An LSTM-Based Dynamic Customer Model for Fashion Recommendation
This work addresses the problem of dynamic recommendation for fashion retailers, but it is incremental as it builds on existing neural network methods for a specific domain.
The paper tackles the challenge of personalized fashion recommendation in online stores with high item turnover and infrequent customer purchases by developing an LSTM-based dynamic customer model. It reports backtest experiments on 100k frequent shoppers at Zalando, showing improved performance over static collaborative filtering and popularity baselines.
Online fashion sales present a challenging use case for personalized recommendation: Stores offer a huge variety of items in multiple sizes. Small stocks, high return rates, seasonality, and changing trends cause continuous turnover of articles for sale on all time scales. Customers tend to shop rarely, but often buy multiple items at once. We report on backtest experiments with sales data of 100k frequent shoppers at Zalando, Europe's leading online fashion platform. To model changing customer and store environments, our recommendation method employs a pair of neural networks: To overcome the cold start problem, a feedforward network generates article embeddings in "fashion space," which serve as input to a recurrent neural network that predicts a style vector in this space for each client, based on their past purchase sequence. We compare our results with a static collaborative filtering approach, and a popularity ranking baseline.