Data Trading Combination Auction Mechanism based on the Exponential Mechanism

TL;DR

This work tackles buyer bid privacy in data-trading combinatorial auctions by introducing DCAE, a differential-privacy-based mechanism that uses the exponential mechanism to select settlement price vectors while preserving privacy and promoting high revenue. The approach combines a two-tier pricing scheme with random allocation to ensure fairness and approximate truthfulness, and it provides a formal DP/Exponential Mechanism framework for price selection. Through extensive simulations in non-competitive and competitive scenarios, DCAE achieves revenue close to the optimum and maintains high buyer privacy across varying privacy budgets $\epsilon$, dataset types $m$, and inventory. The mechanism advances data marketplaces by delivering privacy-preserving, revenue-efficient auctions that are robust across market conditions and scalable with the diversity of datasets.

Abstract

With the widespread application of machine learning technology in recent years, the demand for training data has increased significantly, leading to the emergence of research areas such as data trading. The work in this field is still in the developmental stage. Different buyers have varying degrees of demand for various types of data, and auctions play a role in such scenarios due to their authenticity and fairness. Recent related work has proposed combination auction mechanisms for different domains. However, such mechanisms have not addressed the privacy concerns of buyers. In this paper, we design a \textit{Data Trading Combination Auction Mechanism based on the exponential mechanism} (DCAE) to protect buyers' bidding privacy from being leaked. We apply the exponential mechanism to select the final settlement price for the auction and generate a probability distribution based on the relationship between the price and the revenue. In the experimental aspect, we consider the selection of different mechanisms under two scenarios, and the experimental results show that this method can ensure high auction revenue and protect buyers' privacy from being violated.

Figures (10)

• Figure 1: DCAE Transaction Process.
• Figure 2: Figure 2 Example comparison of three pricing strategies.
• Figure 3: Revenue comparison in non-competitive scenario.
• Figure 4: Mean revenue change (a) and mean satisfaction change (b) in Figure 4
• Figure 5: Mean income change (a) and mean satisfaction change (b)