Demand Planning for Online Retailers

Switching from supply to demand planning takes guts. This document shows how to transition from a supply planner to a demand planner for those who want to make the move: ➡️ Shift from Internal to External Mindset ↳ Move beyond production constraints; focus on market & consumer trends ↳ Meet customers to understand their pain points; visit the retail stores to see how products perform and are positioned ➡️ Learn the Language of Forecasting ↳ Get fluent in forecast accuracy terms like MAPE, WMAPE, bias ↳ Get also familiar with consensus forecast, baseline vs. uplift, forecast lag ➡️ Master Forecasting Tools & Models ↳ Explore statistical methods in Excel like moving averages and exponential smoothing ↳ Understand when to use each forecasting technique; pros & cons ➡️ Get Close to Sales and Marketing ↳ Ask questions like 'What's driving the change?', 'How confident are you in this number?' ↳ Get comfortable with challenging sales forecast numbers ➡️ Start Owning a Small Forecast Segment ↳ Ask to take on one region, customer, or category’s forecast as a “stretch task”  ↳ Build, improve, and defend it in review meetings. That hands-on work builds fast credibility. ➡️ Embrace Uncertainty as Way of Working ↳ Forecasts are predictions. Learn to do scenario planning. ↳ Communicate and document assumptions clearly ➡️ Bridge with S&OP ↳ Use your supply planning expertise to connect demand, supply, and finance ↳ Embrace the learning curve and enjoy the journey Any others to add?

A few months back, I interviewed a senior demand planner from a global skincare brand. I asked a simple question: "How do you improve your forecast when the system gives you a number that feels... off?" She replied, "We talk to the right people before we talk to the system." That line stayed with me. In Demand Planning, we often focus heavily on historical data, statistical models, and software outputs. But what truly differentiates an average forecast from a high-confidence, actionable one - is the process of Demand Enrichment. And no, it’s not just a buzzword. It’s a discipline - a method of adding intelligence beyond what the system predicts. In fact, according to a McKinsey study, companies that effectively integrate enriched demand signals (like promotions, competitor moves, distribution expansion, influencer campaigns, and even climate effects) can improve forecast accuracy by up to 25%. When I worked for a consumer brand in North India, we noticed our system forecast underestimated demand by 18% during Q4. Why? Because it didn’t factor in the impact of a regional festival that doubled store footfall across 3 key states. Our statistical model was flawless. But our insights were incomplete. That’s when we built a cross-functional "Demand Intelligence Loop" - gathering inputs from marketing, sales, trade partners, and retailers - and feeding it back into planning. The result? Forecast accuracy jumped. Inventory positioning improved. And stockouts during peak weeks were cut in half. If you're a planner reading this: Don't just accept the forecast. Enrich it. Challenge it. Elevate it. That’s how Demand Planning transforms from reactive to strategic.

"Our salespeople are responsible for generating our forecasts, and they own the final numbers. They are crushing it." Said no one to me ever. Often, when I discuss with companies with low demand planning maturity, their process is driven by salespeople. This usually results in, ▪️ A lot of politics ▪️ Biased forecasts (either too high as they confuse demand forecasts and supply plans or under forecasts as salespeople want to beat targets) ▪️ Inaccurate forecasts, as humans aren't the best at generating baseline forecasts. ▪️ 100% manual and time-intensive process and poor utilization of salespeople. Here's how I would design a scalable demand planning process. 1️⃣ Use an ML-generated forecast as a baseline. This forecast should already leverage most of your business drivers (promotions, shortages, prices, per orders, sell-outs—if available) and generate forecasts for new products. 2️⃣ Allow demand planners to enrich forecasts if they have specific insights/information that the model isn't aware of ("I just called our client(s), they told me XXX.") Salespeople can propose insights to demand planners. 3️⃣ Track Forecast Value Added to ensure that the team is adding value. Coach people to success. If you have difficulties with step 2️⃣, focus on four essentials: new products, phased-out products, new clients, and lost clients. You will already add a lot of value. --- If you enjoy demand planning content, I forecast that you will love my mailing list. https://lnkd.in/gSWngz9u

