arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2006.07042cs.LGcs.AIcs.GT
收藏

实时的投标报价随机控制的循环神经网络

Recurrent Neural Networks for Stochastic Control in Real-Time Bidding

Verizon Media(威瑞森传媒)

Nicolas Grislain, Nicolas Perrin, Antoine Thabault

摘要:

实时的【形】拍卖中的投标可能是一个困难的随机控制任务,特别是如果交付不足会招致严厉的惩罚和市场是非常不确定的。大多数当前的作品和实现集中在最佳地提供一个合理的预测市场的活动。实际的实现有一个反馈回路来调整和稳健的预测错误,但没有实现,据我们所知,使用市场风险模型,并积极预测市场变化。在实践中解决这样的随机控制问题实际上是非常具有挑战性的。本文提出了一种基于递归神经网络(RNN)架构的近似解决方案,该架构对于在生产环境中实施既有效又实用。RNN投标者提供了避免错过目标所需的一切。它还故意达不到目标,因为购买缺失的印象所花费的成本超过了没有达到目标的惩罚。

英文摘要:

Bidding in real-time auctions can be a difficult stochastic control task; especially if underdelivery incurs strong penalties and the market is very uncertain. Most current works and implementations focus on optimally delivering a campaign given a reasonable forecast of the market. Practical implementations have a feedback loop to adjust and be robust to forecasting errors, but no implementation, to the best of our knowledge, uses a model of market risk and actively anticipates market shifts. Solving such stochastic control problems in practice is actually very challenging. This paper proposes an approximate solution based on a Recurrent Neural Network (RNN) architecture that is both effective and practical for implementation in a production environment. The RNN bidder provisions everything it needs to avoid missing its goal. It also deliberately falls short of its goal when buying the missing impressions would cost more than the penalty for not reaching it.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