Predicting the risk of mission failure for leading pharmaceutical supply chain management solution
The modulai team applied a set of machine learning techniques to predict the risk of failure of shipments of sensitive pharmaceutical goods.
The models were based on time series and auxiliary data from hundreds of thousands of historical missions. The approach developed can be used to optimize choice of packaging solution and transport route as well as being a basis for a warning system notifying the operators of increased risk of failure along the way.
This client is one of the world’s leading providers of solutions for tracking sensitive shipments of pharmaceutical goods throughout the supply chain. Each shipment is tracked minute-by-minute by a temperature logger, and at mission end the shipment is rejected if the goods has been exposed to prolonged temperatures above certain thresholds. Their system store temperature time series data for hundreds of thousands of shipments to destinations all over the globe.
The Modulai team used bayesian regressions to estimate the distributions in shipment max and mean kinetic temperatures, tree ensemble models to build classifiers for probability point estimates and Deep neural networks for ahead of time predictions of the timeseries.
Preprocessing, modeling and validation flows were developed in Python with data fetched from a relational database, and the final solution was deployed in a web-app for showcasing and internal use. Deep learning architectures were developed in pyTorch and Tensorflow.
The final solution was deployed in a web app for showcasing and internal use.