建议已成为电子商务公司越来越多的兴趣领域。产品建议中最困难的任务之一是尺寸和适合预测。电子时尚域中有很多相关的回报和退款，这给客户带来了不便，并给公司带来了损失。因此，拥有良好的尺寸和合适的推荐系统，可以预测客户的正确尺寸，不仅可以减少相关的回报和退款，而且可以改善客户体验。该领域的早期作品使用传统的机器学习方法来估计购买历史记录的客户和产品规模。由于客户产品数据中的巨大稀疏，这些方法遭受了冷启动问题。最近，人们通过嵌入客户和产品功能来使用深度学习来解决此问题。但是，它们都没有包含在产品页面上存在的有价值的客户反馈以及客户和产品功能。我们提出了一种新颖的方法，可以使用客户评论中的信息以及客户和产品功能来进行尺寸和合适的预测。与仅在4个数据集上使用产品和客户功能相比，我们证明了方法的有效性。我们的方法显示，在4个不同数据集的基线上，F1（宏）得分的提高了1.37％-4.31％。
With the huge growth in e-commerce domain, product recommendations have become an increasing field of interest amongst e-commerce companies. One of the more difficult tasks in product recommendations is size and fit predictions. There are a lot of size related returns and refunds in e-fashion domain which causes inconvenience to the customers as well as costs the company. Thus having a good size and fit recommendation system, which can predict the correct sizes for the customers will not only reduce size related returns and refunds but also improve customer experience. Early works in this field used traditional machine learning approaches to estimate customer and product sizes from purchase history. These methods suffered from cold start problem due to huge sparsity in the customer-product data. More recently, people have used deep learning to address this problem by embedding customer and product features. But none of them incorporates valuable customer feedback present on product pages along with the customer and product features. We propose a novel approach which can use information from customer reviews along with customer and product features for size and fit predictions. We demonstrate the effectiveness of our approach compared to using just product and customer features on 4 datasets. Our method shows an improvement of 1.37% - 4.31% in F1 (macro) score over the baseline across the 4 different datasets.
