This is an Open access book which provides a comprehensive framework for identifying monopolistic behaviors in the digital economy, with a focus on discriminatory pricing as one manifestation of these practices. As digital platforms increasingly dominate markets and collect unprecedented volumes of user data, pricing strategies tailored to user profiles—often resulting in discriminatory pricing—raise major concerns about consumer rights, market fairness, and competition. Differential pricing driven by big data is widespread in sectors like e-commerce, travel, and ride-hailing; however, when adopted by dominant enterprises, it risks evolving into monopolistic practices that challenge existing legal frameworks and consumer protections. On the algorithmic level, this book tackles these challenges by developing an innovative, machine-learning-based approach for real-time detection of discriminatory pricing and related monopolistic behaviors. Recognizing that traditional regulatory oversight heavily relies on consumer complaints and is often retrospective, we propose an advanced Dual Pricing Model Clustering (DPMC) framework, which proactively distinguishes between discriminatory and non-discriminatory pricing using real-world data patterns. Initially, the book focuses on the online ride-hailing industry, where dynamic pricing is common and has attracted widespread public attention. It offers practical insights and a robust, transferable framework applicable to other sectors facing similar issues. From the perspective of antitrust business needs, we have also developed an intelligent antitrust system. Beyond its statistical analysis capabilities, the book explores the application of large models in the antitrust field, proposing a "Computational Antitrust Large Model." This model integrates large language models with monopolistic behavior identification models, combining insights from public sentiment and other intelligence sources to assist regulators in proactively detecting monopolistic behavior clues. The book is designed for professionals and scholars in antitrust regulation, digital economy governance, and data science, aiming to equip them with the knowledge and tools needed to address monopolistic and discriminatory practices in the platform economy.

This is an Open access book which provides a comprehensive framework for identifying monopolistic behaviors in the digital economy, with a focus on discriminatory pricing as one manifestation of these practices. As digital platforms increasingly dominate markets and collect unprecedented volumes of user data, pricing strategies tailored to user profiles—often resulting in discriminatory pricing—raise major concerns about consumer rights, market fairness, and competition. Differential pricing driven by big data is widespread in sectors like e-commerce, travel, and ride-hailing; however, when adopted by dominant enterprises, it risks evolving into monopolistic practices that challenge existing legal frameworks and consumer protections. On the algorithmic level, this book tackles these challenges by developing an innovative, machine-learning-based approach for real-time detection of discriminatory pricing and related monopolistic behaviors. Recognizing that traditional regulatory oversight heavily relies on consumer complaints and is often retrospective, we propose an advanced Dual Pricing Model Clustering (DPMC) framework, which proactively distinguishes between discriminatory and non-discriminatory pricing using real-world data patterns. Initially, the book focuses on the online ride-hailing industry, where dynamic pricing is common and has attracted widespread public attention. It offers practical insights and a robust, transferable framework applicable to other sectors facing similar issues. From the perspective of antitrust business needs, we have also developed an intelligent antitrust system. Beyond its statistical analysis capabilities, the book explores the application of large models in the antitrust field, proposing a "Computational Antitrust Large Model." This model integrates large language models with monopolistic behavior identification models, combining insights from public sentiment and other intelligence sources to assist regulators in proactively detecting monopolistic behavior clues. The book is designed for professionals and scholars in antitrust regulation, digital economy governance, and data science, aiming to equip them with the knowledge and tools needed to address monopolistic and discriminatory practices in the platform economy.

This is an Open access book which provides a comprehensive framework for identifying monopolistic behaviors in the digital economy, with a focus on discriminatory pricing as one manifestation of these practices. As digital platforms increasingly dominate markets and collect unprecedented volumes of user data, pricing strategies tailored to user profiles—often resulting in discriminatory pricing—raise major concerns about consumer rights, market fairness, and competition. Differential pricing driven by big data is widespread in sectors like e-commerce, travel, and ride-hailing; however, when adopted by dominant enterprises, it risks evolving into monopolistic practices that challenge existing legal frameworks and consumer protections. On the algorithmic level, this book tackles these challenges by developing an innovative, machine-learning-based approach for real-time detection of discriminatory pricing and related monopolistic behaviors. Recognizing that traditional regulatory oversight heavily relies on consumer complaints and is often retrospective, we propose an advanced Dual Pricing Model Clustering (DPMC) framework, which proactively distinguishes between discriminatory and non-discriminatory pricing using real-world data patterns. Initially, the book focuses on the online ride-hailing industry, where dynamic pricing is common and has attracted widespread public attention. It offers practical insights and a robust, transferable framework applicable to other sectors facing similar issues. From the perspective of antitrust business needs, we have also developed an intelligent antitrust system. Beyond its statistical analysis capabilities, the book explores the application of large models in the antitrust field, proposing a "Computational Antitrust Large Model." This model integrates large language models with monopolistic behavior identification models, combining insights from public sentiment and other intelligence sources to assist regulators in proactively detecting monopolistic behavior clues. The book is designed for professionals and scholars in antitrust regulation, digital economy governance, and data science, aiming to equip them with the knowledge and tools needed to address monopolistic and discriminatory practices in the platform economy.