<![CDATA[This study proposes a data-driven approach to estimate passenger volume and revenue for new rail transit lines under construction, addressing the challenge of limited historical data. Principal Component Analysis (PCA) was used to reduce 29 demographic variables into three principal components, which collectively captured up to 85% of the variance. These components informed a Fuzzy C-Means (FCM) clustering process that grouped new stations with existing ones based on demographic similarity. The clustering yielded a Fuzzy Partition Coefficient (FPC) of 0.913, indicating high cluster validity and low overlap between clusters. Transition probabilities of passenger flows between stations were modeled using Markov Chains. The expanded transition matrix, incorporating new stations through demographic analogy, demonstrated rapid convergence to a stationary distribution within 5–10 iterations, validating the model’s stability. Simulation results project a 57% increase in weekday passengers and a 74% increase in weekend passengers, with estimated daily revenue peaking at Rp1.216 billion. The evaluation results confirm the robustness and reliability of the combined FCM–Markov model for long-term passenger and revenue forecasting in new transit infrastructure planning.]]>
Copyrights © 2025
