How to forecast Amazon inventory to prevent stockouts
The 12-week rolling forecast serious Amazon operators run in 2026: reorder points, safety stock, lead-time math, and the Days of Inventory thresholds that stop stockouts before they bleed rank.
By MaxPublished May 17, 2026Updated Oct 8, 202613 minAnalytics
Forecasting Amazon inventory is not a procurement problem. It is a profit problem. Every unit short of demand pushes your listing down the search ranks, triggers a low-inventory-level fee on standard-size SKUs, and burns paid traffic against an out-of-stock badge. Every unit over demand pays monthly storage, then aged-inventory surcharges starting at 181 days. The job is to thread the needle, week after week, across your entire catalog. Here is how serious operators do it in 2026.
Lead time, stock targets and on-order units put replenishment decisions in one view.
In short
โขForecasting on Amazon has to absorb three constraints retail does not face: low-inventory-level fees, Capacity Manager restock limits, and aged-inventory surcharges that kick in at 181 days.
โขThe base formula is unchanged: Reorder Point = (daily sales x lead time) + safety stock. What changed is that lead time now includes Amazon receive time, not just freight.
โขBuild three layers: 12-week operational, 6-month tactical, 12-month strategic. Each layer answers a different decision and runs on a different refresh cadence.
โขSell-through velocity, Days of Inventory, BSR trend, and seasonality index are the four inputs that drive 80 percent of forecast accuracy.
โขThe fastest gain is not a better model. It is hourly visibility into the inputs so your existing model is never run on stale data.
Our take
If you only do one thing this month
Pick your top 20 SKUs by revenue. Compute a 12-week forecast using the basic reorder-point formula, with safety stock tied to lead-time variance not a flat percentage. Then check actual vs forecast every Friday for 8 weeks. The point is not the model. The point is the discipline of comparing forecast to reality every week.
Best fit if
โขFBA and FBM sellers above $50K monthly revenue with 10+ active SKUs
โขBrands on 60-90 day overseas supplier cycles where one missed reorder costs a full quarter
โขAgencies and aggregators managing forecast across multiple accounts and marketplaces
Skip if
โขNew sellers under 5 SKUs where weekly manual counts are still tractable
โขPure 1P Vendor Central operations (Amazon handles replenishment differently)
What makes Amazon inventory forecasting different?
General retail forecasting boils down to one question: how many units will I sell, by when, and with what variance? Amazon adds three constraints that change the answer.
The first is the low-inventory-level fee, introduced in April 2024 for standard-size FBA SKUs with historically low days of supply. Under-forecast and you pay a per-unit penalty on top of every fulfilment fee. The second is restock limits set by Capacity Manager, which caps how much inbound volume you are allowed regardless of what your forecast says. Forecast 6,000 units, get approved for 4,000, and the remaining 2,000 either sits in a 3PL or pays an overage fee at auction. The third is the aged-inventory surcharge schedule that begins at 181 days and escalates sharply past 271 and 365 days.
Marketplace Pulse has been documenting the broader pattern for years: Amazon fees only go up, and the inventory-side fees are now where most of the variance hides. A forecast that ignores them is technically a forecast and operationally a guess.
Generic retail forecasting vs Amazon inventory forecasting
Variable
Generic retail
Amazon FBA
Lead time
Supplier + freight
Supplier + freight + Amazon receive (7-21 days)
Penalty for stockout
Lost sale + customer churn
Lost sale + search-rank decay + low-inventory fee
Penalty for overstock
Carrying cost
Storage + aged-inventory surcharge (181+ days)
Capacity ceiling
Warehouse space
Capacity Manager restock limit
Demand signal
POS data
SP-API sales + BSR + session data
Refresh cadence needed
Weekly
Hourly during peak season
Nova insight
Compare forecast units with actual units over the same window. Set safety stock from lead-time variability, and model Amazon receive time separately from supplier and transit lead time.
The forecasting formula that actually scales
The math is older than e-commerce. What changed is the inputs. The base reorder-point formula is:
Reorder Point = (Daily Sales x Lead Time) + Safety Stock
Where safety stock = Z x sigma_demand x sqrt(lead time), and Z = 1.65 for a 95 percent service level
eComEngine's reorder-point playbook walks through the same structure for FBA-specific use, and supplychainmath.com's safety stock guide covers the underlying Z-score table if you want to tune for a 90, 95, or 99 percent service level. The honest answer for most brands: 95 percent is the right anchor. 99 percent doubles your safety stock for marginal stockout-rate gains.
