Product Popularity Modeling Via Time Series Embedding

Electronic commerce has a dominant role in consumer economics. and popular garnering a lot of research attention. Understanding consumer market dynamics based on product popularity is crucial for business intelligence. This work explores the temporal dynamics in online marketing. We introduce a new popularity index based on Amazon: Product Popularity based on Sales Review Volume (PPSRV). We explore and evaluate sequential deep learning models to obtain time series embedding that can predict the product popularity. We further characterize popularity competition between similar products and extend our model of popularity prediction in a competitive environment. Experimental results on large-scale reviews demonstrate the effectiveness of our approach.