Customer Lifetime Value Prediction Using Embeddings

We describe the Customer LifeTime Value (CLTV) prediction system deployed at ASOS.com, a global online fashion retailer. CLTV prediction is an important problem in e-commerce where an accurate estimate of future value allows retailers to effectively allocate marketing spend, identify and nurture high value customers and mitigate exposure to losses. The system at ASOS provides daily estimates of the future value of every customer and is one of the cornerstones of the personalised shopping experience. The state of the art in this domain uses large numbers of handcrafted features and ensemble regressors to forecast value, predict churn and evaluate customer loyalty. Recently, domains including language, vision and speech have shown dramatic advances by replacing handcrafted features with features that are learned automatically from data. We detail the system deployed at ASOS and show that learning feature representations is a promising extension to the state of the art in CLTV modelling. We propose a novel way to generate embeddings of customers, which addresses the issue of the ever changing product catalogue and obtain a significant improvement over an exhaustive set of handcrafted features.

[1]  Albert C. Bemmaor,et al.  Modeling Purchasing Behavior with Sudden "Death": A Flexible Customer Lifetime Model , 2012, Manag. Sci..

[2]  Guigang Zhang,et al.  Deep Learning , 2016, Int. J. Semantic Comput..

[3]  Steven Skiena,et al.  DeepWalk: online learning of social representations , 2014, KDD.

[4]  Ricardo Baeza-Yates,et al.  Predicting The Next App That You Are Going To Use , 2015, WSDM.

[5]  Yoshua Bengio,et al.  Extracting and composing robust features with denoising autoencoders , 2008, ICML '08.

[6]  Peter S. Fader,et al.  Counting Your Customers the Easy Way: An Alternative to the Pareto/NBD Model , 2005 .

[7]  Jeffrey Dean,et al.  Distributed Representations of Words and Phrases and their Compositionality , 2013, NIPS.

[8]  Rajesh Parekh,et al.  An Engagement-Based Customer Lifetime Value System for E-commerce , 2016, KDD.

[9]  Dominique M. Hanssens,et al.  Modeling Customer Lifetime Value , 2006 .

[10]  Bianca Zadrozny,et al.  Obtaining calibrated probability estimates from decision trees and naive Bayesian classifiers , 2001, ICML.

[11]  Nemanja Djuric,et al.  E-commerce in Your Inbox: Product Recommendations at Scale , 2015, KDD.

[12]  Paul Covington,et al.  Deep Neural Networks for YouTube Recommendations , 2016, RecSys.

[13]  David C. Schmittlein,et al.  Counting Your Customers: Who-Are They and What Will They Do Next? , 1987 .

[14]  Trevor Darrell,et al.  Caffe: Convolutional Architecture for Fast Feature Embedding , 2014, ACM Multimedia.

[15]  David C. Schmittlein,et al.  Generalizing the NBD Model for Customer Purchases: What Are the Implications and Is It Worth the Effort? , 1988 .

[16]  Heng-Tze Cheng,et al.  Wide & Deep Learning for Recommender Systems , 2016, DLRS@RecSys.

[17]  Martín Abadi,et al.  TensorFlow: Large-Scale Machine Learning on Heterogeneous Distributed Systems , 2016, ArXiv.

[18]  Artit Wangperawong,et al.  Churn analysis using deep convolutional neural networks and autoencoders , 2016, ArXiv.

[19]  Tapani Raiko,et al.  Deep Learning Made Easier by Linear Transformations in Perceptrons , 2012, AISTATS.

[20]  Elena Smirnova,et al.  Meta-Prod2Vec: Product Embeddings Using Side-Information for Recommendation , 2016, RecSys.

[21]  Peter S. Fader,et al.  RFM and CLV: Using Iso-Value Curves for Customer Base Analysis , 2005 .

[22]  S T Roweis,et al.  Nonlinear dimensionality reduction by locally linear embedding. , 2000, Science.

[23]  Martin Wattenberg,et al.  Ad click prediction: a view from the trenches , 2013, KDD.

[24]  Oren Barkan,et al.  ITEM2VEC: Neural item embedding for collaborative filtering , 2016, 2016 IEEE 26th International Workshop on Machine Learning for Signal Processing (MLSP).