# Negotiating Networks in Oligopoly Markets for Price-Sensitive Products

arXiv: https://arxiv.org/abs/2110.13303 · HTML: https://mlsanity.com/paper/2110.13303/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 9 of its 38 references that are in the map.
- First posted on arXiv 25 Oct 2021.

## Builds on (most cited first, 9 of 9)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Image-to-Image Translation with Conditional Adversarial Networks](https://mlsanity.com/paper/1611.07004/) (2016)
- [Pointer Networks](https://mlsanity.com/paper/1506.03134/) (2015)
- [Unsupervised Image-to-Image Translation Networks](https://mlsanity.com/paper/1703.00848/) (2017)
- [Unsupervised Pixel-Level Domain Adaptation with Generative Adversarial Networks](https://mlsanity.com/paper/1612.05424/) (2016)
- [Semantic-Aware Generative Adversarial Nets for Unsupervised Domain Adaptation in Chest X-ray Segmentation](https://mlsanity.com/paper/1806.00600/) (2018)
- [How to Incorporate Monotonicity in Deep Networks While Preserving Flexibility?](https://mlsanity.com/paper/1909.10662/) (2019)
- [Deep Choice Model Using Pointer Networks for Airline Itinerary Prediction](https://mlsanity.com/paper/1803.05976/) (2018)
- [Dynamic Pricing for Airline Ancillaries with Customer Context](https://mlsanity.com/paper/1902.02236/) (2019)

## Abstract (arXiv)

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.