Shapley Value Methods for Attribution Modeling in Online Advertising
Authors: Kaifeng Zhao, Seyed Hanif Mahboobi, Saeed R. Bagheri
Abstract
This paper re-examines the Shapley value methods for attribution analysis in the area of online advertising. As a credit allocation solution in cooperative game theory, Shapley value method directly quantifies the contribution of online advertising inputs to the advertising key performance indicator (KPI) across multiple channels. We simplify its calculation by developing an alternative mathematical formulation. The new formula significantly improves the computational efficiency and therefore extends the scope of applicability. Based on the simplified formula, we further develop the ordered Shapley value method. The proposed method is able to take into account the order of channels visited by users. We claim that it provides a more comprehensive insight by evaluating the attribution of channels at different stages of user conversion journeys. The proposed approaches are illustrated using a real-world online advertising campaign dataset.
The papers around it, by date and closeness
Higher is closer to this paper; left is older. Lines join papers close to each other: groups of lines are sub-topics. Select a point to see why it is there. Back to the summary of this paper
Papers around this one
Ranked by how close their title and abstract are to this paper’s. Select some to read them together.
Closest papers
-
Beyond the Last Touch: Attribution in Online AdvertisingRon Berman · 2018 · Marketing science (Providence, R.I.) · cited 143 times · Not summarized yet
“Beyond the Last Touch” examines how to attribute online advertising effects across publishers while accounting for externalities and uncertain consumer visit patterns.
Abstract
Online advertisers often utilize multiple publishers and bid in multiple auctions concurrently to deliver ads, a process which may result in externalities between publishers that impact advertising effectiveness. In conjunction with these externalities, uncertainty about consumer visit patterns may limit the advertiser's ability to optimize its campaigns.We define the attribution problem as the attempt to measure such uncertainties and correct for the externalities, and determine the characteristics of a good attribution process. Using an analytical model of an online campaign we show that publisher externalities will lead an advertiser to shift from truthful bidding in equilibrium, and that…
-
A Non-parametric Approach to the Multi-channel Attribution ProblemM. Yadagiri, Shiv Kumar Saini, R. Sinha · 2015 · WISE · cited 18 times · Not summarized yet
“A Non-parametric Approach” addresses the multi-channel attribution problem in online advertising.
-
Counterfactual Shapley Additive ExplanationsEmanuele Albini, Jason Long, Danial Dervovic et al. · 2021 · Machine Learning · cited 80 times · AI summary available
“Counterfactual SHAP” adapts Shapley values to explain model features using counterfactual information, rather than attributing advertising-channel contributions.
Abstract
Feature attributions are a common paradigm for model explanations due to their simplicity in assigning a single numeric score for each input feature to a model. In the actionable recourse setting, wherein the goal of the explanations is to improve outcomes for model consumers, it is often unclear how feature attributions should be correctly used. With this work, we aim to strengthen and clarify the link between actionable recourse and feature attributions. Concretely, we propose a variant of SHAP, Counterfactual SHAP (CF-SHAP), that incorporates counterfactual information to produce a background dataset for use within the marginal (a.k.a. interventional) Shapley value framework. We motivate …
-
Attributing Conversions in a Multichannel Online Marketing Environment: An Empirical Model and a Field ExperimentHong-Shuang Li, P. K. Kannan · 2014 · Journal of Marketing Research · cited 446 times · Not summarized yet
“Attributing Conversions” studies conversion attribution in a multichannel online marketing environment using an empirical model and field experiment.
-
Causally motivated attribution for online advertisingBrian Dalessandro, Claudia Perlich, Ori Stitelman et al. · 2012 · International Workshop on Data Mining for Online Advertising · cited 122 times · Not summarized yet
“Causally motivated attribution” studies attribution for online advertising, the same problem of allocating advertising contributions.
