Forecasting moduleAI Assistant · MCP

    AI Demand Forecasting for Every SKU

    Most planning tools run one forecasting model across the whole catalog, and it's the wrong model for most products. buffers.ai backtests five models on every SKU's own history, forecasts each one with the model that actually performed best, and turns that forecast into a purchase plan.

    Built forDemand planners, supply planners and purchasing teams buying for a central warehouse across a large SKU catalog.

    5
    Models backtested on every SKU
    21,600
    Backtests in our public benchmark
    36.2%
    Best single model's win rate: no model fits all
    BACKTEST WINDOWJUN ’24JUN ’25JUN ’26
    AI Assistant
    • Question: Why did the December forecast for SKU 4471 jump 40%? Answer: Last December's promotion repeats this year, and LightGBM, this SKU's champion with a 14% backtest WAPE, carries that lift. Do you want to see the backtest comparison, or forecast December without the promotion?
    • Question: How much kids' footwear should we order from the supplier next month? Answer: Forecast demand is 4,200 pairs. After stock on hand and open purchase orders, and rounded to the supplier's MOQ, I recommend ordering 2,850 pairs. Shall I draft the PO, or show the split by size first?
    • Question: Which forecasts should I trust least right now? Answer: 12 SKUs have a WAPE above 35%, mostly items with intermittent sales. I can forecast them at the style-family level and split back down by size curve. Want me to do that?
    Forecasting: Champion model per SKU

    Demand → Forecast → Purchase plan

    1. Step 1

      Demand

      Each SKU's daily sales history. Past promotions and events are measured from it, not entered by hand.

    2. Step 2

      Champion forecast

      Five models backtested per SKU; the best performer on WAPE and bias forecasts it.

    3. Step 3

      Purchase plan

      The forecast becomes order quantities after lead time, safety stock, MOQs, budget and open commitments.

    New · AI Assistant

    Run Forecasting by conversation

    Control the Forecasting module with a conversational AI Assistant and query your own data in plain language. Ask about a SKU, a category or a supplier order, get a recommendation, and let the assistant carry it out once you approve.

    • Control the system by conversationCreate a push, draft a purchase order or change the plan just by asking. The assistant prepares the action and carries it out once you confirm.
    • Query your data in plain languageAsk about any store, category, SKU or month the way you'd ask a colleague. No reports to build, no filters to set.
    • See the reasoningEvery answer comes with the numbers behind it, and you can open the full breakdown before deciding.
    MCP supportedModel Context Protocolbuffers.ai supports the Model Context Protocol (MCP), so the AI assistants and agents your team already uses can query your data and work with the system too.

    Try asking

    • Which model is the champion for SKU 1023, and why?
    • Compare this month's forecast with last year's actuals.
    • What's the forecast bias for Home Fragrance?
    • Which SKUs have the highest WAPE this month?
    • Which SKUs need a PO this week to stay above safety stock?
    • How does a two-week supplier delay change our orders?
    The champion model

    One model never fits every SKU

    A fast-moving basic, a seasonal fashion item and a slow seller with sporadic sales need different models. Instead of assuming one works for everything, buffers.ai measures which one does, product by product.

    1. 01

      Backtest every model

      Each SKU's own sales history runs through all five engines over a rolling six-month window, on data none of them has seen.

    2. 02

      Score on WAPE and bias

      WAPE measures how far off each forecast ran against total actual demand; bias shows whether it systematically over- or under-forecasts.

    3. 03

      Crown a champion per SKU

      The closest fit forecasts that SKU. Champions are re-scored on a rolling basis, so a different model takes over when it starts performing better.

    buffers.ai forecasting backtest: monthly actuals plotted against the forecasts of several models for one SKU
    A real backtest: each model's forecast plotted against actual sales for one SKU, before a champion is picked.
    Read how the champion model is chosenSee the forecast model benchmarkSee the backtest screenshots
    The field

    Five engines, one winner per SKU

    We don't bet on a single algorithm. All five run on every product, from a foundation model down to a plain average, and the backtest decides.

    • Foundation model

      TimesFM

      Created byGoogle

      A time-series foundation model, pre-trained on billions of points, then pointed at your demand.

      Strengths
      Captures nonlinear demand patterns and transfers what it learned from other series, so it performs well with little SKU-specific history.
      Watch out for
      Less interpretable than statistical models, and heavier to run at scale.

      Best for: New products, fast-fashion items and categories with irregular or trending demand.

    • Gradient-boosted trees

      LightGBM

      Created byMicrosoft

      Trained across the whole catalogue, reading product attributes (color, price, season, style) so similar products inform each other.

      Strengths
      Handles nonlinear relationships and many inputs at once; fast to train and score across a large catalog.
      Watch out for
      Needs enough history to learn reliable relationships between attributes and demand.

      Best for: Trending products and large catalogs where similar items share demand patterns.

    • Trend + seasonality

      Prophet

      Created byMeta

      Decomposes demand into trend and seasonal waves: sturdy, interpretable, hard to beat.

      Strengths
      Explicit, interpretable seasonality; robust to missing data and outliers; easy to see why it forecasts what it does.
      Watch out for
      Assumes seasonality is fairly regular from year to year.

      Best for: Seasonal products with recurring calendar patterns: holiday goods, seasonal apparel, weather-linked categories.

    • Holt-Winters family

      Exponential Smoothing

      Created byBrown, Holt & Winters (1950s)

      Classical exponential smoothing, weighting recent sales most heavily: the line every fancier model has to clear to earn its keep.

