Business has always been a numbers game. That’s why spending on supply chain advanced analytics is on the rise. Analysts from River Logic write, “The importance of supply chain analytics is demonstrated by predictions that the market will grow at a CAGR of 17.3% between 2019 to 2024, more than doubling in size. “[1] Business people who don’t understand numbers don’t stay in business very long. I’m reminded of the story of two men who bought a truck and went into the watermelon business. They drove their truck to the farm and bought watermelons for $1 each. They then drove back to the city and sold them for $1. When it became obvious they weren’t making a profit, one of the men said, “Maybe we need a bigger truck.” Understanding the numbers requires more than analyzing past and present performance. The most successful decision-makers also want to understand the numbers concerning the future. Thanks to cognitive technologies and big data, predictive analytics allow decision-makers a peek into the future. River Logic analysts attribute the predicted growth in analytics spending primarily to “the benefits of being able to predict, with a reasonable degree of certainty, what will happen in the future.” Tim Sandle (@timsandle) notes, “Advances with machine learning and big data analytics are helping researchers, and ultimately companies, to make predictions about future trends by analyzing patterns.”[2]
Cognitive technologies and predictive analytics
Shailendra Kumar (@meisshaily), a senior analytics executive, believes there might be some confusion about the differences between machine learning, a type of artificial intelligence, and predictive analytics. He writes, “Amidst the rapid advancements in technology today, people tend to get confused over the specifics of machine learning and predictive analytics. Although they are closely related and very much centered on efficient data processing to enhance accurate predictions for increased productivity, the application of these two concepts reveals many differences.”[3] He notes, “Machine learning is underlying intelligence behind most artificial intelligence (AI) applications which involve the development of systems or algorithms which have the ability to learn and improve automatically from data experience without relying on explicit programming based on rules or instructions with the changing data patterns. … Almost all prominent companies nowadays depend on the use of machine learning algorithms for the better understanding of their clients and potential revenue opportunities. The hundreds of different existing and newly developed machine learning algorithms all target the derivation of high-end predictions which can guide real-time decisions without so much reliance on human intervention.” When it comes to predictive analytics, Kumar notes, “All predictive analytics applications involve three fundamental components.” Those components are:
1. Data: “The effectiveness of every predictive model strongly depends on the quality of the historical data which it processes.”
2. Statistical modeling: “This component includes the various statistical techniques it applies ranging from very basic to complex functions for the derivation of meaning, insight and inference. Regression is the most commonly used statistical technique.”
3. Assumptions: “Analyzed data … usually assume the future to follow a pattern related to the past.”
The last point about assumptions is critical because we all know the future is not always an extrapolation of the past. Shannon Kearns (@ShannonKrns), an analytics expert at River Logic, explains the purpose of predictive analytics is “to answer the question ‘what is the likelihood that x, y, or z will happen based on the data I have?’.”[4] She goes on to note, “Predictive analytics can tell you when you should consider taking action, but it can’t tell you what action to take. Thus, if you rely on gut feel or standard practices to make decisions, sometimes you’ll end up selecting a bad response. The more complex the decision, the greater the likelihood becomes that you won’t select (or even consider) the best plan. So, by making poor decisions in response to predictive analytics, predictive all of a sudden becomes significantly less valuable.” As a result, she concludes, “The main limitation of predictive analytics isn’t the analytics itself — it’s how a business responds.”
River Logic analysts observe, “The first step in supply chain predictive analytics is preparing a mathematical model that closely represents the trend you’re trying to understand. This may mean testing numerous forecasting models to determine the one that most closely represents reality. Typically, this will entail testing the model with known historical data and refining it until it’s capable of reliably forecasting the past. The next step is adding current data and using the model to forecast future trends. It’s essential to understand that the model is simply applying probability theory to determine what’s most likely to happen; the model can’t see into the future. What’s also important is to have lots of high-quality data, as this increases the probability of an accurate forecast.” Although predictive analytics models can’t really see into the future, thanks to machine learning they can adapt quickly as conditions change and are reflected in near-real-time data. The River Logic analysts conclude, “Numerous examples exist of where supply chain professionals are winning with predictive analytics. These include demand forecasting, predictive pricing strategies, inventory management, logistics and predictive maintenance.”
Predictive analytics and future supply chains
Gracie Myers, an analyst from Research Optimus, writes, “Predictive analytics is being applied toward all facets of business operations and processes to help anticipate events, avoid risks, and create solutions. By forecasting future supply chain and logistical events, companies can gain a competitive advantage and prevent monetary loss due to inaccurate stocking, and mismanagement of goods, deliveries, and time.”[5] She lists a number of ways organizations can use predictive insights for supply chain and logistics. They include:
Transportation Management Systems: “Supply chains depend on fixed lead time and uncertainty for factors such as ocean shipping, can be addressed by predicting future disruptions.”
Third Party Logistics: “Predictive analytics can create more value by developing partnerships with technology providers to apply Big Data to their services.”
Industrial Procurement: “Retailers and distributors can prepare months in advance to help their suppliers plan to inventory and shipments based on customer demand and buying behavior.”
Customer Visibility: “Organizations can obtain market insights about customers, suppliers, and trading partners, as well as seasonal buying patterns and consumer forecasts to make quicker more intelligent decisions.”
Product and Content Placement: “Organizations can better prepare for short-term behavioral changes that affect supply chain and logistics such as news, weather, shortages, and manufacturing promotions. By utilizing predictive analytic models to detect unexpected conditions, they can better adjust site merchandising in response to specific time-sensitive data.”
Improved Personalization for B2B: “Predictive analytic models can be used to ensure that the correct seasonal products are delivered to customers based on geographical region. A model can detect changes that may necessitate a modification in merchandising per geographic location.”
Predict supply and demand: “Predictive analytics ensures that there are less waste and on-time deliveries during pinnacle demand times.”
Predictive Maintenance: “This is extensively used in supply chain logistics in a technology-focused way, particularly in operations that focus on picking and packing, and across fleets of transport ships and trucks.”
Concluding thoughts
Although there are limitations to predictive analytics, the value added by predictive analytics far surpasses any limitations. Kearns asserts, “Predictive analytics is gaining momentum with the rapid increase of Internet of Things (IoT) devices. These devices embed sensors in equipment to monitor and transmit data continuously to IoT platforms. Twenty billion units are expected to be deployed by 2020. With this influx of technology, predictive analytics is more powerful than ever.” Her River Logic colleagues add, “If there’s anything that separates organizations, it’s their ability to forecast requirements accurately. Whether it’s simply the next day’s sales or something more complex, such as the long-term life product cycle, those organizations using predictive analytics have a head start.”
Footnotes
[1] Staff, “Supply Chain Predictive Analytics: What Is It and Who’s Doing It?” The Stream by River Logic, 31 March 2020.
[2] Tim Sandle, “Using big data to predict the future,” Digital Journal, 2 December 2018.
[3] Shailendra Kumar, “Understanding the difference between machine learning and predictive analytics,” Information Management, 5 March 2018 (out of print).
[4] Shannon Kearns, “The Limitations of Predictive Analytics Tools and Why Execs Should Care,” The Stream by River Logic, 19 January 2019.
[5] Gracie Myers, “How Predictive Analytics Is Benefitting Supply Chain and Logistics Industry,” Research Optimus, 19 December 2017. (EMAIL Gracie Myers gracie.m@fwsblogger.com)
