DCRMTA: Unbiased Causal Representation for Multi-touch Attribution
- URL: http://arxiv.org/abs/2401.08875v2
- Date: Mon, 5 Feb 2024 08:43:29 GMT
- Title: DCRMTA: Unbiased Causal Representation for Multi-touch Attribution
- Authors: Jiaming Tang
- Abstract summary: Multi-touch attribution (MTA) currently plays a pivotal role in achieving a fair estimation of the contributions of each advertising to-wards conversion behavior.
Previous works attempted to eliminate the bias caused by user preferences to achieve the unbiased assumption of the conversion model.
This paper re-defines the causal effect of user features on con-versions and proposes a novel end-to-end ap-proach, Deep Causal Representation for MTA.
- Score: 0.2417342411475111
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Multi-touch attribution (MTA) currently plays a pivotal role in achieving a
fair estimation of the contributions of each advertising touchpoint to-wards
conversion behavior, deeply influencing budget allocation and advertising
recommenda-tion. Previous works attempted to eliminate the bias caused by user
preferences to achieve the unbiased assumption of the conversion model. The
multi-model collaboration method is not ef-ficient, and the complete
elimination of user in-fluence also eliminates the causal effect of user
features on conversion, resulting in limited per-formance of the conversion
model. This paper re-defines the causal effect of user features on con-versions
and proposes a novel end-to-end ap-proach, Deep Causal Representation for MTA
(DCRMTA). Our model focuses on extracting causa features between conversions
and users while eliminating confounding variables. Fur-thermore, extensive
experiments demonstrate DCRMTA's superior performance in converting prediction
across varying data distributions, while also effectively attributing value
across dif-ferent advertising channels.
Related papers
- A Preference-oriented Diversity Model Based on Mutual-information in Re-ranking for E-commerce Search [11.49911967350851]
This paper proposes a Preference-oriented Diversity Model Based on Mutual-information (PODM-MI)
PODM-MI consider both accuracy and diversity in the re-ranking process.
We have successfully deployed PODM-MI on an e-commerce search platform.
arXiv Detail & Related papers (2024-05-24T13:03:34Z) - Debiasing Multimodal Models via Causal Information Minimization [65.23982806840182]
We study bias arising from confounders in a causal graph for multimodal data.
Robust predictive features contain diverse information that helps a model generalize to out-of-distribution data.
We use these features as confounder representations and use them via methods motivated by causal theory to remove bias from models.
arXiv Detail & Related papers (2023-11-28T16:46:14Z) - Mitigating Biases with Diverse Ensembles and Diffusion Models [99.6100669122048]
We propose an ensemble diversification framework exploiting Diffusion Probabilistic Models (DPMs)
We show that DPMs can generate images with novel feature combinations, even when trained on samples displaying correlated input features.
We show that DPM-guided diversification is sufficient to remove dependence on primary shortcut cues, without a need for additional supervised signals.
arXiv Detail & Related papers (2023-11-23T15:47:33Z) - Ad-Rec: Advanced Feature Interactions to Address Covariate-Shifts in
Recommendation Networks [2.016365643222463]
Cross-feature learning is crucial to handle data distribution drift and adapt to changing user behaviour.
This work introduces Ad-Rec, a network that leverages feature interaction techniques to address covariate shifts.
Our approach improves model quality, accelerates convergence, and reduces training time, as measured by the Area Under Curve (AUC) metric.
arXiv Detail & Related papers (2023-08-28T21:08:06Z) - Causal Disentangled Variational Auto-Encoder for Preference
Understanding in Recommendation [50.93536377097659]
This paper introduces the Causal Disentangled Variational Auto-Encoder (CaD-VAE), a novel approach for learning causal disentangled representations from interaction data in recommender systems.
The approach utilizes structural causal models to generate causal representations that describe the causal relationship between latent factors.
arXiv Detail & Related papers (2023-04-17T00:10:56Z) - The Minority Matters: A Diversity-Promoting Collaborative Metric
Learning Algorithm [154.47590401735323]
Collaborative Metric Learning (CML) has recently emerged as a popular method in recommendation systems.
This paper focuses on a challenging scenario where a user has multiple categories of interests.
We propose a novel method called textitDiversity-Promoting Collaborative Metric Learning (DPCML)
arXiv Detail & Related papers (2022-09-30T08:02:18Z) - DELTA: Diverse Client Sampling for Fasting Federated Learning [9.45219058010201]
Partial client participation has been widely adopted in Federated Learning (FL) to reduce the communication burden efficiently.
Existing sampling methods are either biased or can be further optimized for faster convergence.
We present DELTA, an unbiased sampling scheme designed to alleviate these issues.
arXiv Detail & Related papers (2022-05-27T12:08:23Z) - Deep Causal Reasoning for Recommendations [47.83224399498504]
A new trend in recommender system research is to negate the influence of confounders from a causal perspective.
We model the recommendation as a multi-cause multi-outcome (MCMO) inference problem.
We show that MCMO modeling may lead to high variance due to scarce observations associated with the high-dimensional causal space.
arXiv Detail & Related papers (2022-01-06T15:00:01Z) - CausalMTA: Eliminating the User Confounding Bias for Causal Multi-touch
Attribution [16.854552780506822]
We propose CausalMTA to eliminate the influence of user preferences.
CaulMTA achieves better prediction performance than the state-of-the-art method.
It also generates meaningful attribution credits across different advertising channels.
arXiv Detail & Related papers (2021-12-21T01:59:16Z) - Harnessing Perceptual Adversarial Patches for Crowd Counting [92.79051296850405]
Crowd counting is vulnerable to adversarial examples in the physical world.
This paper proposes the Perceptual Adrial Patch (PAP) generation framework to learn the shared perceptual features between models.
arXiv Detail & Related papers (2021-09-16T13:51:39Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.