Decomposing Amazon lead time
The number that breaks most spreadsheets is lead time. On Amazon, total lead time has four components, and treating them as one number is the single biggest accuracy leak.
Production lead time. Supplier from PO to ready-to-ship. Usually 30 to 60 days for overseas manufacturing.
Freight transit. Ocean from origin port to US port, plus rail or trucking to the freight forwarder. 30 to 50 days for sea freight, 5 to 10 for air.
Inbound to Amazon. Carrier delivery to the assigned fulfilment centre after appointment booking. 3 to 14 days.
Amazon receive time. From dock arrival to units showing as sellable in inventory. 7 to 21 days, longer during Q4 peak.
Add it up and a "60 day lead time" assumption is more like 75 to 110 days end-to-end. Forecast against the short number and you stock out four weeks before the reorder lands.
One forecast cannot answer every question. The brands that get this right run three in parallel, each with a different horizon, refresh cadence, and decision use.
12-week operational. Refreshed weekly. Drives reorder triggers, removal-order decisions, and ad-budget adjustments when DOI drifts. Granularity: SKU x marketplace.
6-month tactical. Refreshed monthly. Drives promo calendar planning, Q4 staging, and supplier MOQ negotiation. Granularity: parent ASIN x category.
12-month strategic. Refreshed quarterly. Drives capacity bidding, brand-level cash budgeting, and SKU rationalisation decisions. Granularity: brand x country.
Nova insight
The tell that a brand has not yet built the three-layer view: the same spreadsheet is used to decide both "should we reorder unit 12345 this week" and "should we keep this brand at all next year". Those are different questions answered by different math.
Get the four inputs your forecast needs, with orders and units arriving in real time
Nova surfaces sell-through, Days of Inventory, BSR trends and P&L impact at SKU level across 23 marketplaces. The forecast model is yours. The inputs are clean.
The four inputs that drive 80 percent of forecast accuracy
Forecasting tooling has exploded in the last three years. Most of it solves the wrong problem. Better algorithms cannot save a forecast running on dirty or stale inputs. These four data points, refreshed at the right cadence, account for the majority of accuracy gains.
Daily unit sales show the changes in demand behind a replenishment forecast.
The four inputs and where they come from
Input
Why it matters
Refresh cadence
Sell-through velocity per SKU
Direct demand signal, last 30-90 days
in real time
Days of Inventory (DOI)
Reorder trigger and overstock alarm
Daily
BSR trend (7D, 30D, 90D)
Leading indicator of demand shifts
Daily
Seasonality index per SKU
Year-over-year monthly multiplier
Monthly
Nova surfaces all four natively. Sell-through and DOI sit in the FBA analytics view. BSR trends live in the BSR tracker. Seasonality indexes come out of the historical P&L data in the profit and loss module. None of that is forecasting per se. It is the input layer that any forecast model worth its name has to consume.
Pre-Nova setup was a Google Sheet refreshed every Monday by the operations lead with last 30-day velocity and a flat 21-day safety stock. Three of six SKUs went out of stock at least twice per quarter, costing roughly $180K in lost revenue and a 12-position search-rank slide on the worst offender. The brand also paid the low-inventory-level fee on two SKUs in Q1 2026 for the first time.
Stockout incidents / qtr
92.6
Forecast accuracy (8wk)
62%84%
Days of Inventory band
0-18040-65
Low-inventory-level fee
$3,200/qtr$0
How: The model itself did not change much. What changed was the input refresh cadence (weekly to daily) and decomposing lead time into its four components. Both shifts came directly from putting Nova between the spreadsheet and the raw Amazon data.
What most brands get wrong
A forecast can be sound on paper while execution breaks at three points.
Treating the average as the truth. Average daily sales over the last 30 days is a starting point, not the answer. Demand is rarely normal; it spikes around promos, seasonality, BSR jumps. Use a weighted average tilted toward the last 14 days for fast movers, last 60 days for stable movers.
Forgetting receive-time variance. Amazon's 7-21 day receive window during Q4 is not a fixed number. Track it per fulfilment centre and build the upper bound into your reorder timing, not the median.
Ignoring the cost of being right too late. Reordering when DOI hits 35 days "works" if your lead time is 35 days. It also leaves zero buffer for the 1-in-10 cycle where lead time creeps to 50. A forecast without a buffer assumption is a wish.
Nova insight
Check whether the TACoS target assumes full stock availability, and define when campaigns should pause as DOI approaches the reorder point. Connect the two systems and ad spend should automatically throttle when inventory falls below a defined floor.
