Customer Lifetime Value Prediction Using Embeddings
| Autor: | Marc Peter Deisenroth, Benjamin Paul Chamberlain, Angelo Cardoso, Roberto Pagliari, C. H. Bryan Liu |
|---|---|
| Rok vydání: | 2017 |
| Předmět: |
FOS: Computer and information sciences
Random Forests Technology Neural Networks Computer science cs.LG Future value Machine Learning (stat.ML) Customer Lifetime Value E-commerce 02 engineering and technology Machine learning computer.software_genre Computer Science Artificial Intelligence Computer Science - Information Retrieval Machine Learning (cs.LG) Loyalty business model Domain (software engineering) Set (abstract data type) Computer Science - Computers and Society Statistics - Machine Learning Computer Science Theory & Methods 020204 information systems Computers and Society (cs.CY) 0202 electrical engineering electronic engineering information engineering Feature (machine learning) Neural and Evolutionary Computing (cs.NE) cs.NE cs.CY Science & Technology Computer Science Information Systems business.industry Computer Science - Neural and Evolutionary Computing cs.IR Customer lifetime value stat.ML Embeddings Product (business) Computer Science - Learning Computer Science Value (economics) 020201 artificial intelligence & image processing Artificial intelligence business computer Information Retrieval (cs.IR) |
| Zdroj: | International Conference on Knowledge Discovery and Data Mining |
| Popis: | 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. Comment: 10 pages, 11 figures |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|