Picture a metro dispatcher seeing on the dashboard that in one hour, the 'Sportivnaya' station is expected to have an 85% surge due to a concert. They have 45 minutes to reroute an extra train and boost staff. This is reality with our AI system for passenger flow forecasting. We have developed and implemented such solutions for bus depots, subways, and railway operators. Forecast accuracy directly impacts operational costs: reduced downtime, optimal scheduling, and decreased overtime. Our models achieve MAPE 8-12% for a 1-hour horizon — 2-3 times more accurate than classical statistical methods. We take into account seasonality, weather, city events, and network topology. For example, on one station we reduced overtime by 30%, saving about 2 million rubles per year. The system pays for itself in an average of 6 months, delivering net savings from 1.5 million rubles annually.
Main Forecasting Tasks
- Optimize headways: when a peak is expected, the system recommends reducing the interval from 3 to 1.5 minutes.
- Schedule staff: flow forecasts per station allow calculating the number of cashiers and inspectors per shift.
- Prevent overcrowding: early warning 60-90 minutes before an anomaly.
How We Build Models
We use a combination of gradient boosting (LightGBM) and graph neural networks (GNN) for metro. For buses and railways, LightGBM with rich feature engineering is often sufficient.
# LightGBM with rich feature set features = { # Lags 'passengers_lag_15min': passengers_t_minus_1, 'passengers_lag_1h': passengers_t_minus_4, 'passengers_same_time_yesterday': passengers_same_period_yesterday, 'passengers_same_time_last_week': passengers_same_period_week_ago, # Time 'hour': hour, 'minute': minute, 'day_of_week': dow, 'is_holiday': holiday_flag, 'month': month, # External 'weather_rain': rain_intensity, 'temperature_c': temperature, 'stadium_event_distance_time': event_proximity_score, # Station/route 'station_type': encode(terminal_transfer_intermediate), 'line_id': line_embedding } Why Graph Neural Networks Are Effective for Metro
In metro, flow at one station strongly depends on neighboring stations — passengers transfer, a line closure redistributes load. GNN models this dependency explicitly, yielding a 2-3% MAPE gain at peak hours. LightGBM processes data 10x faster than GNN during training, but GNN consistently wins on tasks with explicit network structure. Certified engineers with over 5 years of experience tune hyperparameters for each project.
More about graph neural networks
GNNs are trained on a network graph where nodes are stations and edges are interstations. We use convolutional layers (GCN) to aggregate neighboring flows. This allows modeling passenger redistribution during disruptions. For large networks (100+ stations), we use mini-batches and neighbor sampling.Compare accuracy of different approaches on one dataset:
| Model | MAPE (1 hour) | Training (1M records) | Graph network awareness | Data requirements |
|---|---|---|---|---|
| LightGBM | 8-12% | 2 min on CPU | No | AFC + external |
| GNN | 6-10% | 30 min on GPU | Yes | AFC + graph + >6 mo |
| Temporal Fusion Transformer | 7-11% | 1 hour on GPU | Optional | Large data |
| Data source | Type | Frequency | Impact on accuracy |
|---|---|---|---|
| AFC transactions | Time series | 5-15 min | Primary |
| CCTV counts | Video | 1 hour | +5-10% MAPE |
| Weather | External | 1 hour | +2-3% MAPE |
| Event calendar | External | As needed | +10-15% MAPE at peaks |
What Does Event Awareness Provide?
Without event-awareness, the forecast on a concert day deviates by 30-50%. We add known future covariates: for planned events — a flag and duration, for anomalous ones — automatic detection via z-score. This reduces peak-hour error to 12%. Thanks to our AI forecasting system for passenger flow, we consistently achieve high accuracy even in non-standard situations. Our AI passenger flow forecasting system includes an event detection module based on LightGBM and GNN.
Typical Implementation Mistakes
- Ignoring events: without an event calendar, peak forecast error is 30-50%.
- Missing lags: flow strongly correlates with previous intervals.
- Overly complex model for small data: GNN requires >6 months of history.
Scope of Work
- Data audit: analyze AFC, CCTV, IoT sources and build ETL pipeline.
- Baseline model: LightGBM in 2 weeks with MAPE 10-14%.
- Model enhancement: if needed, GNN or TFT, training on GPU cluster.
- Integration: control center dashboard with heatmap, forecast API, alerts on threshold exceedance.
- Testing: A/B test on a station, compare with current methods.
- Documentation and training: feature list, usage manual, model handover.
- Support: monitor data drift, retrain monthly.
Implementation Phases: From ETL to Dashboard
- Audit and ETL: analyze sources (AFC, CCTV, IoT) and build processing pipeline.
- Baseline model: LightGBM in 2 weeks, accuracy MAPE 10-14%.
- Enhancement: if needed, GNN or TFT, training on GPU cluster.
- Integration: control center dashboard with heatmap, forecast API, threshold alerts.
- Testing: A/B test on a station, compare with current methods.
- Deployment and support: monitor data drift, retrain monthly.
Estimated Timelines
- Pilot on one station/route — 3-4 weeks.
- Full network system with GNN and dashboard — 4-5 months.
- Costs are calculated individually. Request a pilot project on one station to evaluate the effect. Get a consultation: we will help you choose the optimal solution for your transport.