Complete Understanding of Complex Markets through ML

New AI algorithm as a tool for economists.

Auction theory is an essential part of game theory. It is mainly used in economic theory to model markets. Auctions depend on the attached rule: multiple parties place bids to buy products. The parties can pursue one essential strategy, such as bidding less than they will spend, in order to increase their profits. However, you need to be prepared for other parties to act strategically as well.

The Bayes-Nash equilibrium is an essential concept for describing strategic behavior in auctions. Simply put, if neither party could improve their expected benefits by changing their strategy, a sort of an optimal line. An equilibrium of this kind can be modeled as a system of differential equations that cannot be precisely solved in more complex markets. Precise equilibrium strategies are only available for simple auctions, for example, when the parties only bid on one good. Scientists at the Technical University of Munich (TUM) used a machine learning algorithm to analyze complex markets and equilibrium strategies. This new method opens up new possibilities for economic theory and new applications, such as the auction of wireless spectrum.

Martin Bichler, Professor of Decision Sciences and Systems at TUM said: “Machine learning is not yet widely used in auction theory. Using neural networks, we were able to compute equilibrium strategies for complex auction models that were previously unsolvable.”

“For common auction models, we can prove mathematically that the results of the NPGA method reliably converge to the equilibrium strategy. We also showed in experiments that our process delivers extremely close approximations to equilibrium strategies for markets.”

“The new algorithm will help economists to analyze more complex markets and their equilibria. But real-world applications are also conceivable: Since the mid-1990s, governments worldwide have sold wireless spectrum through auctions. The Nobel laureates Robert Wilson and Paul Milgrom have developed auction formats for this purpose.”

“Spectrum auctions are an exciting real-world example. NPGA can help identify strategic issues in advance that could lead to undesirable results – for example, a high likelihood of bidding strategies resulting in spectrum licenses being purchased by inefficient bidders. In this case, the organizers could opt for a different auction mechanism. And conversely, the algorithm could also support bidders in developing their bidding strategies.”

Source link