Early detection of delivery delays
How a predictive model over delivery, customer and production data identified which factors were actually causing late deliveries, and what targeted stock optimisation did about them. Prospero does not name the manufacturer.
Knowing which factor to act on
Consistent late delivery costs money twice, in the direct cost and in the customer relationship. The work here was not to predict the delay but to identify what was causing it, so that a change could be aimed rather than guessed.
At a glance
- Sector
- Manufacturing
- Solution
- DetectX® Business Monitoring
- Customer
- Not published
- Location and date
- Germany based, with global reach. No date published
The story, as Prospero publishes it
The business challenge
Late deliveries, and the cost on both sides of them
- The Germany based manufacturer with global reach was grappling with additional costs and customer dissatisfaction stemming from consistent delivery delays.
The solution
Find the factors, from all the data already held
- Using predictive analytics and the DetectX® Business Monitoring solution, Prospero were able to identify the relevant factors for delay in delivery on the basis of all the available delivery and customer data, for example production details and input material stock levels.
The results
Stock optimised where it mattered, delays down 27 percent
- The manufacturer was able to take direct action for improvement by acting on the insight the model provided, knowing which factors were most relevant in causing the delays. Targeted stock optimisation based on those insights resulted in a reduction of delivery delays by 27 percent. The live page reports cost savings and increased customer satisfaction alongside that figure, and quantifies neither.
What the model returned
One figure, what the model reads, and what the source leaves unmeasured. The 27 percent is the only measurement on the source page, and it is attached to no named institution.
Published result
27% fewer delays
The reduction in delivery delays after targeted stock optimisation, as Prospero states it. No baseline, period or measuring party is published.
Data already held
The model was built from the delivery and customer data the manufacturer already had, including production details and input material stock levels.
Stock, not schedule
The action taken on the insight was targeted stock optimisation. The source names no other change, and quantifies neither the cost savings nor the customer satisfaction it reports alongside the 27 percent.
There is no customer quotation on this page because the source has none. The source also describes this customer in two different ways, as a Germany based manufacturer on the case study and as a global stationery company on the index, and this page does not pick between them.
Where to look next
The sector page for work outside financial services, the platform the model was built on, and the two other manufacturing studies.
- Beyond financial services
- Where DetectX® is applied outside banking and insurance.
- DetectX® platform
- The predictive analytics layer these models are built on.
- Optimisation of production planning
- The same module, forecasting sales volume instead of finding delay factors.
- Process optimisation in aluminium company
- An early warning model on input data measured before the production run.