Jaguar Land Rover and Colgate-Palmolive are among the many enterprises turning to machine learning software and other data-crunching tools to ensure supply can meet demand. Credit: Thinkstock Technologies that can help companies choreograph how they ship goods around the world are having their moment. Battling shortfalls in parts and products in the wake of a coronavirus pandemic, enterprises are turning to machine learning (ML) and other data-crunching technologies to help clear supply chain hurdles. Yes, companies mustered their way through disruptions triggered by 9-11 and the financial collapse, but nothing could have prepared them for the coronavirus pandemic, which has spurred shortages in everything from cleaning products and toilet paper to medical devices, such as ventilators critical for treating patients who have contracted COVID-19. Thirty percent of 100 supply chain executives said their companies saw decreased market share during the outbreak, while 30 percent say they saw an uptick, says Matt Lekstutis, global lead for supply chain transformation at Tata Consultancy Services (TCS), which polled 100 executives in July. “What we considered the laws of physics of supply chain have been suspended,” Lekstutis tells CIO.com. Organizations that relied on historical averages and trends to calibrate supply and demand are now seeing their data models drift. To get back on course, companies are embracing technologies such as graph databases and machine learning to recalibrate sales forecasts, anticipate and avoid machine breakdowns and make their supply chains more nimble and responsive. Auto company plots a path with graph analytics Jaguar Land Rover is one such organization using analytics to help alleviate disruptions to its sales forecasts. JLR, which makes the namesake Land Rover and Range Rover SUVs, typically relies on forecasts issued years in advance, granting hundreds of suppliers lead time to craft parts. In addition to helping JLR estimate demand, the forecasts ensure it can commit to purchase minimum buy volumes of parts. But the COVID-19 outbreak forced JLR to scrap its sales forecasts, says Harry Powell, JLR’s director of data and analytics, who told his business peers the company had to be more nimble about balancing supply and demand given the uncertainty about whether suppliers would be able to make enough of the 30,000-odd parts automotive makers require. To perform a more timely analysis of its supply chain, JLR leaned into graph database software to correlate data and identify relationships between entities across multiple complex data sources, including forecast and supply chain data, parts data and car configuration data. Graph analytics helps data scientists find unknown relationships and connections within data that are not easily discovered with traditional analytics technologies that query relational database systems. The software, from startup TigerGraph, queried data across disparate systems, including mainframe, ERP and manufacturing applications. The task, in which JLR combined 12 data sources in a graph equivalent to 23 relational database tables, helped JLR make connections within the data — such as what exactly it can build at the moment with its parts in hand — that it previously couldn’t. The analysis also took only 45 minutes compared to the weeks it would take to join data using relational systems, Powell says. The analysis helped JLR potentially avoid millions of dollars in charges from suppliers for failing to fulfill minimum buy volume stipulations. ML helps toothpaste maker squeeze more out of its machines As the pandemic spread and people purchased an abundance of personal-care products, Colgate-Palmolive tapped machine learning software to ensure that its toothpaste products made it to retail shelves. The software, from Augury, teams with Bluetooth wireless sensors to monitor the 2,000 machines that Colgate uses to build toothpaste tubes and other products in an effort to eliminate production line failures, which can cost the company thousands of dollars due to downtime, says Warren Pruitt, Colgate’s director of global engineering. For instance, the ML software alerted Colgate’s production team after it detected rising temperatures in the drive motor of one of its tube producers. The team discovered a problem with the motor’s water cooling system and resolved it, preventing the drive from failing, which would have stopped the tube production line. Pruitt estimates the effort saved 192 hours of downtime and an output of 2.8 million tubes of toothpaste, plus $12,000 for a new motor and $27,000 in variable conversion costs. In another case, the software alerted workers that a gearbox in a liquids machine was experiencing structural and operational issues, putting it at high risk of failure. The team ordered a replacement gearbox and swapped it in. “Unlike scheduled routine checkups for equipment, this digitally enabled method diagnoses problems early, allowing for quick remediation and minimized downtime,” says Pruitt, adding that it is akin to wearing a glucose monitor versus waiting until your doctor’s visit to discover you have an imbalance. Pruitt says that while Colgate may have been able to build similar technology, it would have “taken us years, even with approval to hire” data scientists and engineers to create such a platform. Pruitt says the technologies have helped Colgate beef up production volumes at a time when the pandemic is generating surges in demand. He adds that this success is prompting Colgate to roll out Augury across its global supply chain, including its Hill brand of pet foods, as well as its manufacturing facilities across India and China. Over time, Pruitt expects to combine the Augury software with digital twins of Colgate’s manufacturing plants to help determine in which facilities its product formula will flourish. The bottom line The technology deployments from JLR and Colgate illuminate how global organizations can walk the tightrope of disruption. The key lies in using ML, IoT and analytics to eliminate data latency that constrains most supply chains, helping organizations know when to ramp up manufacturing, says Lekstutis, of TCS. “The sooner we know something, the faster we have the chance to put in the right supply chain response,” Lekstutis says. “This creates huge opportunities for supply chains to be more resilient and agile, which is a competitive weapon.” More on supply chain management: What is supply chain management? Mastering logistics end to end5 keys to supply chain management successAI in the supply chain: Logistics gets smartThe top 5 supply chain management vendors Related content brandpost The steep cost of a poor data management strategy Without a data management strategy, organizations stall digital progress, often putting their business trajectory at risk. Here’s how to move forward. By Jay Limbasiya, Global AI, Analytics, & Data Management Business Development, Unstructured Data Solutions, Dell Technologies Jun 09, 2023 6 mins Data Management feature How Capital One delivers data governance at scale With hundreds of petabytes of data in operation, the bank has adopted a hybrid model and a ‘sloped governance’ framework to ensure its lines of business get the data they need in real-time. By Thor Olavsrud Jun 09, 2023 6 mins Data Governance Data Management feature Assessing the business risk of AI bias The lengths to which AI can be biased are still being understood. The potential damage is, therefore, a big priority as companies increasingly use various AI tools for decision-making. By Karin Lindstrom Jun 09, 2023 4 mins CIO Artificial Intelligence IT Leadership brandpost Rebalancing through Recalibration: CIOs Operationalizing Pandemic-era Innovation By Kamal Nath, CEO, Sify Technologies Jun 08, 2023 6 mins CIO Digital Transformation Podcasts Videos Resources Events SUBSCRIBE TO OUR NEWSLETTER From our editors straight to your inbox Get started by entering your email address below. Please enter a valid email address Subscribe