Dynamic Pricing Strategy for Data Product Through Deep Reinforcement Learning

With the rapid development of the data trading market, traditional fixed pricing strategies can no longer effectively reflect the real value of data products, thereby restricting the development of the data trading market. To address this challenge, this paper proposes a dynamic pricing method for d...

Full description

Saved in:
Bibliographic Details
Main Authors: Junxin Shen, Yashi Wang, Fanghao Xiao
Format: Article
Language:English
Published: IEEE 2024-01-01
Series:IEEE Access
Subjects:
Online Access:https://ieeexplore.ieee.org/document/10810405/
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1846102154061807616
author Junxin Shen
Yashi Wang
Fanghao Xiao
author_facet Junxin Shen
Yashi Wang
Fanghao Xiao
author_sort Junxin Shen
collection DOAJ
description With the rapid development of the data trading market, traditional fixed pricing strategies can no longer effectively reflect the real value of data products, thereby restricting the development of the data trading market. To address this challenge, this paper proposes a dynamic pricing method for data products based on deep reinforcement learning, aiming to attract buyers through dynamic pricing strategies and maximize the cumulative profits of data sellers, thus driving the further development of the data trading market. First, the dynamic pricing problem for data products is modeled as a Markov Decision Process (MDP). Then, a dynamic pricing algorithm based on the Deep Q-learning algorithm is designed, incorporating an annealing mechanism to optimize the exploration strategy. Finally, the performance of traditional reinforcement learning algorithms, specifically Q-learning and SARSA, is compared. The experimental results show that the dynamic pricing method based on deep reinforcement learning not only effectively enhances the cumulative profits of sellers but also significantly improves both revenue and algorithm performance compared to static pricing strategies and traditional reinforcement learning algorithms. This research provides a novel solution for data product pricing, contributing to the healthy development of the digital economy.
format Article
id doaj-art-a8cff29ce4b34fd4ba2bbf796a083bac
institution Kabale University
issn 2169-3536
language English
publishDate 2024-01-01
publisher IEEE
record_format Article
series IEEE Access
spelling doaj-art-a8cff29ce4b34fd4ba2bbf796a083bac2024-12-28T00:01:12ZengIEEEIEEE Access2169-35362024-01-011219482919483810.1109/ACCESS.2024.352067010810405Dynamic Pricing Strategy for Data Product Through Deep Reinforcement LearningJunxin Shen0https://orcid.org/0000-0001-7671-6636Yashi Wang1Fanghao Xiao2https://orcid.org/0000-0003-2390-8399School of Economics and Management, Kunming University of Science and Technology, Kunming, ChinaSchool of Economics and Management, Kunming University of Science and Technology, Kunming, ChinaMarxist College, Xiamen Institute of Technology, Xiamen, ChinaWith the rapid development of the data trading market, traditional fixed pricing strategies can no longer effectively reflect the real value of data products, thereby restricting the development of the data trading market. To address this challenge, this paper proposes a dynamic pricing method for data products based on deep reinforcement learning, aiming to attract buyers through dynamic pricing strategies and maximize the cumulative profits of data sellers, thus driving the further development of the data trading market. First, the dynamic pricing problem for data products is modeled as a Markov Decision Process (MDP). Then, a dynamic pricing algorithm based on the Deep Q-learning algorithm is designed, incorporating an annealing mechanism to optimize the exploration strategy. Finally, the performance of traditional reinforcement learning algorithms, specifically Q-learning and SARSA, is compared. The experimental results show that the dynamic pricing method based on deep reinforcement learning not only effectively enhances the cumulative profits of sellers but also significantly improves both revenue and algorithm performance compared to static pricing strategies and traditional reinforcement learning algorithms. This research provides a novel solution for data product pricing, contributing to the healthy development of the digital economy.https://ieeexplore.ieee.org/document/10810405/Data trading marketdynamic pricingdeep reinforcement learningdigital economy
spellingShingle Junxin Shen
Yashi Wang
Fanghao Xiao
Dynamic Pricing Strategy for Data Product Through Deep Reinforcement Learning
IEEE Access
Data trading market
dynamic pricing
deep reinforcement learning
digital economy
title Dynamic Pricing Strategy for Data Product Through Deep Reinforcement Learning
title_full Dynamic Pricing Strategy for Data Product Through Deep Reinforcement Learning
title_fullStr Dynamic Pricing Strategy for Data Product Through Deep Reinforcement Learning
title_full_unstemmed Dynamic Pricing Strategy for Data Product Through Deep Reinforcement Learning
title_short Dynamic Pricing Strategy for Data Product Through Deep Reinforcement Learning
title_sort dynamic pricing strategy for data product through deep reinforcement learning
topic Data trading market
dynamic pricing
deep reinforcement learning
digital economy
url https://ieeexplore.ieee.org/document/10810405/
work_keys_str_mv AT junxinshen dynamicpricingstrategyfordataproductthroughdeepreinforcementlearning
AT yashiwang dynamicpricingstrategyfordataproductthroughdeepreinforcementlearning
AT fanghaoxiao dynamicpricingstrategyfordataproductthroughdeepreinforcementlearning