Supply chain scenario planning optimisation

Applying Artificial Intelligence in manufacturing and distribution footprint studies

By Tom Mertens (bluecrux) and Marc Jacobs (Genzai), Jan- 2018

Proof-of-concept

Bluecrux has developed a supply chain network analysis tool (www.lightsoutplanning.com), to investigate for its customers the effects and sensitivities of its manufacturing and distribution footprint decisions. Nowadays supply chains use more than 1000 supply chain nodes with different input parameters and produces more than 5000 output parameters with EBITDA as a key output to analyse each scenario. In order to investigate the potential of AI algorithms to accelerate the scenario analysis phase, bluecrux asked Genzai to apply artificial intelligence solutions. With these amounts of scenarios, the main objective was to accelerate the identification process for the key influencing input parameters which lead to the optimum EBITDA results of the model.

The approach

We started with an understanding of the underlying data-structures and the data-preparation for Machine Learning and regression modelling. In the Microsoft Azure Machine Learning environment, we tested 5 different regression models: linear, Bayesian, Neural Network, Decision Forest and Boosted Decision Tree. Using 90% of the scenarios we trained the 5 models to predict EBITDA, and compared the accuracy of the predictions with the final 10% of scenarios. Next to predicting the EBITDA outcome, we focused on the reliability and accuracy  of the prediction: with 600 inputs and 2,000 scenarios, do we have sufficient data to achieve a high predictability of the outcome?

First outcomes

During the first iteration, the Boosted Decision Tree algorithm resulted in the best outcome, and we could determine the ranking of 600 inputs based on their influence. Although the ranking top-10 was immediately recognised as very relevant by the bluecrux network optimising engineers, the evaluated accuracy of the prediction was low: 0.43. We had too few scenarios, or too many inputs, to make reliable predictions. From their experience, bluecrux engineers were missing some important inputs that the model did not detect.

Cascaded approach

To improve reliability, we decided on a cascaded approach. The 100 highest ranking inputs of the first iteration were used to create an additional 2,000 scenarios, with the idea to increase the number of scenarios and reduce the number of inputs to be investigated. The second iteration showed scenarios with less spread, indicating a denser set of inputs. The additional scenarios were fed into the trained Boosted Decision Tree algorithm. The final accuracy of the EBITDA prediction improved to 0.84, where the model created a new ranking of most important inputs. The final 20 best inputs are now used by bluecrux engineers to complete the optimization of the supply chain network for its customer.

Learnings

AI algorithms can accelerate (from weeks down to hours) labour-intensive scenario-analyses.

A critical human mindset remains vital: the measured accuracy of an algorithm can be used to determine if you have sufficient data in order to apply your learnings, or if you need to continue digging deeper before deriving conclusions.

The cascaded approach, where man and machine take alternating turns, leads to faster results which are also recognised and trusted by the engineers. The AI algorithms have assisted the bluecrux engineers in achieving more accurate and faster manufacturing and distribution footprint results for its customers.

Bluecrux (www.bluecrux.com) is a Belgium based consultancy supporting and advising logictics and manufacturing companies.

 

Genzai (www.genzai.nl) is a Netherlands based advanced-analytics consultancy, applying artificial intelligence solutions with customers in their day-to-day operations.

 

 


Related Projects