Predictive Supply Risk Management (p-SRM)

Tredence’s predictive Supply Risk Management (p-SRM) data model contains both internal (SAP ERP or MES data) and external (weather, social media, or port congestion) data to deliver near-real-time visibility into at-risk in-transit shipments and downstream impacts, has risk prediction models that account for both internal and external factors, and exploits prescriptive analytical models and simulation layers to help mitigate the supply chain risks.

It has 70% pre-built code deployed on AWS, which helps accelerate the development and deployment of the solution. SCCT uses native Glue (PySpark) and runs on Spark clusters that easily scale to process millions of records in minutes. It uses various AWS services like S3, Redshift, Athena, Lake Formation, Kinesis (real-time), etc., required to develop, deploy, manage, and maintain the necessary predictive models and leverage the potential of AI and ML. The combination of Tredence’s supply chain domain expertise, AWS’ data processing speeds, and AWS SageMaker ML capabilities provides a winning combination.

Predictive Supply Risk Management engine uses ML algorithms and various internal and external data sets to accurately predict delays and disruptions in inbound shipments (including raw materials and SKUs), so that businesses can have agility to mitigate supply chain risks. It uses the following tools:

Inbound Order Delay accurately predicts the inbound ETA of all inbound potentially delayable purchase orders due to various internal and external factors, and that determines downstream impact.

Near Realtime Shipment Tracking provides near real-time visibility to all your inbound and purchase orders, with alerts to flag potential delays.

Stockout Risk Prediction allows the sourcing team to proactively identify which materials are at risk of running out due to macro and operational supply disruptions in advance so that mitigation steps can be taken.

Dynamic Inventory Planning uses a dynamic inventory planning engine for optimal stock plan recommendations.

Dynamic Sourcing and Fulfilment Downstream Prescriptive Modules that Help to Optimize Identify alternate sourcing or alternate DC fulfilment orders based on material availability and cost optimization to reduce the impact of delays.

Delivering real-world value

A recent client, one of the largest CPG companies, was experiencing disruptions in supplies due to multiple supply chain challenges, which were causing stockouts. The sourcing team worked to proactively identify where stock-out materials risk existed due to macro and operational supply disruptions that could be mitigated.

Tredence deployed an easy-to-consume supply risk monitor with the following capabilities and components:

• Predict the lead time considering: 1) Operational aspects include quality, order attributes, and vendor attributes. 2) External disruptors include extreme weather, port congestion, traffic, and other supply chain disruptors.

• Calculate the stockout probability score (SPS) to assess the risk using the below two inputs: 1) Item metrics 2) Dynamic market risk