LiDDA: Data Driven Attribution at LinkedIn

John Bencina, Erkut Aykutlug, Yue Chen, Zerui Zhang, Stephanie Sorenson +2 more
5/14/2025
cs.LGcs.AIcs.IR

No confident code implementation found for this paper.

Abstract

Data Driven Attribution, which assigns conversion credits to marketing interactions based on causal patterns learned from data, is the foundation of modern marketing intelligence and vital to any marketing businesses and advertising platform. In this paper, we introduce a unified transformer-based attribution approach that can handle member-level data, aggregate-level data, and integration of external macro factors. We detail the large scale implementation of the approach at LinkedIn, showcasing significant impact. We also share learning and insights that are broadly applicable to the marketing and ad tech fields.

View on arXivView PDF

Code Implementations

No confident code match yet

We couldn't find an author-owned or strongly-evidenced community implementation for this paper. Any repos shown below are weak matches — verify before relying on them.

No code implementations found yet.

Know of an implementation? Let us know in the comments below!

Similar Papers

Causal-driven attribution (CDA): Estimating channel influence without user-level data

78% match2025

DCRMTA: Unbiased Causal Representation for Multi-touch Attribution

77% match2024

Revisiting Data Attribution for Influence Functions

76% match2025

AttributionLab: Faithfulness of Feature Attribution Under Controllable Environments

74% match2023

Concept Influence: Leveraging Interpretability to Improve Performance and Efficiency in Training Data Attribution

72% match2026

Harmonizing Feature Attributions Across Deep Learning Architectures: Enhancing Interpretability and Consistency

72% match2023

Cite this paper

@article{bencina2025lidda,
  title  = {LiDDA: Data Driven Attribution at LinkedIn},
  author = {John Bencina and Erkut Aykutlug and Yue Chen and Zerui Zhang and Stephanie Sorenson and Shao Tang and Changshuai Wei},
  year   = {2025},
  eprint = {2505.09861},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2505.09861v2}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2505.09861.svg)](https://codeofpaper.com/paper/2505.09861)

Discussion