Passenger assistance services are essential for accessible rail travel, yet demand varies substantially across stations and over time, creating challenges for workforce planning and staff rostering. This paper presents a data-driven decision support framework for forecasting station-level passenger assistance demand and translating forecasts into workforce plans. The forecasting component applies a horizon-aware Prophet modelling approach using multi-source operational data, while the planning component maps demand forecasts to staffing requirements under service and operational constraints through an interpretable red-amber-green risk framework. The approach has been implemented within a production-grade system to support routine planning and staffing decisions across LNER-managed stations. Results demonstrate improved forecast accuracy relative to year-on-year baseline methods, with absolute error reduced by up to 76.9%, and show that forecast-informed staffing is associated with an approximate 50% reduction in failed passenger assistance deliveries attributable to staff availability. These findings highlight the value of integrating interpretable forecasting with operational work.
Figures & tables
Figure 1: Station-level passenger assistance requests over the last four years, illustrating strong seasonality and peak demand periods.
Figure 2: Cumulative distribution of passenger assistance booking lead times.
Planning horizon
Responsible role/team
Typical duties
8–12 weeks ahead
Strategic / resource planning
Coordinate timetable and works impacts; set high-level station allocations; plan recruitment to close gaps.
2–4 weeks ahead
Roster clerks / accessibility planning teams
Build rosters aligned to expected demand; manage leave, training, and planned overtime.
Less than 1 week ahead
Service delivery & Station managers
Deploy staff day to day; approve short-notice overtime or rest day working
• As-of booking counts at coarse thresholds ( τ≥8 weeks)
Table 2: Horizon-bucket routing and horizon-specific regressor availability.
Figure 3: Forecast error across horizon buckets for representative stations at hourly (left) and daily (right) resolutions. Solid lines denote asymmetric RMSE and dashed lines denote MAE.
Station
Horizon (days)
MAE
aRMSE
Coverage (%)
Berwick-upon-Tweed
Baseline (YoY)
Baseline
4.8
7.7
100.0
Long Term
>28
3.8
6.1
100.0
Medium II Term
15–28
2.8
4.8
100.0
Medium I Term
8–14
2.4
4.1
100.0
Short Term
3–7
2.2
3.6
100.0
Table 3: Daily forecast performance by station and horizon (in days).
Station
Horizon (days)
MAE
aRMSE
Coverage (%)
Berwick-upon-Tweed
Baseline (YoY)
Baseline
1.1
2.1
98.1
Long Term
>28
0.9
1.9
99.2
Medium II Term
15–28
0.9
1.6
99.9
Medium I Term
8–14
0.8
1.4
100.0
Short Term
3–7
0.7
1.2
100.0
Table 4: Hourly forecast performance by station and horizon (in days).
Figure 4: Workforce planning RAG heatmap for York (06:00–21:00, 50 days). Green indicates forecast demand is within primary capacity; Amber indicates secondary capacity is required; Red indicates forecast demand exceeds total capacity.
Figure 5: Prophet component decomposition for York (Medium II horizon), illustrating the contribution of trend, multiple seasonalities, holiday effects, and external regressors to the final forecast.
Figure 6: Residual diagnostics for York (Medium II horizon), including the residual distribution, Q–Q plot, and residuals over time. Circled observations correspond to periods of engineering works not explicitly captured in the model.
Time series forecasting predicts future values from ordered observations using statistical, neural, and probabilistic models to support decisions under uncertainty.
