AI applications in Supply Chain

In Goals for supply chain information technology we described the four IT goals:

1.      Collect information on each product from production to delivery or purchase point, and provide complete visibility for all parties involved.

2.      Access any data in a system from a single point of contact

3.      Analyze, plan and make trade-offs based on information from the entire supply chain

4.      Collaborate with supply chain partners

Here we focus on data analysis and planning which has become more pertinent due to the much faster pace of change in many industries. Traditionally analytics was done either with off the shelf software or using Excel spreadsheets. Custom solution development was often slow and cumbersome making it hard to bring in new techniques and innovations.

There have been two major information technology developments related to analytics. First, the growing use of machine learning with new languages such as R and Python providing strong built in capabilities. Second, the ease of deploying cloud computing through Amazon Web Services, Microsoft Azure and other providers. This enables flexible access to diverse data, scaleable computing power and the ability to run large analytics models.

The terms Machine Learning, Artificial Intelligence (AI) and Cognitive computing are vying to describe the advanced capabilities that can now be applied to different aspects of supply chain and operations. We will try to differentiate the terms but they all point to the same type of data processing and are often used interchangeably. 

AI typically refers to machines that can learn, reason, and act for themselves. They can make their own decisions when faced with new situations, in the same way that humans and animals can. As it currently stands, the vast majority of the AI advancements and applications you hear about refer to a category of algorithms known as machine learning. These algorithms use statistics to find patterns in massive amounts of data. They then use those patterns to make predictions on things like what shows you might like on Netflix or whether you have cancer based on your MRI. In Prediction Machines three eminent economists recast the rise of AI as a drop in the cost of prediction. When AI is framed as cheap prediction, its extraordinary potential becomes clear as prediction is at the heart of making decisions under uncertainty, with which supply chain practitioners are very familiar.

Machine Learning enables researchers, data scientists, engineers and analysts to construct algorithms that can learn from and make predictions based on data. Rather than following a specific set of rules or instructions, an algorithm is trained to spot patterns in large amounts of data. Deep learning takes this idea further, processing information in a layered structure of algorithms called an artificial neural network which is inspired by the biological neural network of the human brain.

The integration of predictive (AI) and prescriptive (stochastic and deterministic optimization) is referred to as intelligent or cognitive systems. These systems while similar to AI are typically more prescriptive – they can help decide what to do not only predict what will happen. For instance using machine learning and optimization as in Price Optimization can provide the best solution based on strong prediction while optimizing goals such as profit maximization and constraints such as promotional budgets. Another example is a transportation system that takes in data from various sources (weather, routes, forecasts) and recommends actions based on this information through use of AI and planning parameters as described in How UPS uses AI,.

There are many opportunities to apply AI in supply chain and operations. Some examples:

• Planning: AI provides improved forecasting which is always needed for better planning and execution. An example of use of AI with supply chain planners is Merck introduces automation to supply chain
• Risk: AI help companies identify and mitigate risk - IBM uses extensive weather and other data with AI technology.
• Internet of Things:- AI helps identify patterns and detect anomalies in the data that smart sensors and devices generate: AI is often used for predictive maintenance and operational efficiency.
• Robotics:  From the manufacturing floor, warehouses to transportation AI has expanded the opportunities to automate labor intensive and dangerous tasks such as intelligent robotic sorting. An important application in transportation is self driving trucks.
• Visuals: Ability to process scanner pictures, drone images and process for damage or faults as in critical inspection.

AI is one of the three main new technologies that are having a large impact on supply chain and operations. The other two are Internet of things often using RFID which introduces the wide use of sensors providing real time data and visibility. Blockchain which enables unconnected parties to collaborate across the supply chain. Together they provide new capabilities to work towards achieving the four supply chain goals.