Predicting purchasing intent: Automatic Feature Learning using Recurrent Neural Networks
This reduces the significant investment in feature engineering for e-commerce applications, though it is incremental as it builds on existing neural network methods.
The paper tackles the problem of predicting purchasing intent in e-commerce by eliminating the need for manual feature engineering, achieving classification accuracy within 98% of state-of-the-art on one benchmark and exceeding it on another.
We present a neural network for predicting purchasing intent in an Ecommerce setting. Our main contribution is to address the significant investment in feature engineering that is usually associated with state-of-the-art methods such as Gradient Boosted Machines. We use trainable vector spaces to model varied, semi-structured input data comprising categoricals, quantities and unique instances. Multi-layer recurrent neural networks capture both session-local and dataset-global event dependencies and relationships for user sessions of any length. An exploration of model design decisions including parameter sharing and skip connections further increase model accuracy. Results on benchmark datasets deliver classification accuracy within 98% of state-of-the-art on one and exceed state-of-the-art on the second without the need for any domain / dataset-specific feature engineering on both short and long event sequences.