Machine learning: A new tool for better forecasting
Business volatility and the complexity of factors influencing demand are making it hard to reliably model the causes of demand variation. Machine learning can help companies overcome that challenge.
Demand forecasting is difficult, and most demand forecasting conducted today produces disappointing results and significant forecast errors. It cannot easily identify trends in the demand data, and its limited ability to understand the underlying causes of demand variability makes that variability seem worse than it would if demand drivers were clearly understood. And because it is manually intensive, it suffers from persistent bias and poor planner productivity.
"Supply Chain Shaman" Lora Cecere puts it bluntly. In her excellent book, Bricks Matter, she writes, "Within an organization, the words 'Demand Planning' stir emotions. Usually, it is not a mild reaction. Instead, it's a series of emotions defined by wild extremes including anger, despair, disillusionment, or hopelessness." She goes on to say that planning teams are dismayed by demand planning's challenges, and further claims that leaders are not optimistic about making improvements to planning processes and technologies.
What makes forecasting demand so challenging? Rather than appearing as a logical series of numbers, in today's business environment demand more often seems like a pattern of partially constrained chaos. Demand is increasingly influenced by multiple internal and external factors that drive it up and down in ways that can't be understood by simply looking at a historical time-series of aggregated demand buckets. Instead, demand should be viewed as being driven by a complex series of indicators that can be nearly impossible to manage with traditional forecasting algorithms.
However, a new technology called machine learning can help companies address demand-forecasting challenges by reliably modeling the numerous causes of demand variation. Machine learning is a computer-based discipline in which algorithms can actually "learn" from the data. Rather than following only explicitly programmed instructions, these algorithms use data to build and constantly refine a model to make predictions. I'll explain in more detail later, but first I'd like to describe several business scenarios where companies have employed machine learning in their demand forecasting. See if any of these scenarios suggest familiar attributes in your own business.
Lots of promotions. Every year, the Italian dairy producer Granarolo S.p.A. runs thousands of consumer promotions, creating forecasting scenarios for 34,000 unique stock-keeping unit (SKU) promotions. And it gets worse: Demand spikes can amount to an extraordinary 30 times baseline sales. (For more about these challenges, see the Granarolo sidebar.)
This is a common predicament. Expenses for advertising and promotions can add up to more than 20 percent of sales for many consumer products companies. Yet according to Michael Kantor, founder and chief executive officer of the Promotion Optimization Institute, only about 1 in 50 brands is able to forecast demand uplift reliably enough to guarantee consumer product availability and to evaluate the economic returns on those promotions. Without improved technology, few companies can forecast effectively in such a promotion-heavy environment. (For an example, see the sidebar about Groupe Danone.)
Lots of new products. The United Kingdom-based electronics distributor Electrocomponents plc is a top-ranked global distributor with 500,000-plus in-stock items. The company introduces 5,000 new products every month and fulfills more than 44,000 same-day orders every day from its operations in 32 countries. A few new products a month is one thing, but predicting demand for such a vast array of new products is more than a demand planner can reasonably be expected to handle. Plus, new products, by definition, are difficult to forecast. Nevertheless, planners can tap into external data to help them predict initial demand and thus decide how much marketing budget to invest in launching a new product.
Lots of "long-tail" demand. Companies whose e-commerce business is growing find themselves having to forecast demand for more slow-moving, "long-tail" items that customers order infrequently and in small quantities. Outliers are naturally hard to predict, making inventory planning notoriously difficult. Even if you can predict the average demand for certain products, you probably can't predict the demand spikes. This makes it nearly impossible to maintain a balance—having enough on hand to satisfy sudden spikes without adding unnecessary inventory and eventually holding "dead stock."
Growing complexity. Planning wasn't so complicated when Granarolo started out in the 1960s as a local collective of milk producers, but gradually complexity intensified as the company grew into a multinational concern comprising eight brands and hundreds of different dairy products, and utilizing various delivery modes. Its basic software was never designed to handle this kind of growth, and what resulted was progressively inaccurate forecasting that needed time-consuming manual activity to fine-tune. Granarolo's situation is typical of modern supply chains, which continue to increase in complexity.
Extreme seasonality. The United States-based heating, ventilation, and air conditioning (HVAC) manufacturer Lennox International Inc.'s forecasting was complicated because of its high number of SKUs (each of which had its own unique demand pattern) and a significant stock of slow-moving parts, and because it is an extremely seasonal business. Further complicating matters was the company's plans to greatly expand its distribution network, as detailed in the Lennox sidebar. There was no way the manufacturer could manage this level of complexity and variability without adopting a highly automated demand planning system.
