predictive-logistics-developer

Compare original and translation side by side

🇺🇸

Original

English

🇨🇳

Translation

Chinese

Predictive Logistics Developer

预测物流开发者

When to Use

适用场景

Build demand forecasts at SKU, location, lane, or network-node granularity with logistics-aware features
Design inventory positioning and safety stock model interfaces that feed planning and execution systems
Predict ETA, lead time, and transit time distributions from operational and external signals
Forecast capacity, congestion, and throughput for nodes, lanes, and facilities at integration level
Integrate route and network flow predictions with TMS/WMS/OMS—not full VRP solver implementation
Model cold chain, perishables, and shelf-life constraints in forecast and positioning logic
Encode promotions, seasonality, and calendar effects for logistics demand and capacity
Run backtests, monitor drift, and score models against fill rate, OTIF, WMAPE/MAPE, and service KPIs
Define feature stores, inference contracts, and batch/real-time scoring pipelines for logistics ML

结合物流相关特征，构建SKU、地点、线路或网络节点粒度的需求预测模型
设计可对接计划与执行系统的库存布局和安全库存模型接口
基于运营与外部信号预测ETA、提前期和运输时间分布
在集成层面预测节点、线路和设施的运力、拥堵和吞吐量
将路线与网络流量预测结果与TMS/WMS/OMS集成——而非完整实现VRP求解器
在预测与布局逻辑中纳入冷链、易腐货物和保质期约束
为物流需求与运力编码促销、季节性和日历效应
针对订单满足率、OTIF、WMAPE/MAPE及服务类KPI运行回测、监控漂移并为模型打分
为物流ML定义特征库、推理契约和批量/实时评分管道

When NOT to Use

不适用场景

Pure OR/MIP formulation and solver implementation without logistics prediction scope →
```
operations-research-algorithm-developer
```
Supply chain strategy, RFQ, supplier scorecards, or inventory policy governance without ML build →
```
supply-chain-manager
```
WMS workflows—waves, pick paths, RF scanning, slotting application logic →
```
wms-developer
```
Fleet telematics ingestion, map matching, or geospatial pipeline engineering →
```
geospatial-telematics-developer
```
Generic ML experimentation, causal inference, or MLOps without logistics domain framing →
```
data-scientist
```
EDI/X12 mapping, AS2, or partner document translation →
```
edi-engineer
```
Warehouse dimensional modeling or dbt mart design without prediction modeling →
```
analytics-data-engineer
```

无物流预测范围的纯运筹学/混合整数规划（OR/MIP）公式与求解器实现 →
```
operations-research-algorithm-developer
```
无ML模型构建的供应链战略、报价请求（RFQ）、供应商评分卡或库存策略治理 →
```
supply-chain-manager
```
WMS工作流——波次、拣选路径、RF扫描、货位分配应用逻辑 →
```
wms-developer
```
车队远程信息处理采集、地图匹配或地理空间管道工程 →
```
geospatial-telematics-developer
```
无物流领域框架的通用ML实验、因果推断或MLOps →
```
data-scientist
```
EDI/X12映射、AS2或合作伙伴文档转换 →
```
edi-engineer
```
无预测建模的仓库维度建模或dbt集市设计 →
```
analytics-data-engineer
```

Related skills

Need	Skill
LP/MIP, VRP, scheduling optimization	`operations-research-algorithm-developer`
SCM strategy, forecast process, supplier QBRs	`supply-chain-manager`
WMS application and ERP/WMS integration	`wms-developer`
GPS/telematics streams and spatial ETL	`geospatial-telematics-developer`
Partner EDI and order/shipment documents	`edi-engineer`
General ML, A/B tests, MLOps patterns	`data-scientist`
BI dashboards and KPI storytelling	`bi-analyst`
Feature pipelines and warehouse modeling	`analytics-data-engineer`

需求	技能
LP/MIP、VRP、调度优化	`operations-research-algorithm-developer`
供应链管理（SCM）战略、预测流程、供应商季度业务评审（QBRs）	`supply-chain-manager`
WMS应用与ERP/WMS集成	`wms-developer`
GPS/远程信息处理流与空间ETL	`geospatial-telematics-developer`
合作伙伴EDI与订单/发货文档	`edi-engineer`
通用ML、A/B测试、MLOps模式	`data-scientist`
BI仪表盘与KPI可视化	`bi-analyst`
特征管道与仓库建模	`analytics-data-engineer`

Core Workflows

核心工作流

1. Scope and problem framing

1. 范围与问题定义

Clarify horizon, granularity, decision consumer, and operational KPI contract.

See
references/predictive_logistics_scope.md
.

明确预测周期、粒度、决策使用者及运营KPI契约。

详见
references/predictive_logistics_scope.md
。

2. Demand forecasting and features

2. 需求预测与特征工程

Build SKU/location/lane demand models with logistics calendars, promotions, and hierarchy reconciliation.

See
references/demand_forecasting_and_features.md
.

