The New York City subway moves millions every day, yet its delays remain a constant frustration. Current prediction systems rely heavily on manual reporting and opaque algorithms, leaving commuters in the dark and transit managers reacting rather than preventing disruptions. This groundbreaking study by Amanda M. Olachea offers a transformative alternative.
Blending anomaly detection with explainable AI, Olachea designs and tests an AI-powered dashboard that predicts subway delays with an 89% accuracy rate, surpassing the MTA's own reported performance. Unlike black-box models, this system pairs predictions with confidence scores and causal explanations, giving decision-makers both foresight and accountability.
Drawing on open MTA data, iterative modeling, and global case studies from Seoul, London, and Tokyo, the book provides a replicable blueprint for any transit agency. Beyond technical innovation, it wrestles with the ethical and governance challenges of AI in public infrastructure: transparency, equity, bias mitigation, and public trust.
Whether you're a commuter curious about the future of New York's subways, a policymaker seeking practical AI frameworks, or a technologist interested in real-world applications of machine learning, this book demonstrates how artificial intelligence can serve the public good without sacrificing accountability.
Key Features:
Real-world deployment results, with live data integration and iterative model testing
A hybrid AI architecture combining anomaly detection, supervised learning, and temporal forecasting
Ethical safeguards, fairness audits, and governance models for responsible AI in public transit
A long-term roadmap for scaling explainable AI across global infrastructure
This isn't just about predicting when the next train will arrive but to reshape public trust in the systems that move us.