Just too much data. In all of these companies we find a pattern that is common to most of today's businesses: a proliferation of new data. I'm referring here primarily to market and logistical data that can help companies better predict demand. Having to manage huge volumes of diverse and ever-growing data streams is more than most planners (and planning systems) can handle. Trying to incorporate them into a forecast using spreadsheets or traditional planning tools is frustrating, often futile, and can be extremely costly.
The companies in the scenarios above share an intrinsic level of complexity and scale that makes it almost impossible for planners to generate reliable forecasts. They are no longer simple and predictable businesses, able to forecast based on historic sales volumes—if they ever were! Their planners were overwhelmed.
In many cases we see, people don't start contributing to forecasts until the very end of the process. So, rather than providing input to help generate an accurate forecast in the first place, they're collaborating to adjust the forecast "output." This approach is inefficient. While some late-stage "crowd wisdom" can be useful, it can also introduce bias. A typical example is when a sales organization artificially adjusts a forecast to match revenue targets.
What else do these companies have in common? They all turned to machine learning in order to increase forecast reliability. This decision dramatically slashed inventory costs and at the same time provided better, more efficient service to customers. It also meant that planners no longer had to waste time manually overriding or adjusting forecasts.
Let's examine how machine learning enabled these improvements.
What machine learning is and does Machine learning systems were designed to handle forecasting models that can incorporate many kinds of data. Rather than following traditional programmed instructions, machine learning systems reduce demand variability by capturing and modeling all the relevant attributes that shape demand while filtering out the "noise," or random and unpredictable demand fluctuations.
As a result, they learn from the data that they process and modify their operations accordingly. For example, a machine learning system that uses Web data to quickly detect successful new products will find and learn which demand indicators—such as Web page hits, specification downloads, and time on site—are most reliable, and then will update its model over time as consumer behavior changes.
Machine learning can interpret the effect of stimuli (such as trade promotions and advertising) and demand indicators (such as social media activity) originating from each distribution channel. As information proliferates, the data concerning these causes and demand indicators become both more accessible and more manageable over time. Machine learning systems therefore can integrate and usefully model these important new data sources, including detailed market data, machine telemetry, and social media feeds, in ways that are simply not possible with legacy planning systems.
What does this mean in practical terms? For one thing, it means companies can take advantage of valuable data signals that are generated closer to the consumer, including data from points of sale and social media channels. This enables companies to understand the impact of demand drivers such as media, promotions, and new product introductions, and to then use that knowledge to significantly improve forecast quality and detail.
Could you benefit from machine learning? Would machine learning technology be beneficial for your supply chain? One way to know is by finding out whether your old planning system may be causing escalating costs. Here are three potential signs of this problem, and how machine learning can help to address them:
Inflated safety-stock levels. You can't trust your safety-stock levels to deliver the required service levels, so you keep them artificially high. By taking more demand variables into account, machine learning can help companies with a diverse range of SKU profiles, including long-tail items, to set optimal, lower levels they can trust.
Planning team "burnout." Your team is spending too much time manually adjusting and evaluating forecasts, and often is still not able to deliver them accurately enough or on time. This leads to poor productivity and morale. Machine learning takes more demand variables into account and weights each according to its significance, resulting in much more accurate forecasts. This helps planners succeed in their roles and frees up time for them to refine forecasts using their personal insights and business knowledge.
An inefficient sales and operations planning (S&OP) process. Your consensus forecast from the S&OP is unreliable, or the collaboration process behind it is too slow to adapt to the dynamic nature of the market and SKU behavior. Machine learning's high level of automation can improve the quality of the short- and mid-term forecast by picking up key trends from transactional and promotional data and providing actionable insights about those trends, thereby making the S&OP process more efficient and effective in achieving your business objectives.
If any of these situations resonate, it's likely time to take a closer look at machine learning technology. This doesn't have to mean "ripping and replacing" your existing software. Granarolo, for example, implemented machine learning technology alongside its existing systems to boost performance. Companies that implement machine learning often find that it is easy to use, and that its ability to learn from existing data means that it takes relatively less time to implement, deliver benefits, and pay for itself.
In the not-too-distant future, most supply chains will rely on software that uses machine learning technology to analyze much larger, more diverse data sets. For companies that are serious about tackling today's complex forecasting problems, this new technology will prove an invaluable tool.
GRANAROLO S.p.A.
Forecasting scenario: The Italian dairy producer Granarolo runs thousands of promotions annually, producing 34,000 item-promotion forecasting combinations and causing demand peaks of up to 30 times baseline sales.
Supply chain environment: Eight production plants, six logistics technology platforms, 35 transit depots holding inventory, a large fleet of refrigerated vehicles, and about 750 merchandisers servicing daily sales. A network of 100 wholesale distributors covers other local markets.