How to start in one week
The trap is wanting a perfect forecasting system before you have a workable one. The brands that get this right ship something rough in week one and iterate. BigCommerce's FBA overview covers the foundational mechanics if you are still bedding down the basics.
Day 1 - Pick 20 SKUs. Top 20 by trailing 90-day revenue. Anything outside that does not need a model yet, just a DOI alarm.
Day 2 - Pull the four inputs. Sell-through, DOI, BSR trend, seasonality index. Either pull manually from Seller Central reports or wire up Nova for the hourly version.
Day 3 - Compute reorder points. Use the formula above with a real lead-time decomposition. Document the assumptions next to the SKU so the next person to look at it knows what to challenge.
Day 4 - Set DOI alerts. Green 30-90 days. Amber 14-30 days. Red below 14 or above 120. Same alarm structure across the catalog, even if some categories run wider naturally.
Day 5 - Schedule the Friday review. 30 minutes per week. Forecast vs actual, exception list of reds and ambers, decisions taken. Discipline beats sophistication.
Inside three months that loop produces a forecast accuracy gain that compounds: tighter safety stock means lower DOI on average, lower DOI means fewer aged-inventory surcharges, fewer surcharges mean higher contribution margin per SKU. The same operating discipline that runs your weekly cash review cadence also runs your inventory loop.
The bottom line
Amazon inventory forecasting is not about picking the cleverest model. It is about feeding a workable model the right inputs at the right cadence, then comparing forecast to actual every single week until your accuracy band tightens. Most brands jump straight to the model and starve it of fresh data. The result is a sophisticated forecast running on month-old velocity, missing the BSR jump that signalled the demand shift two weeks ago.
Build the inputs first. The math will look after itself.
Frequently asked questions
Start with sell-through velocity over the last 30 to 60 days, then add a safety-stock buffer sized to your supplier lead time. The base formula is: Reorder Point = (Average Daily Units Sold x Lead Time in Days) + Safety Stock. Safety stock is usually 1.65 x standard deviation of daily demand x square root of lead time for a 95 percent service level. That single calculation, refreshed weekly per SKU, beats gut-feel ordering at almost every catalog size.
Three reasons. First, Amazon now penalises both ends of the curve with a low-inventory-level fee on standard-size SKUs and an aged-inventory surcharge starting at 181 days. Second, your effective lead time includes Amazon receive times (often 7 to 21 days after the truck arrives at the warehouse), not just supplier and freight. Third, restock limits set by Capacity Manager cap how much you can send regardless of demand, so your forecast has to live inside that ceiling or you pay an overage fee.
Build a 12-week rolling forecast at minimum. Anything shorter and you cannot place a PO that covers production plus ocean freight from Asia (typically 60 to 90 days). Anything longer than 26 weeks and the assumptions decay faster than they help. Most brands keep three layers: a 12-week operational view for reorder triggers, a 6-month tactical view for promo and seasonality planning, and a 12-month strategic view for cash and capacity budgeting.
Five inputs: unit sales velocity per ASIN (last 30 to 90 days), seasonality index per SKU (year-over-year monthly multipliers), promotion calendar (Prime Day, Black Friday, planned discounts), supplier lead time distribution (not just the average), and Amazon receive-time distribution per fulfilment centre. Without all five you are guessing on at least one variable, which compounds across a multi-SKU catalog.
Nova surfaces the inputs every forecast needs: SKU-level sell-through, Days of Inventory across 23 marketplaces, BSR trends as a leading indicator, and the P&L impact of stockouts and aged-inventory surcharges hour by hour. The forecasting model itself lives in your spreadsheet, ERP, or BI tool. Nova feeds it clean numbers via the data warehouse export so the model is never starved or stale.
Use a three-month proxy from the closest analog SKU in your catalog, adjusted by category BSR rank and any review-velocity differential. Plan for the first 90 days to be wrong by 30 to 50 percent in either direction, and hold a tighter safety stock buffer until you have 8 weeks of real velocity. Refresh the forecast weekly during the launch window, not monthly.
Excess inventory accrues monthly storage fees and, after 181 days, the aged-inventory surcharge that scales sharply from 271 days onward. On a unit costing $5 with a $1.20 monthly storage charge, sitting 9 months instead of 3 erases roughly half your contribution margin. Catching the drift early with a Days of Inventory threshold (Nova flags anything over 90 days red) gives you a 30 to 60 day window to discount, bundle, or pull units back via removal orders before the surcharge curve bites.