Reinforcement Mechanism Design: With Applications to Dynamic Pricing in Sponsored Search Auctions
Mechanism Design
Dynamic Pricing
Combinatorial auction
DOI:
10.1609/aaai.v34i02.5600
Publication Date:
2020-06-29T19:46:20Z
AUTHORS (10)
ABSTRACT
In many social systems in which individuals and organizations interact with each other, there can be no easy laws to govern the rules of environment, agents' payoffs are often influenced by other actions. We examine such a system setting sponsored search auctions tackle engine's dynamic pricing problem combining tools from both mechanism design AI domain. this setting, environment not only changes over time, but also behaves strategically. Over repeated interactions bidders, engine dynamically change reserve prices determine optimal strategy that maximizes profit. first train buyer behavior model, real bidding data set major engine, predicts bids given information disclosed bidders' performance previous rounds. then formulate as an MDP apply reinforcement-based algorithm optimizes time. Experiments demonstrate our model outperforms static optimization strategies including ones currently use well several ones.
SUPPLEMENTAL MATERIAL
Coming soon ....
REFERENCES (0)
CITATIONS (21)
EXTERNAL LINKS
PlumX Metrics
RECOMMENDATIONS
FAIR ASSESSMENT
Coming soon ....
JUPYTER LAB
Coming soon ....