Algorithmic Content Selection and the Impact of User Disengagement

• URL: http://arxiv.org/abs/2410.13108v1
• Date: Thu, 17 Oct 2024 00:43:06 GMT
• Title: Algorithmic Content Selection and the Impact of User Disengagement
• Authors: Emilio Calvano, Nika Haghtalab, Ellen Vitercik, Eric Zhao,
• Abstract summary: We introduce a model for the content selection problem where dissatisfied users may disengage. We show that when the relationship between each arm's expected reward and effect on user satisfaction are linearly related, an optimal content selection policy can be computed efficiently.
• Score: 19.14804091327051
• License:
• Abstract: The content selection problem of digital services is often modeled as a decision-process where a service chooses, over multiple rounds, an arm to pull from a set of arms that each return a certain reward. This classical model does not account for the possibility that users disengage when dissatisfied and thus fails to capture an important trade-off between choosing content that promotes future engagement versus immediate reward. In this work, we introduce a model for the content selection problem where dissatisfied users may disengage and where the content that maximizes immediate reward does not necessarily maximize the odds of future user engagement. We show that when the relationship between each arm's expected reward and effect on user satisfaction are linearly related, an optimal content selection policy can be computed efficiently with dynamic programming under natural assumptions about the complexity of the users' engagement patterns. Moreover, we show that in an online learning setting where users with unknown engagement patterns arrive, there is a variant of Hedge that attains a $\tfrac 12$-competitive ratio regret bound. We also use our model to identify key primitives that determine how digital services should weigh engagement against revenue. For example, when it is more difficult for users to rejoin a service they are disengaged from, digital services naturally see a reduced payoff but user engagement may -- counterintuitively -- increase.

Related papers

• A Primal-Dual Online Learning Approach for Dynamic Pricing of Sequentially Displayed Complementary Items under Sale Constraints [54.46126953873298]
  We address the problem of dynamically pricing complementary items that are sequentially displayed to customers. Coherent pricing policies for complementary items are essential because optimizing the pricing of each item individually is ineffective. We empirically evaluate our approach using synthetic settings randomly generated from real-world data, and compare its performance in terms of constraints violation and regret.
  arXiv  Detail & Related papers  (2024-07-08T09:55:31Z)
• Learning from Streaming Data when Users Choose [3.2429724835345692]
  In digital markets comprised of many competing services, each user chooses between multiple service providers according to their preferences, and the chosen service makes use of the user data to incrementally improve its model. The service providers' models influence which service the user will choose at the next time step, and the user's choice, in return, influences the model update, leading to a feedback loop. We develop a simple and efficient decentralized algorithm to minimize the overall user loss.
  arXiv  Detail & Related papers  (2024-06-03T16:07:52Z)
• Ad-load Balancing via Off-policy Learning in a Content Marketplace [9.783697404304025]
  Ad-load balancing is a critical challenge in online advertising systems, particularly in the context of social media platforms. Traditional approaches to ad-load balancing rely on static allocation policies, which fail to adapt to changing user preferences and contextual factors. We present an approach that leverages off-policy learning and evaluation from logged bandit feedback.
  arXiv  Detail & Related papers  (2023-09-19T09:17:07Z)
• Preferences Evolve And So Should Your Bandits: Bandits with Evolving States for Online Platforms [12.368291979686122]
  We propose a model for learning with bandit feedback while accounting for deterministically evolving and unobservable states. The workhorse applications of our model are learning for recommendation systems and learning for online ads.
  arXiv  Detail & Related papers  (2023-07-21T15:43:32Z)
• Online Learning in a Creator Economy [91.55437924091844]
  We study the creator economy as a three-party game between the users, platform, and content creators. We analyze two families of contracts: return-based contracts and feature-based contracts. We show that under smoothness assumptions, the joint optimization of return-based contracts and recommendation policy provides a regret.
  arXiv  Detail & Related papers  (2023-05-19T01:58:13Z)
• How Bad is Top-$K$ Recommendation under Competing Content Creators? [43.2268992294178]
  We study the user welfare guarantee through the lens of Price of Anarchy. We show that the fraction of user welfare loss due to creator competition is always upper bounded by a small constant depending on $K$ and randomness in user decisions.
  arXiv  Detail & Related papers  (2023-02-03T19:37:35Z)
• Learning with Exposure Constraints in Recommendation Systems [7.397067779113841]
  We propose a contextual multi-armed bandit setting to model the dependency of content providers on exposure. We develop algorithms with sub-linear regret, as well as a lower bound that demonstrates that our algorithms are optimal up to logarithmic factors.
  arXiv  Detail & Related papers  (2023-02-02T19:23:50Z)
• Personalizing Intervened Network for Long-tailed Sequential User Behavior Modeling [66.02953670238647]
  Tail users suffer from significantly lower-quality recommendation than the head users after joint training. A model trained on tail users separately still achieve inferior results due to limited data. We propose a novel approach that significantly improves the recommendation performance of the tail users.
  arXiv  Detail & Related papers  (2022-08-19T02:50:19Z)
• Modeling Content Creator Incentives on Algorithm-Curated Platforms [76.53541575455978]
  We study how algorithmic choices affect the existence and character of (Nash) equilibria in exposure games. We propose tools for numerically finding equilibria in exposure games, and illustrate results of an audit on the MovieLens and LastFM datasets.
  arXiv  Detail & Related papers  (2022-06-27T08:16:59Z)
• PURS: Personalized Unexpected Recommender System for Improving User Satisfaction [76.98616102965023]
  We describe a novel Personalized Unexpected Recommender System (PURS) model that incorporates unexpectedness into the recommendation process. Extensive offline experiments on three real-world datasets illustrate that the proposed PURS model significantly outperforms the state-of-the-art baseline approaches.
  arXiv  Detail & Related papers  (2021-06-05T01:33:21Z)
• Non-Stationary Latent Bandits [68.21614490603758]
  We propose a practical approach for fast personalization to non-stationary users. The key idea is to frame this problem as a latent bandit, where prototypical models of user behavior are learned offline and the latent state of the user is inferred online. We propose Thompson sampling algorithms for regret minimization in non-stationary latent bandits, analyze them, and evaluate them on a real-world dataset.
  arXiv  Detail & Related papers  (2020-12-01T10:31:57Z)

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.