# Customer Lifetime Value Prediction Using Embeddings

## TL;DR

This paper presents a novel embedding-based system for predicting customer lifetime value at ASOS, improving accuracy over traditional handcrafted feature methods by automatically learning customer representations.

## Contribution

Introduces a new embedding approach for CLTV prediction that adapts to changing product catalogs, enhancing prediction accuracy beyond handcrafted features.

## Key findings

- Embedding-based features outperform handcrafted features in CLTV prediction
- System provides daily updated customer lifetime value estimates
- Significant improvement over traditional feature-based models

## Abstract

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.