Though AI cannot yet replace people or make up for inadequate logistical capabilities, it can optimize the use of what's currently available. JL
Sarah Hunt reports in Datamation:
Big data predictive analysis is transforming the way warehouse managers handle inventory by providing insight impossible to unravel with manual, human-driven processes and self-improving forecasting loops, including how goods are loaded and unloaded from shipping containers. AI create the most efficient routes from all possibilities. Conventional approaches have been inadequate for fully analyzing the myriad route possibilities. IoT device data taken from in-transit supply chain vehicles can provide insights about the longevity of the equipment required to keep goods moving through supply chains. Machine learning makes maintenance recommendations and failure predictions.Applying artificial intelligence (AI) is one way supply chain professionals are solving key issues and improving global operations.
AI-enhanced tools are being used throughout supply chains to increase efficiency, reduce the impact of a worldwide worker shortage, and discover better, safer ways to move goods from one point to another.
AI applications can be found throughout supply chains, from the manufacturing floor to front door delivery. Shipping companies are using Internet of Things (IoT) devices to gather and analyze data about goods in shipment and to track the mechanical health and constant location of expensive vehicles and related transportation tools.
Customer-facing retailers are using AI to gain a better understanding of their key demographics to make better predictions about future behavior. The list goes on — anywhere there are goods that need to make it from point A to point B, there’s a good chance AI is being used to enhance, refine, and analyze supply chain operations.
Some of the benefits derived from AI in supply chains are less tangible than others. For example, determining the impact of predictive analytics based on supply chain data can eventually yield benefits, but some companies are reporting a direct link between revenue shifts and the addition of AI in supply chains. Recent research conducted by McKinsey & Company found that 61% of executives who have introduced AI into their supply chains report decreased costs, and more than 50% report increased revenues. More than a third of study respondents reported revenue increases of more than five percent.
An IBM article, “AI is reshaping the supply chain,” featuring Aera Technology senior engagement director Arnaud Morvan, identifies four advantages to applying AI to modern supply chain challenges:
- End-to-end visibility enhanced with near real-time data
- Actionable analytic insights based on pattern identification, at scale, far exceeding the abilities of conventional supply chain systems
- Reduced manual human work
- Informed decision making augmented by machine learning (ML), AI-driven predictions and recommendations based on analyzing multiple potential scenarios
Here, we examine some of the ways AI is used in supply chains.
5 Examples Of AI In Supply Chains
1. Demand Forecasting Is Improving Warehouse Supply And Demand Management
Machine learning is being used to identify patterns and influential factors in supply chain data with algorithms and “constraint-based modeling,” a mathematical approach where the outcome of each decision is constrained by a minimum and maximum range of limits. This data-rich modeling empowers warehouse managers to make much more educated decisions about inventory stocking.
This type of big data predictive analysis is transforming the way warehouse managers handle inventory by providing deep levels of insight impossible to unravel with manual, human-driven processes and endless, self-improving forecasting loops.
C3 AI uses AI to power its Inventory Optimization platform, which gives warehouse managers data on inventory levels in real-time, including information about parts, components, and finished goods. As the machine learning ages, the platform produces stocking recommendations based on data from production orders, purchase orders, and supplier deliveries.
2. AI Is Optimizing Routing Efficiency And Delivery Logistics
In a world where just about anything can be ordered online and delivered within data, companies that don’t have a firm handle on delivery logistics are at risk of falling behind. Customers today expect quick, accurate shipping, and they’re all too happy to turn somewhere else when a company is unable to deliver on that expectation. McKinsey & Company reports that around 40% of customers who tried grocery delivery for the first time during the COVID-19 pandemic intend to keep using these services indefinitely. Customers in major markets like New York and Chicago have dozens of choices.
Delivery logistics is a detail-oriented, challenging field. This Economist article unpacks some of this complexity, pointing to the “devilishly complex” task of delivering 25 packages by van — the number of possible routes for a single van adds up to around 15 septillion.
AI-driven route optimization platforms and GPS tools powered by AI like ORION, a company used by logistics leader UPS, create the most efficient routes from all the possibilities, a task untenable with conventional approaches, which have been inadequate for fully analyzing the myriad route possibilities.
3. Machine Learning AI Is Improving The Health And Longevity Of Transportation Vehicles
IoT device data and other information taken from in-transit supply chain vehicles can provide invaluable insights about the health and longevity of the expensive equipment required to keep goods moving through supply chains. Machine learning makes maintenance recommendations and failure predictions based on past and real-time data. This allows companies to take vehicles out of the chain before performance issues create a cascading backlog of delays.
Chicago-based Uptake uses AI and machine learning to analyze data to predict mechanical failures for a wide range of transportation vehicles and cargo containers, including trucks, cars, railcars, combines, and planes. The company uses data from IoT devices, GPS information, and data pulled directly from vehicle performance records to arrive at its predictions, which can greatly reduce downtime.
4. AI Insights Are Adding Efficiency And Profitability To Loading Processes
Supply chain management includes a great deal of detail-oriented analysis, including how goods are loaded and unloaded from shipping containers. Both art and science are needed to determine the fastest, most efficient ways to get goods on and off trucks, ships, and planes.
Companies like Zebra Technologies use a combination of hardware, software, and data analytics to deliver real-time visibility into loading processes. These insights can be used to optimize space inside trailers, reducing the amount of “air” being shipped. Zebra can also help companies design quicker, less risky, more efficient processing protocols to manage parcels.
5. Supply Chain Managers Are Uncovering Cost-Saving And Revenue-Increasing Methods With AI
Moving goods around the world is expensive, and only becoming more expensive. Bloomberg reports that the cost of moving goods by ship, for example, increased by 12% in 2020, the highest level in five years, according to the Drewry World Container Index.
Companies like Echo Global Logistics use AI to negotiate better shipping and procurement rates, manage carrier contracts, and pinpoint where changes in supply chains could deliver better profits. Users access a centralized database that takes virtually every aspect of supply chains into account to deliver financial decision-making advice.
AI in supply chain innovations are paving the way for a future where we can eventually expect to see AI-powered, autonomous vehicles used throughout supply chains. The data these platforms are mining and analyzing today will continue improving the cost and efficiency of an increasingly complicated global supply chain.
0 comments:
Post a Comment