Learning to Mitigate AI Collusion on Economic Platforms

• URL: http://arxiv.org/abs/2202.07106v1
• Date: Tue, 15 Feb 2022 00:26:59 GMT
• Title: Learning to Mitigate AI Collusion on Economic Platforms
• Authors: Gianluca Brero, Nicolas Lepore, Eric Mibuari, and David C. Parkes
• Abstract summary: We demonstrate that reinforcement learning can be used by platforms to learn buy box rules that are effective in preventing collusion by RL sellers. We adopt the methodology of Stackelberg MDPs, and demonstrate success in learning robust rules that continue to provide high consumer welfare.
• Score: 19.105292496322022
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Algorithmic pricing on online e-commerce platforms raises the concern of tacit collusion, where reinforcement learning algorithms learn to set collusive prices in a decentralized manner and through nothing more than profit feedback. This raises the question as to whether collusive pricing can be prevented through the design of suitable "buy boxes," i.e., through the design of the rules that govern the elements of e-commerce sites that promote particular products and prices to consumers. In previous work, Johnson et al. (2020) designed hand-crafted buy box rules that use demand-steering, based on the history of pricing by sellers, to prevent collusive behavior. Although effective against price collusion, these rules effect this by imposing severe restrictions on consumer choice and consumer welfare. In this paper, we demonstrate that reinforcement learning (RL) can also be used by platforms to learn buy box rules that are effective in preventing collusion by RL sellers, and to do so without reducing consumer choice. For this, we adopt the methodology of Stackelberg MDPs, and demonstrate success in learning robust rules that continue to provide high consumer welfare together with sellers employing different behavior models or having out-of-distribution costs for goods.

Related papers

• The Patterns of Digital Deception [0.0]
  New data-analysis techniques have disrupted the balance of power between companies and their customers. Online tracking enables sellers to amass troves of historical data, apply machine-learning tools to construct detailed customer profiles. The same tools are also used for ill -- to target vulnerable members of the population with scams specially tailored to prey on their weaknesses.
  arXiv  Detail & Related papers  (2024-12-25T15:55:17Z)
• 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)
• Tacit algorithmic collusion in deep reinforcement learning guided price competition: A study using EV charge pricing game [0.0]
  Players in pricing games with complex structures are increasingly adopting artificial intelligence (AI) aided learning algorithms. Recent studies of games in canonical forms have shown contrasting claims ranging from none to a high level of tacit collusion. We consider a practical game where EV charging hubs compete by dynamically varying their prices. Results from our numerical case study yield collusion index values between 0.14 and 0.45, suggesting a low to moderate level of collusion.
  arXiv  Detail & Related papers  (2024-01-25T16:51:52Z)
• Algorithmic Collusion or Competition: the Role of Platforms' Recommender Systems [2.2706058775017217]
  Online platforms commonly deploy recommender systems that influence how consumers discover and purchase products. We propose a novel repeated game framework that integrates several key components. We show that a revenue-maximizing recommender system intensifies algorithmic collusion, whereas a utility-maximizing recommender system encourages more competitive pricing behavior among sellers.
  arXiv  Detail & Related papers  (2023-09-25T21:45:30Z)
• Contextual Dynamic Pricing with Strategic Buyers [93.97401997137564]
  We study the contextual dynamic pricing problem with strategic buyers. Seller does not observe the buyer's true feature, but a manipulated feature according to buyers' strategic behavior. We propose a strategic dynamic pricing policy that incorporates the buyers' strategic behavior into the online learning to maximize the seller's cumulative revenue.
  arXiv  Detail & Related papers  (2023-07-08T23:06:42Z)
• Protecting User Privacy in Online Settings via Supervised Learning [69.38374877559423]
  We design an intelligent approach to online privacy protection that leverages supervised learning. By detecting and blocking data collection that might infringe on a user's privacy, we can restore a degree of digital privacy to the user.
  arXiv  Detail & Related papers  (2023-04-06T05:20:16Z)
• Benchmarking Offline Reinforcement Learning Algorithms for E-Commerce Order Fraud Evaluation [0.571097144710995]
  We propose a system that considers both financial losses of fraud and long-term customer satisfaction. We show that offline RL methods outperform traditional binary classification solutions in SimStore.
  arXiv  Detail & Related papers  (2022-12-05T22:10:13Z)
• Characterization of Frequent Online Shoppers using Statistical Learning with Sparsity [54.26540039514418]
  This work reports a method to learn the shopping preferences of frequent shoppers to an online gift store by combining ideas from retail analytics and statistical learning with sparsity.
  arXiv  Detail & Related papers  (2021-11-11T05:36:39Z)
• Winning at Any Cost -- Infringing the Cartel Prohibition With Reinforcement Learning [1.1470070927586016]
  In e-commerce scenarios, multiple reinforcement learning agents can set prices based on their competitor's prices. We build a scenario that is based on a modified version of a prisoner's dilemma where three agents play the game of rock paper scissors. Our results indicate that the action selection can be dissected into specific stages, establishing the possibility to develop collusion prevention systems.
  arXiv  Detail & Related papers  (2021-07-05T08:21:52Z)
• Learning to Infer User Hidden States for Online Sequential Advertising [52.169666997331724]
  We propose our Deep Intents Sequential Advertising (DISA) method to address these issues. The key part of interpretability is to understand a consumer's purchase intent which is, however, unobservable (called hidden states)
  arXiv  Detail & Related papers  (2020-09-03T05:12:26Z)
• Adversarial Attacks on Linear Contextual Bandits [87.08004581867537]
  Malicious agents may have incentives to attack the bandit algorithm to induce it to perform a desired behavior. We show that a malicious agent can force a linear contextual bandit algorithm to pull any desired arm $T - o(T)$ times over a horizon of $T$ steps. We also investigate the case when a malicious agent is interested in affecting the behavior of the bandit algorithm in a single context.
  arXiv  Detail & Related papers  (2020-02-10T15:04:09Z)

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.