Accurate and coherent passenger demand forecasting is essential for Urban Rail Transit (URT) operations. Passenger demand has a hierarchical structure in which origin-destination (OD) flows aggregate to station-level inflows and outflows through conservation constraints. In practice, station-level and OD-level forecasts are often generated independently, producing incoherent predictions that violate these constraints and introduce inconsistencies into operational decision-making. Such issues become more severe during disruptions, when forecasting reliability is most critical. This paper presents the first hierarchical forecast reconciliation framework for joint station-level and OD-level URT demand prediction. A neural Fully Connected Reconciler (FCR) learns a non-linear mapping from incoherent base forecasts to coherent hierarchical predictions while guaranteeing exact structural consistency by construction. The method is benchmarked against OLS, WLS, and Minimum Trace (MinT) variants using Rejsekort smart-card data from the Copenhagen S-train network under one-step, multi-step, and disruption forecasting scenarios. Results show that reconciliation consistently improves OD forecasting accuracy while ensuring hierarchical coherence. Under normal conditions, FCR performs competitively with MinT-based methods. An oracle analysis indicates that perfect station-level forecasts could reduce OD prediction error by up to 34 percent, highlighting the value of improved base forecasts. Under severe disruptions, FCR outperforms classical methods, reducing OD forecasting error by up to 17.45 percent in multi-step destination-side delay scenarios. These findings establish hierarchical reconciliation as an effective mechanism for improving forecast robustness, with the largest benefits occurring under the most challenging operating conditions.
Dang Viet Anh Nguyen, Alma Fazlagic, Kristine Pryds Loft +1
Department of Technology, Management, and Economics, Technical University of Denmark (DTU), 2800 Kongens Lyngby, Denmark
Accurate short-term demand forecasting is crucial to airline revenue management, yet most existing systems fail to meet this need because current models treat booking data as a single temporal dimension, either the accumulation of bookings for a specific flight or the historical booking profile of the same route. This unidimensional view discards information carried by the other temporal stream and forecasting absolute passenger counts introduces a further operational fragility when change in planned aircraft type alters total seat capacity. This study addresses both limitations. A dual-stream Long Short-Term Memory (LSTM) integrated with attention framework is proposed that simultaneously processes two complementary input sequences: a horizontal sequence capturing intra-flight booking accumulation over the days preceding departure, and a vertical sequence capturing inter-flight booking patterns at fixed days-before-departure offsets across historical flights. Multiple dual-stream architectural variants, combining self-attention, cross-attention, and hybrid attention with concatenation, residual, and gated fusion strategies, are developed and evaluated. Experiments on real-world reservation data from the national airline of Bangladesh, Biman Bangladesh Airlines (BBA), demonstrate that the proposed hybrid model achieves a Mean Absolute Error of 2.8167 and a coefficient of determination (R2) of 0.9495, outperforming single-stream baselines, tree-based models, and three prior dual-LSTM architectures applied to the same data. Validation across four flight category pairs; domestic versus international, direct versus transit, high versus low frequency, and short versus mid versus long haul confirms that the model generalizes across operationally diverse route types. Biman Bangladesh Airlines (BBA) has officially integrated this methodology into its operations.
ASM Nazrul Islam, Md. Hasanul Kabir, Md. Liakot Ali +1
Institute of Information and Communication Technology, Bangladesh University of Engineering and Technology, Dhaka, Bangladesh · Islamic University of Technology, Dhaka, Bangladesh
Accurate passenger queue forecasting in airport terminals is essential for efficient departure operations, as it enables proactive congestion management. However, time-varying passenger demand and heterogeneous facility usage across multiple departure facilities make forecasting challenging. In this work, we propose a passenger queue forecasting framework that learns historical passenger flow patterns from operational data. The proposed model employs a Transformer-based architecture to capture temporal dependencies and inter-facility correlations using past queue length and waiting time at departure gates and security checkpoints, together with passenger throughput at check-in islands. The learned representations are mapped to two facility-specific prediction heads to predict queue length and waiting time at departure gates and security checkpoints. Experimental results demonstrate accurate forecasts up to two hours ahead. The proposed approach offers practical real-time decision support for proactive queue management and staff reallocation in airport terminal operations.
Juhwan Lee, Seokbin Yoon, Keumjin Lee +2
Department of Air Transport, Transportation, and Logistics, Korea Aerospace University, Goyang, South Korea · Airport Industry Technology Research Institute, Incheon International Airport Corporation, Incheon, South Korea