🎯
Business Objectives
- ›Maximize yard throughput
- ›Prevent overflow and weekend fees
- ›Balance load across yards
⚙️
Operational KPIs
- ›Utilization %
- ›Avg dwell
- ›Gate throughput / day
📈
Management KPIs
- ›Cost per stored vehicle
- ›Overflow events
🤝
Customer KPIs
- ›Time-to-ready
🗄️
Available Data
- ›Yard capacity
- ›Gate-in / gate-out events
- ›Current inventory
- ›Dwell per vehicle
✨
AI Use Cases
- ›Capacity forecasting
- ›Yard routing optimization
- ›Gate congestion prediction
🔮
Predictive Analytics
- ›Expected utilization 7 days ahead per yard
- ›Predicted gate wait time
🚨
Anomaly Detection
- ›Sudden dwell spike
- ›Gate throughput drop
🎁
Recommendation Engines
- ›Redirect inbound to under-utilized yard
- ›Recommend staffing shifts
🤖
AI Copilot Features
- ›'Where should the next 12 inbound vehicles go?'
💬
Natural-Language Reporting
- ›'Gate-in vs gate-out by yard this week'
📊
Executive Dashboard Metrics
- ›Util per yard, dwell heatmap, overflow risk
⚡
Workflow Automation
- ›Auto-redirect inbound when yard > 90%
🛰️
Autonomous Agents
- ›Yard Balancer Agent recommends and executes redirects
🖥️
Recommended Dashboards
- ›Capacity & Throughput
- ›Yard SLA
💡
Example Executive Insights
- ›Yard 03 at 99% — redirect 12 vehicles to Yard 07 saves $3.4k/wk
- ›Yard 03 dwell +44% — root cause: driver shortage on PHX lane
📦
Required Datasets
- ›yards
- ›gate_events
- ›vehicle_status_history
📅
Historical Data Needed
12–24 months
🧠
ML Models / AI Approaches
- ›Prophet for capacity forecast
- ›Linear programming for routing