Saved in:
Bibliographic Details
Main Authors: Smirnov, Oleg, Polisi, Labinot
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2406.05274
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913381902974976
author Smirnov, Oleg
Polisi, Labinot
author_facet Smirnov, Oleg
Polisi, Labinot
contents In this paper, we introduce the Behavior Structformer, a method for modeling user behavior using structured tokenization within a Transformer-based architecture. By converting tracking events into dense tokens, this approach enhances model training efficiency and effectiveness. We demonstrate its superior performance through ablation studies and benchmarking against traditional tabular and semi-structured baselines. The results indicate that structured tokenization with sequential processing significantly improves behavior modeling.
format Preprint
id arxiv_https___arxiv_org_abs_2406_05274
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Behavior Structformer: Learning Players Representations with Structured Tokenization
Smirnov, Oleg
Polisi, Labinot
Computation and Language
Machine Learning
In this paper, we introduce the Behavior Structformer, a method for modeling user behavior using structured tokenization within a Transformer-based architecture. By converting tracking events into dense tokens, this approach enhances model training efficiency and effectiveness. We demonstrate its superior performance through ablation studies and benchmarking against traditional tabular and semi-structured baselines. The results indicate that structured tokenization with sequential processing significantly improves behavior modeling.
title Behavior Structformer: Learning Players Representations with Structured Tokenization
topic Computation and Language
Machine Learning
url https://arxiv.org/abs/2406.05274