      Strengths
      Simple, fast and well understood; produces a stable forecast from little data.
      Watch out for
      Struggles with complex, nonlinear shifts in demand.

      Best for: Stable-demand staples and steadily seasonal products.

    • Day-of-week average

      Moving Average

      OriginClassical statistics

      A plain day-of-week average of recent weeks. No parameters, the simplest yardstick in the field.

      Strengths
      Extremely transparent and hard to overfit; a strong baseline for very stable SKUs.
      Watch out for
      Reacts slowly to genuine shifts in demand and can't model trend.

      Best for: Low-volume, low-variance SKUs where simplicity beats complexity.

    Capabilities

    From backtest to purchase order

    The champion forecast is the start. Promotions, new products and supply constraints are handled before it reaches a purchase recommendation.

    / Forecasting

    Backtest & Champion Selection

    Race 5 forecasting engines, crown the best fit per SKU

    Every SKU's sales history runs through five forecasting engines — TimesFM (Google), LightGBM (Microsoft), Prophet (Meta), Exponential Smoothing, and Moving Average — backtested over a rolling six-month window on data none of them has seen. Each model is scored on WAPE, bias, safety stock, and service level, and the closest fit is crowned the champion for that SKU.

    Function
    5-engine backtest: TimesFM, LightGBM, Prophet, Exponential Smoothing, Moving Average
    Optimizes for
    Forecast accuracy per SKU, scored on WAPE, bias, safety stock, service level
    / Forecasting

    Blended Demand Build

    Build the demand signal from the champion model

    Once a champion algorithm is selected per SKU, buffers.ai builds a blended demand forecast from its output — the single demand number that feeds every downstream buffer, replenishment, and supply calculation.

    Function
    Demand signal construction from each SKU's champion forecasting model
    Optimizes for
    Forecast accuracy feeding the supply calculation
    / Forecasting

    Supply Calculation

    Turn the demand forecast into a purchase order

    Converts the blended demand forecast into a purchase recommendation, accounting for lead time, safety stock, minimum order quantities, budget limits, and open commitments.

    Function
    Lead time, safety stock, minimum order quantity, budget, and commitments applied to the blended forecast
    Optimizes for
    Right-sized purchase orders within budget and commitment constraints
    / Forecasting

    Promotion Uplift

    Measure each promotion's real lift, then forecast the next one with it

    Every past promotion is measured on each SKU's own sales: average daily demand during the event against a clean baseline of the four weeks before and after it, with other event days left out and repeat runs of the same event pooled. A future promotion points at a comparable past one and inherits its measured lift, so a brand-new promo is forecast from real history instead of a guess. Prophet reads the events directly as holidays; the other engines get the measured lift applied to the forecast on the promotion days. One-off events nobody planned are smoothed out of the training data so they don't skew the model.

    Example: one Category A SKU, a 7-day sale copied from last spring's

    Measured: last spring's 30%-off sale

    Baseline
    50/day
    During the sale
    82/day

    Applied: this summer's sale, same 7 days

    Model forecast
    55/day
    With uplift
    90/day
    Measured lift
    82 / 50 − 1 = +64%
    Applied to the forecast
    55 × 1.64 = 90.2/day
    Over the 7 days
    385 → 631 units
    Function
    Per-SKU promotion lift measured from history and applied to future promotion days
    Optimizes for
    Forecast accuracy through promotions, without one-off spikes distorting the baseline
    / Forecasting

    Family Forecast & Size Curve

    Forecast the style family, then split it back down to every size

    In footwear and apparel a single SKU (one style, colour and size) often sells only a couple of units a season, far too few for any model to forecast reliably. So buffers.ai forecasts one level up, at the style family, where demand is strong enough for the backtest and champion selection to work. That family forecast is then split back down to the SKUs you actually order. Colourways get their share from recent sales, so a new colourway or version takes over from the old one. Sizes and widths get their share from a size curve: the size mix is mostly a property of the store's customers, not of the shoe, so it is learned across every family in the same category and gender, and each family's own sales nudge it in proportion to how much that family has sold. Each size then orders a service-level quantity of its expected demand instead of a plain round, so a size expected to sell 0.4 units isn't silently dropped.

    Example: a men's footwear size curve, learned from 6,328 units sold
    buffers.ai size curve for men's footwear: share of units by size and width, peaking at 15.7% for size 9 D and falling to under 1% for wide EE widths
    1. Family forecast

      Forecast the style family, where there is enough demand to read

    2. × Colourway share

      Split by what each colourway sold recently

    3. × Size curve

      Split by the size and width mix of the store's customers

    4. = SKU order

      Each size rounded up to a service-level quantity, not a plain round

    Function
    Family-level forecast split to SKUs by colourway share and a pooled size-and-width curve
    Optimizes for
    A reliable forecast for thin, size-run SKUs and a size-by-size order quantity
    / Forecasting

    Forecast every SKU with the model that fits it

    Champion selection, WAPE and bias per SKU, and a supply calculation that turns the forecast into purchase quantities.

    See pricing
    Go deeper
    How buffers.ai chooses the best forecastThe full champion-model explanation: the five algorithms, backtesting, WAPE, bias and re-scoring.Forecast model benchmark21,600 backtests across 9 retail catalogs and 6 horizons: which model wins, and why it changes.Planning slow-moving, high-value SKUsLuxury styles that sell one unit a season: family forecasts, service-level buying, and rebalancing.
    Forecasting FAQ

    Frequently Asked Questions

    The platform

    One platform, three modules

    Each module is licensed on its own. Start with the one that solves today's problem and add the others when you need them.