Analytics is increasingly playing a prominent role in the world of Supply Chain. It bridges the gap between the physical, information, and financial flows.

Organizations can increase functional integration within their supply chain operation by adopting data analytics that processes data into information.

Being a sub-function within Supply Chain, this also applies to procurement, meaning that procurement also has and will generate considerable value by leveraging data.

To provide an overview of what analytical techniques are leveraged within procurement, I will use the three widely known categories of analytics. Please note that these are just examples and obviously not exhaustive lists.

• Descriptive
• Predictive
• Prescriptive

Descriptive

Descriptive analytics processes historical data to provide information highlighting past events and issues requiring intervention. Examples from a procurement perspective include:

• Product availability issues and stockouts
• Customer returns by stock-keeping units (SKUs)
• Inventory markdowns or write-offs by SKUs
• Products returned to suppliers
• Quality issues by SKU and Suppliers
• Product lead times
• Customer complaints

Note that the real enhancement of the information comes from how it is generated and shared within the organization. That is where procurement visibility tools play a significant role. Sharing this information electronically with the organization’s supplier base, who can then introduce corrective actions based on the feedback generated by descriptive analytics, can help create an agile procurement process.

Predictive Analytics

This form of analytics uses historical data combined with statistical tools and techniques to analyze the data searching for patterns, relationships, and trends within the data that can be used to help predict future outcomes. This information can be beneficial for procurement decisions.

Examples

• If there was a positive relationship between the weather and product volumes, information captured from weather forecasts can be used to place orders with suppliers.
• Analyzing Point of Sales data can reveal an unexpected relationship between different product categories within a retail outlet and provide opportunities to develop promotions or relocate them together to improve customer experience
• The relationship between the time of the day and the type of product purchased is significant for procurement professionals to ensure product availability and replenishment, for example, a lunchtime meal deal with three different items.

Prescriptive Analytics

Prescriptive analytics can enhance procurement decisions by using data to develop simulation models, which can then be used to optimize future scenarios.

Examples

A procurement decision can be taken to change the mode of transport for the primary inbound distribution between a supplier based in Europe and the buyer in the UK from road freight to one based on intermodal using rail. The impact on cost, lead time, service levels, safety stock calculations, customer service, and environmental factors would all need to be derived before deciding to proceed with the change.