Journal of Business Forecasting Articles Issues

In today’s environment of rising tariffs, frequent supply disruptions, and persistent demand volatility, companies can no longer rely on one-size-fits-all planning and execution. This article shows how a unified segmentation approach of categorizing items and customers by profitability, volume, and variability can focus resources, mitigate risk, and align fulfillment strategies to drive measurable improvements in margin, service, and working capital. The article also explains how to embed these insights into IBP performance metrics and use them to guide targeted pricing, part rationalization, and demand shaping actions that strengthen cash flow and asset utilization.

In an era where agility and accuracy are vital for supply chain resilience, this case study highlights the transformation of a global packaging manufacturer’s demand planning process—from fragmented, manual forecasting methods to a centralized, data-driven and machine learning approach. Faced with inconsistent accuracy, reactive planning, and excess inventory, the company implemented a scalable solution that integrated key data sources and introduced more consistent, forward-looking forecasts. The transformation improved forecast accuracy, streamlined planning cycles, and enabled better alignment across sales, operations, and finance. As a result, the organization strengthened its ability to anticipate demand, reduce costs, and support future growth with greater agility.

A review of a new book titled Could Should Might Don’t: How We Think About the Future, casts doubt on whether current discussions about the future would be useful to strategic planning in business. In this article, I debate how the relevance of potential future scenarios for the supply chain planning field including the impact of Artificial Intelligence. I reveal the debates futurists have over to what extent the future lies within our control, and how far we can look into the future with any degree of accuracy or usefulness.

Post-COVID supply chains have prioritized multisourcing to build resilience, yet this expansion has introduced significant hidden costs and complexity. While critical for high-volume materials, multisourcing the “long tail”—the 5–10% of spend comprising 80% of transactions—is often inefficient. In this article, I assess the pros and cons consolidating this incidental spend through third-party partners. By outsourcing these low-volume purchases, organizations can reduce onboarding costs, leverage cost-plus pricing, and simplify transactional loads. This strategic shift allows procurement teams to refocus on strategic priorities while maintaining supply security and operational simplicity.

In an era where agility and accuracy are vital for supply chain resilience, this case study highlights the transformation of a global packaging manufacturer’s demand planning process—from fragmented, manual forecasting methods to a centralized, data-driven and machine learning approach. Faced with inconsistent accuracy, reactive planning, and excess inventory, the company implemented a scalable solution that integrated key data sources and introduced more consistent, forward-looking forecasts. The transformation improved forecast accuracy, streamlined planning cycles, and enabled better alignment across sales, operations, and finance.

In today’s dynamic business environment, new companies are bringing innovative products to market at an unprecedented rate. Startup enterprises experiencing rapid growth realize that a key competitive differentiator is effective S&OP, but balancing demand and supply and maintaining stable operations while maintaining the agility startups require, is fraught with challenges. This article explores how startups can effectively implement S&OP to bridge the gap between vision and execution, with lessons learned from my experience building and managing S&OP at a range of multinational firms including Amazon, Honda, Estée Lauder and more.

Most organizations invest heavily in S&OP processes, yet a critical disconnect persists between planning intent and operational execution. In this article, I discuss how this gap stems not from planning methodology, but from the failure to leverage the granular transactional data residing in ERP systems. I present a practitioner’s framework for using ERP data granularity to bridge this divide. I discuss specific techniques for extracting actionable insights from transactional data, establishing the right level of granularity for different planning horizons, and building feedback loops that transform S&OP from a monthly ritual into a dynamic operational capability.

This article presents Multi-Agent Systems (MAS) as a practical, modular approach to modernizing demand forecasting with low-cost, easy-to-use LLMs like ChatGPT. Instead of relying on a single monolithic model, MAS distributes intelligence across specialized agents that handle data preparation, signal detection, modeling, overrides, narratives, and scenario analysis. A key component is the LLM Judge Agent, which evaluates each agent’s output for logic, consistency, and business relevance—acting like an always-on senior Planner. For planning teams, MAS offers a flexible path to AI-driven agility and transparency while preserving human judgment at the center of forecasting decisions.

The implications of the war with Iran, which began at the end of February, remain uncertain for both the U.S. and the global economy. The national average cost for a gallon of gas in the US has risen by 34% over the past month as shipping through the Strait of Hormuz, a crucial oil passage, remains nearly at a standstill. The national average price for diesel is at $5.41 per gallon at the end of March, up 44% from a month ago.

There are several realities demand planning teams must face when trying to implement AI for the first time, including how AI is more about the ‘plumbing’ than algorithms, how it may highlight structural weaknesses in your existing processes, and how successful planning is more about the right response than it is about the right number. This article reveals how to take your first steps in AI, including how to build a pilot, and how the real value AI in demand planning may not be the technology itself but the way it quietly reshapes how organizations think, talk, and decide about the future.

In 2017 I presented a vision for AI adoption in demand planning in my book The Fundamentals of Demand Forecasting, whereby the Demand Planner of the future would be responsible for managing multiple AI systems. In this article, I revisit the applications of AI that I predicted then, and assess their viability of them now in light of recent developments and use cases. Of the five applications I outlined, I highlight the effectiveness of three agentic approaches that seem likely to add value to an organization, namely validating manual forecast overrides, explaining demand variability, and automatically gathering information affecting the demand plan. I also reveal which potential applications of AI are more difficult to implement and less likely to yield tangible benefits.

AI is a stack of predictive, prescriptive, and generative capabilities embedded in workflows to drive measurable outcomes like higher uptime, lower OPEX, faster cycle time, and better customer experience. It learns from telemetry, transactions, and text to forecast, diagnose, decide, and act. The highest value comes from closed-loop application of insights, where models trigger automated control actions and continuously learn from outcomes to self-improve. Success is judged by business KPIs, not model metrics.

I recently read a Wall Street Journal article that detailed how food manufacturers are using Artificial Intelligence to optimize recipes according to desired characteristics such as flavor, aroma and appearance, as well as ingredient costs, environmental impact, and nutritional profile. Such optimization techniques are not new, in fact they employ Linear Programming methods developed as early as 1947. In this article, I discuss how the Simplex model can be used for product optimization, using case studies from my UMass Business Analytics undergraduate course. I also discuss whether LLM’s like ChatGPT are capable of developing new and better models than those developed by humans or whether they will always rely on existing approaches.

AI is everywhere from conference stages to newsfeeds and it’s often described as a mythical, world-changing force. This article brings AI back down to earth, starting where it matters most: demand planning. Among all supply chain disciplines, demand planning offers the perfect entry point for AI because it blends data, human judgment, and measurable outcomes. This article reveals three actionable steps: start small, find an approachable pain point, and define ROI early. We discuss how AI could have solved a real life problem planning French fry demand, and how even modest AI experiments in forecasting and planning can unlock speed, accuracy, and confidence that once seemed out of reach.