We present a novel framework to learn functions that estimate decisions of sellers and buyers simultaneously in an oligopoly market for a price-sensitive product. In this setting, the aim of the seller network is to come up with a price for a given context such that the expected revenue is maximized by considering the buyer's satisfaction as well. On the other hand, the aim of the buyer network is to assign probability of purchase to the offered price to mimic the real world buyers' responses while also showing price sensitivity through its action. In other words, rejecting the unnecessarily high priced products. Similar to generative adversarial networks, this framework corresponds to a minimax two-player game. In our experiments with simulated and real-world transaction data, we compared our framework with the baseline model and demonstrated its potential through proposed evaluation metrics.
翻译:我们提出了一个新框架,用于学习在价格敏感产品寡头市场上同时估计卖方和买方决定的功能;在这一背景下,卖方网络的目的是为某种特定情况提出价格,这样通过考虑买方的满意度也使预期收入最大化;另一方面,买方网络的目的是将购买概率与提供的价格挂钩,模仿真实世界买方的反应,同时通过其行动显示价格敏感性;换句话说,拒绝价格过高的不必要产品;类似于基因化对抗性网络,这一框架相当于小型双人游戏;在模拟和实际交易数据的实验中,我们将我们的框架与基线模型进行了比较,并通过拟议的评价指标展示了框架的潜力。