For years, the application of predictive analytics in supply chain management has been described as “transformative,” a “big opportunity,” the “new business intelligence,” and even “the holy grail.” However, in conversations, there is often confusion on where and how predictive analytics can be applied.
The basic premise of supply chain management is to control the manufacture, storage, transportation and sales of goods and services to meet customer demand. Have it when they want it, keep nothing else. Predictive analytics is about using a large amount of data to gain insight into possible future scenarios and their potential outcomes. I will focus on two major areas where predictive analytics can be applied to supply chain management—customer demand forecasting and inventory optimization.
Customer Demand Forecasting
Demand forecasting can be defined as the prediction of demand for a product or service, by customers. In the results from their third annual supply chain survey—Supply Chain Talent of the Future—Deloitte Consulting notes that demand forecasting was listed as one of the top “fast-evolving technical capabilities” that is currently in use or expected to be used in the supply chain. In fact, demand forecasting is second only to optimization tools, with 53 percent of respondents noting they currently use demand forecasting and an additional 43 percent expect to use demand forecasting in the future.
In the article, Demand Forecasting: The Key to Better Supply-Chain Performance, The Boston Consulting Group notes that traditional methods are often powered by limited data, time intensive, and use outdated forecasting models that are typical of the one-size-fits-all variety.
The improvements to demand forecasting using predictive analytics are far reaching:
Insight: The machine learning employed in predictive analytics models allows for large amounts of structured ERP and supply chain management data to be processed with seemingly disparate data such as consumer sentiment data which derives from Facebook, Twitter, Pinterest, Instagram and macroeconomic indicators such as GDP, unemployment, Leading Indicators Index, etc. Other disparate data include iOT device data, demographics, weather and other domain-specific factors like production lines, engineering changes, etc. However, predictive analytics is not just about collecting data, but enabling actionable insight into how, when, or why customers make purchases.
Speed: Near real-time collection of data combined with machine learning allows predictive analytics to be calculated within minutes or a few hours rather than a 24/48-hour batch processing cycle that is often used today. Microsoft has a great case study showcasing how Pier 1 Imports used predictive analytics to understand and act on the customer shopping habits across their e-commerce site and more than 1000 neighborhood stores.
“Pier 1 is a very data-rich company,” says Eric Hunter, Executive Vice President of Marketing, Pier 1 Imports. “We needed a way of leveraging these multiple sources to better match our customers to the products they’re looking for.” With a solution that combined its omni-channel retail data with machine learning, Pier 1 Imports could predict customer purchase patterns. “As we learn the patterns in our data, it will help us personalize our website, and merchandise our stores with more accurate and robust data-driven decision making,” says Andrew Laudato, Senior Vice President and CIO of Pier 1 Imports. While supply chain management isn’t specifically mentioned, the case study provided some interesting insight into how predictive analytics impact Pier 1 Imports’ decision-making processes.
By understanding and forecasting customer demand, another major area of applying predictive analytics to supply chain management becomes relevant: inventory optimization.
An article in SupplyChainDigest offers a solid definition of inventory optimization: “…having the right amount of inventory, in just the right places, to meet customer service and revenue goals — but no more than that.”
Inventory optimization helps reduce inventory distortion, a challenge that stems from out-of-stock and overstock inventory situations. A recent study by IHL Group, a global research and advisory firm specializing in technologies for the retail and hospitality industries, found that inventory distortion costs retailers nearly $1.1 trillion globally—$252 billion of that happens in North America alone.
Traditional methods of optimizing inventory include adjusting inventory retroactively and reacting to customer purchase habits that have already occurred. This method is further compounded by segmented IT systems stood up to meet isolated needs that result in decentralized and short-sighted inventory decision-making processes. These traditional methods result in significant issues throughout the supply chain pipeline.
Southern States Cooperative, a U.S.-based agricultural supply cooperative, has over 1,000 retail distribution points. They recognized slow moving inventory within their supply chain, although they didn’t have the insight necessary to enable data-driven decision making around it.
For Southern States Cooperative, any inventory that had no sales in the last 12 months or inventory more than 12 months old is considered slow moving. To address this issue, they implemented a multi-faceted project that leveraged data-mining, predictive analytics and a transition to a centralized inventory management system.
Even in the initial stages, the new reporting capabilities gave direct insight into the percentage of their current inventory that was slow moving:
• 34% of retail crop protectant products
• 33% of retail farm & home + animal health
• 30% of wholesale crop protection products
• 28% of wholesale farm & home + animal health
Aside from the reduction of current inventory while maintaining sales volume, Southern States realized other benefits of employing predictive analytics in its inventory optimization strategy:
• Actionable data delivered to multiple operating units to improve inventory management;
• Greater insight into seasonality, impacting timing of delivery of seasonal products;
• More accurate sales forecasting, tied to inventory levels, to ensure in-stock positions;
Cultural shift in use of information to improve the business — fewer decisions based on gut feelings, more based on the analysis of the business.
Predictive analytics will help you identify trends, understand your customers’ purchase habits, predict purchase behavior, and drive strategic decision-making. If you’re not employing predictive analytics in your supply chain management strategy, put away your complicated spreadsheets and isolated databases and start considering the transition today.
Gary Nakanelua is a Director at Blueprint Consulting Services, a national technical consulting firm that connects strategy and delivery. He helps clients successfully adopt a variety of technology solutions including the Hadoop ecosystem, machine learning, and cloud computing.