When 55% of your SKUs sell zero units monthly, traditional forecasting breaks down. Nikon cracked the code on long-tail demand planning with Databricks by embracing the sparsity at scale. * Smart simplification: Future demand ≈ Past 6 months total * Planner-aligned distribution: Lock first 2 months, distribute remaining evenly * Workflow integration: Built forecasts directly into existing planning processes For supply chain leaders dealing with long-tail inventory: your forecasting challenges might need less algorithm sophistication and more operational alignment. 🎥 Watch: https://lnkd.in/gw8ubDJW

𝗦𝗲𝗹𝗹𝗶𝗻𝗴 𝗮𝗰𝗿𝗼𝘀𝘀 𝗺𝘂𝗹𝘁𝗶𝗽𝗹𝗲 𝗰𝗵𝗮𝗻𝗻𝗲𝗹𝘀 𝗯𝘂𝘁 𝘁𝗿𝗲𝗮𝘁𝗶𝗻𝗴 𝗶𝗻𝘃𝗲𝗻𝘁𝗼𝗿𝘆 𝗮𝘀 𝗮 𝘀𝗶𝗻𝗴𝗹𝗲 𝗽𝗼𝗼𝗹… 𝘆𝗼𝘂’𝗿𝗲 𝗹𝗲𝗮𝘃𝗶𝗻𝗴 $$$ 𝗼𝗻 𝘁𝗵𝗲 𝘁𝗮𝗯𝗹𝗲. The “first-come, first-served” inventory approach works well for most pure-play Shopify brands. Things get complicated once you expand into B2B, marketplaces, or retail. Let’s say your brand just launched B2B. You’ve got 3 reps on the road, pitching your assortment to boutiques and working to get your apparel into stores. But every time they close a deal, they encounter the same problem: “There is no inventory left to fulfill orders—it has already been consumed by online.” At GoodDay Software, we’ve created a retail operating system that enables virtual inventory management. This system allows your operations to adequately serve every demand channel. Here’s what’s working for these brands: 𝟭. 𝗦𝗲𝗴𝗺𝗲𝗻𝘁 𝗶𝗻𝘃𝗲𝗻𝘁𝗼𝗿𝘆 𝗮𝗰𝗿𝗼𝘀𝘀 𝘃𝗶𝗿𝘁𝘂𝗮𝗹 𝗽𝗼𝗼𝗹𝘀 To scale across ecommerce, marketplaces, retail, and wholesale, you need virtual inventory pools, which pre—allocate stock so that one channel doesn’t drain the others. 𝟮. 𝗧𝗿𝗮𝗰𝗸 𝗶𝗻𝘃𝗲𝗻𝘁𝗼𝗿𝘆 𝘀𝗵𝗶𝗳𝘁𝘀 𝗮𝘁 𝗹𝗲𝗮𝘀𝘁 𝘄𝗲𝗲𝗸𝗹𝘆, 𝗻𝗼𝘁 𝗺𝗼𝗻𝘁𝗵𝗹𝘆 Most brands plan demand monthly, but proper inventory management requires more frequent check-ins. You should study sell-through rates, incoming POs, and available stock across channels at least once a week. And, make operational optimizations to improve your inventory positions. 𝟯. 𝗔𝘂𝘁𝗼𝗺𝗮𝘁𝗲 𝗿𝗲𝗯𝗮𝗹𝗮𝗻𝗰𝗶𝗻𝗴 𝗳𝗼𝗿 𝘀𝗺𝗮𝗿𝘁 𝗮𝗹𝗹𝗼𝗰𝗮𝘁𝗶𝗼𝗻 As the number of demand channels continues to grow, the workload related to managing an omnichannel business expands as well. Or, does it? Future-ready brands will use AI-native inventory systems to continuously monitor stock across physical and virtual pools and dynamically help move inventory just-in-time to where demand is strongest. Omnichannel success starts with better inventory discipline. What’s your biggest challenge in managing stock across multiple channels? #inventory #DTC #retail