结合物流日历、促销活动和层级协调，构建SKU/地点/线路需求模型。

详见
references/demand_forecasting_and_features.md
。

3. Inventory and network positioning

3. 库存与网络布局

Connect forecasts to positioning, safety stock interfaces, and multi-echelon handoffs.

See
references/inventory_and_network_positioning.md
.

将预测结果对接至库存布局、安全库存接口及多级递阶交付流程。

详见
references/inventory_and_network_positioning.md
。

4. ETA, lead time, and capacity

4. ETA、提前期与运力

Model transit times, node congestion, and capacity signals for planning and execution.

See
references/eta_leadtime_and_capacity.md
.

为计划与执行系统建模运输时间、节点拥堵和运力信号。

详见
references/eta_leadtime_and_capacity.md
。

5. Evaluation and monitoring

5. 评估与监控

Backtest against operational KPIs; track drift, bias, and forecast value.

See
references/model_evaluation_and_monitoring.md
.

基于运营KPI进行回测；跟踪漂移、偏差及预测价值。

详见
references/model_evaluation_and_monitoring.md
。

6. Operations integration

6. 运营集成

Wire scores to OMS/TMS/WMS, planning cycles, and human-in-the-loop overrides.

See
references/integration_with_operations.md
.

将模型评分对接至OMS/TMS/WMS、计划周期及人工介入覆盖流程。

详见
references/integration_with_operations.md
。

Outputs

输出成果

Problem brief — granularity, horizon, consumers, KPI targets, and non-goals
Feature catalog — definitions, freshness SLAs, leakage checks, and hierarchy keys
Model card — training window, metrics (WMAPE/MAPE, bias), segments, and known failure modes
Backtest report — rolling-origin results tied to fill rate, OTIF, or inventory service proxies
Inference contract — schema, latency, batch cadence, fallback rules, and version pins
Monitoring runbook — drift thresholds, retrain triggers, and escalation to planning ops

问题简报 —— 粒度、周期、使用者、KPI目标及非目标
特征目录 —— 定义、新鲜度SLA、数据泄露检查及层级键
模型卡片 —— 训练窗口、指标（WMAPE/MAPE、偏差）、细分场景及已知失效模式
回测报告 —— 与订单满足率、OTIF或库存服务指标关联的滚动原点测试结果
推理契约 —— schema、延迟、批量频率、fallback规则及版本固定
监控手册 —— 漂移阈值、重训触发条件及向计划运营团队的升级流程

Principles

原则

Optimize for operational KPIs, not only statistical accuracy — tie WMAPE to service and inventory outcomes
Respect logistics calendars — lead times, cutoffs, carrier schedules, and promotion lift are first-class features
Prevent leakage — exclude post-decision signals; align train labels to information available at forecast origin
Reconcile hierarchies — bottom-up vs top-down consistency for SKU × location × lane stacks
Separate prediction from optimization — deliver distributions and interfaces; route MIP/VRP to OR peers
Monitor in production — drift, bias by lane/node, and forecast value beat one-time offline accuracy
Document override paths — planners and TMS rules may supersede scores; model serving must degrade safely

以运营KPI为优化目标，而非仅追求统计准确性——将WMAPE与服务及库存结果挂钩
遵循物流日历 —— 提前期、截止时间、承运商日程及促销提升是核心特征
防止数据泄露 —— 排除决策后信号；使训练标签与预测时点可获取的信息保持一致
协调层级关系 —— SKU×地点×线路组合的自下而上与自上而下一致性
区分预测与优化 —— 输出分布结果与接口；将路线MIP/VRP任务交给运筹学同事
生产环境监控 —— 漂移、按线路/节点划分的偏差及预测价值优于一次性离线准确性
记录覆盖路径 —— 计划人员与TMS规则可能覆盖模型评分；模型服务需具备安全降级能力

When to load references

何时查阅参考文档

Topic	Reference
Role scope, boundaries, RACI	`references/predictive_logistics_scope.md`
Demand features, seasonality, promotions	`references/demand_forecasting_and_features.md`
Safety stock, positioning, multi-echelon	`references/inventory_and_network_positioning.md`
ETA, lead time, capacity signals	`references/eta_leadtime_and_capacity.md`
Backtesting, WMAPE, drift, KPIs	`references/model_evaluation_and_monitoring.md`
OMS/TMS/WMS integration, cadence	`references/integration_with_operations.md`

主题	参考文档
角色范围、边界、RACI职责	`references/predictive_logistics_scope.md`
需求特征、季节性、促销活动	`references/demand_forecasting_and_features.md`
安全库存、布局、多级递阶	`references/inventory_and_network_positioning.md`
ETA、提前期、运力信号	`references/eta_leadtime_and_capacity.md`
回测、WMAPE、漂移、KPI	`references/model_evaluation_and_monitoring.md`
OMS/TMS/WMS集成、频率	`references/integration_with_operations.md`