Supply chain optimization practices focus on leveraging available data within your ecosystem to make smarter business and operations decisions. Organizations also use this data to make their supply chains more sustainable and eco-friendly. Traditionally, this data has typically been consolidated within enterprise resource planning (ERP) tools. ERP system supply chain integration has been a hot topic for years as companies seek to merge far-flung data into a single platform in order to achieve seamless analytics and increase efficiency.
Now, a new option that leverages advanced machine learning techniques for predictive analytics is coming on the scene, ushering in a new wave of innovation in supply chain optimization.
As presented at the recent AspenTech Optimize conference, ML-rich techniques can be applied to operations like manufacturing execution systems (MES) to collect more detailed data than ever before. Automated MES can deliver meaningful intelligence that showcases how long it takes to manufacture a product, how often your manufacturing equipment breaks down and how much scrap you produce in the process – down to the part level.
Case Study: Machine Learning for Customer Satisfaction
One of the case studies presented at Optimize looked at how an automotive manufacturing company used ML-based predictive analytics to overcome countless barriers throughout a difficult year in the automotive sector. Working with Profit Point and AspenTech, the company was able to wrestle with a vast dataset to alert customers to manufacturing delays connected to circumstances outside of their control.
By interpreting the external data and applying it to their cycle time for product development, the manufacturer was able to predict new timelines. They also predicted issues like mechanical failures, cycle time delays or poor raw material quality to notify customers early and offer a recommended course of action. Despite a pandemic, chip shortage and oxygen scarcity, the manufacturer was able to maintain a high-level of customer confidence and profitability throughout a hectic time for all.
Case Study: Supply Chain Sustainability
We also heard from a spokesperson from the European Commission on Energy, who works in the petroleum industry. Most petrol companies use linear processes that go from creation to use in the field, to the dump. The Commission is looking to add machine learning to their supply chain optimization policy plans to get recycling inserted into existing processing streams.
It was interesting and inspiring to hear about the Commission’s goals using emerging technology. As Nilgun reviewed in her article outlining 7 steps to achieve a more sustainable supply chain, success in sustainability largely depends on establishing and sticking to policies and procedures.
The presentation also reminded me of the work we did years ago for a client who wanted to recycle old appliances. This organization collected the appliances, shredded them and then recycled them into raw materials that could be sent to the smelter and made into something completely new, meaningful and profitable.
Machine Learning’s Impact on People, Process and Technology
Now that we know this technology exists, the question remains: what are we going to do with it? Once we understand the end goal, we can manipulate it to achieve the desired outcome. But even before we get here, it’s important to consider how to take any initiative from simply successful to sustainable.
We always encourage our clients that the goal should be to establish a system that will survive their tenure at the company. This way of thinking often involves additional steps and tasks beyond simply adopting a new technology platform. It requires wholesale change for the company’s culture, employee expectations and tools. This is by necessity a multi-pronged approach that should be considered and implemented thoughtfully to guide change management toward a new way of working.
We want to help you through this process and have decades of experience helping customers achieve meaningful change. Learn more about our 5-step approach to sustained supply chain optimization.