User foundation models for Grab

Summary

Grab describes a foundation model that learns from both tabular data and sequential clickstream interactions to represent users, merchants, and drivers across its superapp. Traditional recommender systems depended on manually engineered, task-specific features, which required substantial effort and did not capture evolving behavior holistically. The custom architecture addresses heterogeneous modalities including text, numerical values, IDs, images, and location data, combining long-term profiles with immediate intent. Grab pre-trains the model on a diverse corpus, then either extracts embeddings for downstream recommendation and prediction tasks or fine-tunes it to predict directly. The resulting reusable representations are reported to support applications such as ad optimisation, dual app prediction, fraud detection, and churn probability, while future work targets unified data, improved architecture, and greater training and inference efficiency.

Takeaways

1. 1

   The model combines tabular data describing long-term behavior with clickstream sequences that reflect changing preferences and immediate intent.

2. 2

   Pre-trained embeddings are used for applications including ad optimisation, dual app prediction, fraud detection, and churn probability.

3. 3

   Grab’s future plans include unifying datasets, evolving the architecture, and scaling training and inference infrastructure for greater efficiency.