Reclamation minimization

Fortune telling with accuracy

Customer reclaims stemming from shipping out items is a significant factor for all manufacturers. Therefore, minimizing the probability of customer reclaims is of major importance.

Based on test and reclaim data, we created a machine learning model able to predict future customer reclaims with approximately 80% accuracy.

Our tools of wizardry

The analysis addresses the following questions:

• Measurements, diagnostics, and repair of signal processing and radio frequency modules are currently time-consuming and expensive. Is it possible to cut costs by building a decision aid for diagnostic technicians that will shorten repair times?
• What are the patterns in diagnostic measurement results that provide predictive insight into potential faults and future claim returns from customers?

Our predictive models were suspiciously powerful with nearly 80% precision. A reverse causality case was uncovered: received claim cases undergo different measurement procedures. By removing the measurements that were done after a claim date, the picture became more realistic.

There are no obvious predictors of claims, rather hundreds of subtle ones that accumulate to form one strong predictor.

Results

• Classifier built which predicts future customer claims.
• Process improvement recommendations provided.
• Measurements optimally sequenced to reduce assembly time required.