Benefits from machine learning: Granarolo's average forecast reliability has increased from 80 percent to 85 percent and is peaking at 95 percent for fresh milk and cream and 88 percent for yogurt and dessert products. Inventory levels and delivery times have been halved, resulting in fresher products and less waste. Overall, Granarolo has significantly raised customer service levels and sales while at the same time reducing transportation costs.
Â
LENNOX INTERNATIONAL INC.
Forecasting scenario: Lennox, a U.S.-based manufacturer of heating, ventilation, and cooling equipment, had to manage an ambitious expansion of its North American distribution network while transitioning to a three-tier design that included regional distribution centers. Lennox would have to implement this change while maintaining high service levels in both its finished-goods and aftermarket-parts businesses, and in an environment encompassing fast-moving to very slow-moving items, strong seasonality, and demand variability.
Supply chain environment: The company was shifting from a multiechelon distribution network with more than 80 locations to a network of more than 130 locations in the United States and Canada. This expansion involved:
Moving from 450,000 finished-goods and spare-parts stock-keeping unit (SKU) locations to more than 700,000
Tens of millions of dollars tied up in inventories, including a "long tail" (98 percent of SKUs responsible for 62 percent of revenues) and many slow movers with classic "lumpy" demand that is uneven in terms of timing and quantity
Many new-product introductions; in one recent year, nearly 50 percent of the finished-goods product line was replaced with new models
High product-availability targets, including 75 percent of orders for next-day delivery and 20 percent of sales to installers and contractors who need same-day pickup
Assured serviceability on finished goods for 15+ years
Highly variable independent demand, driven by external factors that are difficult to model (for example, weather and macroeconomic conditions)
Highly seasonal demand (air conditioning and heating), with little retail buffer
Benefits from machine learning: Lennox was able to automate its planning process and create an improved inventory mix over its widespread distribution network. Despite aggressively growing its distribution network by 30 percent in two years, Lennox has already cut stockouts by more than half, from 9 percent down to 4 percent, and trending toward further improvement.
Artificial intelligence (AI) tools can help users build “smart and responsive supply chains” by increasing workforce productivity, expanding visibility, accelerating processes, and prioritizing the next best action to drive results, according to business software vendor Oracle.
To help reach that goal, the Texas company last week released software upgrades including user experience (UX) enhancements to its Oracle Fusion Cloud Supply Chain & Manufacturing (SCM) suite.
“Organizations are under pressure to create efficient and resilient supply chains that can quickly adapt to economic conditions, control costs, and protect margins,” Chris Leone, executive vice president, Applications Development, Oracle, said in a release. “The latest enhancements to Oracle Cloud SCM help customers create a smarter, more responsive supply chain by enabling them to optimize planning and execution and improve the speed and accuracy of processes.”
According to Oracle, specific upgrades feature changes to its:
Production Supervisor Workbench, which helps organizations improve manufacturing performance by providing real-time insight into work orders and generative AI-powered shift reporting.
Maintenance Supervisor Workbench, which helps organizations increase productivity and reduce asset downtime by resolving maintenance issues faster.
Order Management Enhancements, which help organizations increase operational performance by enabling users to quickly create and find orders, take actions, and engage customers.
Product Lifecycle Management (PLM) Enhancements, which help organizations accelerate product development and go-to-market by enabling users to quickly find items and configure critical objects and navigation paths to meet business-critical priorities.
Nearly one-third of American consumers have increased their secondhand purchases in the past year, revealing a jump in “recommerce” according to a buyer survey from ShipStation, a provider of web-based shipping and order fulfillment solutions.
The number comes from a survey of 500 U.S. consumers showing that nearly one in four (23%) Americans lack confidence in making purchases over $200 in the next six months. Due to economic uncertainty, savvy shoppers are looking for ways to save money without sacrificing quality or style, the research found.
Younger shoppers are leading the charge in that trend, with 59% of Gen Z and 48% of Millennials buying pre-owned items weekly or monthly. That rate makes Gen Z nearly twice as likely to buy second hand compared to older generations.
The primary reason that shoppers say they have increased their recommerce habits is lower prices (74%), followed by the thrill of finding unique or rare items (38%) and getting higher quality for a lower price (28%). Only 14% of Americans cite environmental concerns as a primary reason they shop second-hand.
Despite the challenge of adjusting to the new pattern, recommerce represents a strategic opportunity for businesses to capture today’s budget-minded shoppers and foster long-term loyalty, Austin, Texas-based ShipStation said.
For example, retailers don’t have to sell used goods to capitalize on the secondhand boom. Instead, they can offer trade-in programs swapping discounts or store credit for shoppers’ old items. And they can improve product discoverability to help customers—particularly older generations—find what they’re looking for.
Other ways for retailers to connect with recommerce shoppers are to improve shipping practices. According to ShipStation:
70% of shoppers won’t return to a brand if shipping is too expensive.
