Predicting purchasing intent: Automatic Feature Learning using Recurrent
Neural Networks
H. Sheil, O. Rana, and R. Reilly. (2018)cite arxiv:1807.08207Comment: Accepted to SIGIR eCom workshop, Ann Arbor, Michigan, USA, 2018.
Abstract
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.
Description
Predicting purchasing intent: Automatic Feature Learning using Recurrent Neural Networks
%0 Generic
%1 sheil2018predicting
%A Sheil, Humphrey
%A Rana, Omer
%A Reilly, Ronan
%D 2018
%K human-behaviour marketing neural-networks predictive-models preprint recurrent-neural-networks
%T Predicting purchasing intent: Automatic Feature Learning using Recurrent
Neural Networks
%U http://arxiv.org/abs/1807.08207
%X 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.
@misc{sheil2018predicting,
abstract = {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.},
added-at = {2019-08-22T16:17:15.000+0200},
author = {Sheil, Humphrey and Rana, Omer and Reilly, Ronan},
biburl = {https://www.bibsonomy.org/bibtex/20209fd9696280e1554897ccf13d027f2/nonancourt},
description = {Predicting purchasing intent: Automatic Feature Learning using Recurrent Neural Networks},
interhash = {78de604f5d1432a620d067c96ace7e3d},
intrahash = {0209fd9696280e1554897ccf13d027f2},
keywords = {human-behaviour marketing neural-networks predictive-models preprint recurrent-neural-networks},
note = {cite arxiv:1807.08207Comment: Accepted to SIGIR eCom workshop, Ann Arbor, Michigan, USA, 2018},
timestamp = {2019-08-22T16:21:17.000+0200},
title = {Predicting purchasing intent: Automatic Feature Learning using Recurrent
Neural Networks},
url = {http://arxiv.org/abs/1807.08207},
year = 2018
}