-
Attribution Theory and Advertising EffectivenessRichard M. Sparkman, William B. Locander · 1980 · Journal of Consumer Research · cited 108 times · Not summarized yet
“Attribution Theory and Advertising Effectiveness” addresses advertising attribution and effectiveness, a broader context for channel contribution measurement.
-
Do display ads influence search? Attribution and dynamics in online advertisingPavel Kireyev, Koen H. Pauwels, Sunil Gupta · 2016 · International Journal of Research in Marketing · cited 167 times · Not summarized yet
“Do display ads influence search?” examines attribution problems in online advertising and how advertising actions interact over time.
Abstract
As firms increasingly rely on online media to acquire consumers, marketing managers rely on online metrics such as click-through rate (CTR) and cost per acquisition (CPA). However, these standard online advertising metrics are plagued with attribution problems and do not account for synergy or dynamics. These issues can easily lead firms to overspend on some actions and thus waste money and/or underspend in others, leaving money on the table.
-
Efficient Shapley Values Estimation by Amortization for Text ClassificationChenghao Yang, Fan Yin, He He et al. · 2023 · Computation and Language · cited 7 times · AI summary available
“Efficient Shapley Values Estimation” improves computation of Shapley attributions, applying the method to text-classification features rather than advertising channels.
Abstract
Despite the popularity of Shapley Values in explaining neural text classification models, computing them is prohibitive for large pretrained models due to a large number of model evaluations. In practice, Shapley Values are often estimated with a small number of stochastic model evaluations. However, we show that the estimated Shapley Values are sensitive to random seed choices -- the top-ranked features often have little overlap across different seeds, especially on examples with longer input texts. This can only be mitigated by aggregating thousands of model evaluations, which on the other hand, induces substantial computational overheads. To mitigate the trade-off between stability and ef…
Prior work it builds on
-
A patent portfolio-based approach for assessing potential R&D partners: An application of the Shapley valueB. Song, H. Seol, Yongtae Park · 2016 · Technological Forecasting and Social Change · cited 44 times · Not summarized yet
“A patent portfolio-based approach” applies the Shapley value to assess R&D partners, rather than allocate online advertising credit.
-
The Shapley ValueRobert J. Aumann · 1994 · cited 1,083 times · Not summarized yet
“The Shapley Value” presents the underlying cooperative-game allocation concept used by this paper to assign credit to advertising channels.
-
Practice Prize Paper - Marketing's Profit Impact: Quantifying Online and Off-line Funnel ProgressionT. Wiesel, Koen H. Pauwels, J. Arts · 2011 · Marketing science (Providence, R.I.) · cited 185 times · Not summarized yet
“Marketing's Profit Impact” quantifies online and offline funnel progression, addressing how marketing channels contribute to outcomes.
-
A multiple criteria hesitant fuzzy decision making with Shapley value-based VIKOR methodG. Wei, Nian Zhang · 2014 · Journal of Intelligent & Fuzzy Systems · cited 107 times · Not summarized yet
“A multiple criteria hesitant fuzzy decision making” incorporates the Shapley value into a VIKOR decision method, applying it outside advertising attribution.
-
A Value for n-person GamesL. Shapley · 1988 · cited 10,819 times · Not summarized yet
“A Value for n-person Games” introduces a value for cooperative games that grounds this paper’s use of Shapley-based credit allocation.
Go further
How are these papers found?
We compare the title and abstract of this paper with those of every paper summarized on this site, and with the papers Semantic Scholar recommends, those it cites and those citing it (for a much-cited paper, its most recent citations and, from OpenAlex, the most cited ones). Among the prior work and the follow-ups, the papers that use each other in depth, a method it uses and the much-cited follow-ups come a little higher. The levels (very close, close, related) come from the similarity of the texts, not from a judgment of quality; * marks a paper without an abstract, compared by its title. The sentence under a paper is written by an AI from the two abstracts: check it in the papers. A paper marked not relevant by three readers leaves the list.
Updated on 5 November 2026.