51% of consumers are turned off by late deliveries
40% of shoppers won’t return to a retailer again if the packaging is bad.
The “CMA CGM Startup Awards”—created in collaboration with BFM Business and La Tribune—will identify the best innovations to accelerate its transformation, the French company said.
Specifically, the company will select the best startup among the applicants, with clear industry transformation objectives focused on environmental performance, competitiveness, and quality of life at work in each of the three areas:
Shipping: Enabling safer, more efficient, and sustainable navigation through innovative technological solutions.
Logistics: Reinventing the global supply chain with smart and sustainable logistics solutions.
Media: Transform content creation, and customer engagement with innovative media technologies and strategies.
Three winners will be selected during a final event organized on November 15 at the Orange Vélodrome Stadium in Marseille, during the 2nd Artificial Intelligence Marseille (AIM) forum organized by La Tribune and BFM Business. The selection will be made by a jury chaired by Rodolphe Saadé, Chairman and CEO of the Group, and including members of the executive committee representing the various sectors of CMA CGM.
The Raymond Corp. has expanded its energy storage solutions business with the opening of a manufacturing plant that will produce lithium-ion and thin plate pure lead (TPPL) batteries for its forklifts and other material handling equipment. Located in Binghamton, N.Y., Raymond’s Energy Solutions Manufacturing Center of Excellence adds to the more than 100-year-old company’s commitment to supporting the local economy and reinvigorating Upstate New York as an innovation hub, according to company officials and local government and business leaders who gathered for a ribbon cutting and grand opening this week.
“This region has a rich history of innovation,” Jennifer Lupo, Raymond’s vice president of energy solutions, supply chain, and leasing, said in welcoming attendees to the ribbon cutting ceremony Monday.
Lupo referred to the new factory as an “exciting milestone” in Raymond’s history and described it as the next step in the company’s energy storage solutions business, which began nearly 10 years ago with the development of a lithium-ion battery to power its “walkie” pallet jack. That work has expanded to include larger batteries and other technologies to support battery-electric equipment.
“We’re not just keeping up with the electrification movement,” Lupo said. “We’re leading it.”
Raymond, a business unit of Toyota Material Handling, has been building forklifts, pallet jacks, and other material handling equipment at its nearby Greene, New York, headquarters since 1922. The Binghamton factory supports local efforts to boost manufacturing and innovation in New York’s Southern Tier, which was recently designated as a regional technology and innovation hub by the Biden Administration.
Raymond is leasing the 124,000 square foot facility at 196 Corporate Drive, situated in an established industrial park. The manufacturer is currently utilizing just 10,000 square feet of the space to produce its 8250 lithium-ion battery, which can power Raymond’s class 1 and class 2 fork trucks, as well as a smaller TPPL battery for powering pallet jacks.
The Binghamton factory employs 15 people, but the company expects to scale up quickly in space and personnel, adding 12 to 25 employees next year and ramping up to 60 employees by 2027, according to Jim Priestly, battery manufacturing manager for energy solutions at Raymond.
The Binghamton facility also represents Raymond’s larger commitment to helping develop greener, more sustainable supply chains, according to company President and CEO Michael Field.
“We recognize energy’s critical role in shaping our future,” Field told attendees at the grand opening, adding that Raymond is seizing the opportunity to participate in the clean energy transition locally and beyond.
“This facility is just the beginning,” Field said.
Economic activity in the logistics industry expanded in August, though growth slowed slightly from July, according to the most recent Logistics Manager’s Index report (LMI), released this week.
The August LMI registered 56.4, down from July’s reading of 56.6 but consistent with readings over the past four months. The August reading represents nine straight months of growth across the logistics industry.
The LMI is a monthly gauge of economic activity across warehousing, transportation, and logistics markets. An LMI above 50 indicates expansion, and a reading below 50 indicates contraction.
Inventory levels saw a marked change in August, increasing more than six points compared to July and breaking a three-month streak of contraction. The LMI researchers said this suggests that after running inventories down, companies are now building them back up in anticipation of fourth-quarter demand. It also represents a return to more typical growth patterns following the accelerated demand for logistics services during the Covid-19 pandemic and the lows of the recent freight recession.
“This suggests a return to traditional patterns of seasonality that we have not seen since pre-COVID,” the researchers wrote in the monthly LMI report, published Tuesday, adding that the buildup is somewhat tempered by increases in warehousing capacity and transportation capacity.
The LMI report is based on a monthly survey of logistics managers from across the country. It tracks industry growth overall and across eight areas: inventory levels and costs; warehousing capacity, utilization, and prices; and transportation capacity, utilization, and prices. The report is released monthly by researchers from Arizona State University, Colorado State University, Rochester Institute of Technology, Rutgers University, and the University of Nevada, Reno, in conjunction with the Council of Supply Chain Management Professionals (CSCMP).