This chapter introduces a novel framework for detecting discriminatory pricing within digital platform economies, particularly in the ride-hailing sector. Building upon the economic foundations of price discrimination, it explores the intersection between differentiated pricing and antitrust regulation, emphasizing the challenges of identifying algorithmically driven discrimination under opaque pricing mechanisms. To address these issues, we propose the Dual Pricing Model Clustering (DPMC) framework, which formulates discriminatory pricing detection as an unsupervised anomaly detection task. DPMC simultaneously learns two pricing models representing discriminatory and non-discriminatory behaviors and employs an iterative “model-learning⋄ data-clustering” process to distinguish between them. The framework further incorporates a pseudo-pricing augmentation strategy to mitigate data imbalance, enhance robustness, and improve detection accuracy across diverse scenarios. Extensive experiments on simulated ride-hailing datasets demonstrate that DPMC significantly outperforms mainstream anomaly detection algorithms and maintains superior stability under varying markup ratios, discriminatory proportions, and data conditions. Beyond its empirical performance, DPMC exhibits three salient properties essential for large-scale regulatory applications: insensitivity to currency systems, adaptability to evolving platform pricing strategies, and scalability across multiple industries such as e-commerce and food delivery. By providing a generalizable, data-driven approach to detecting algorithmic price discrimination, this framework offers regulators a powerful analytical tool for strengthening antitrust oversight and promoting fairness and transparency in digital marketplaces.