Retail · Inventory Analytics

Inventory analytics: right SKU, right store, right moment.

Demand-aware forecasting, allocation, transfer, and replenishment across every SKU and every store — wired into RELEX, Blue Yonder, Oracle Retail, SAP IS-Retail, and Manhattan Active Omni.

allocation-desk · forecast
PLAN · PLN-7412
Q3 footwear · 18 stores
420 SKUs across women's / men's / kids'
SKU SIGNALS
Women's low-top
SKU 441 · 18 stores
Men's trail
SKU 216 · 12 stores
Kids' slip-on
SKU 072 · 16 stores
KLCC over-allocation
8 SKUs flagged
RECOMMENDED ACTIONS
Transfer recs ready100%
12 SKUs · 3 store pairs
Replenishment re-timed88%
4 stores · early dispatch
Markdown plan queued42%
slow-movers · 6wk horizon
FORECAST ACCURACY
Target 13% · under tolerance across women's / men's
FORECASTING…
relex · jda · oracle

What we build

Every layer of inventory decisioning — modelled.

Forecasts drive allocations. Allocations drive transfers. Transfers feed replenishment. Replenishment performance feeds back into forecasts. Each layer documented, versioned, and monitored.

Demand forecasting · SKU × store

LSTM demand models with promotional uplift per SKU × store × day — probabilistic forecasts with explainable drivers, benchmarked weekly against actuals.

Transfer recommendations

Graph-based transfer engine matches excess inventory at one store to gaps at another — respects size curves, service-level targets, and carrier lead times.

Replenishment optimisation

Right-time, right-quantity replenishment from DC to store — lead-time aware, supplier-SLA aware, and aligned to marketing calendar and weather outlook.

Stockout alerts + recovery plans

Real-time stockout detection at the shelf — with a recommended recovery plan (nearest-store transfer, emergency replen, or markdown avoidance) surfaced immediately.

New-launch allocation · cold start

First-time SKUs with zero historicals allocated using attribute-similarity regression, wishlist-match signals, and early sell-through feedback within 48 hours.

Markdown scheduling + shrinkage

Seasonal markdown cadence optimised against carry cost, recovery curves, and brand equity. Shrinkage analytics flag loss hotspots by store, SKU, and hour.

Use cases we model

Inventory decisions happen every hour. We model every one.

Fashion lifecycles, beauty velocity, regional demand curves, new-launch cold-start, markdown cadence, shrinkage patterns — each is a distinct decisioning problem, and each is wired into the same shared feature store and orchestration plane.

01

Fashion · seasonal collections

SS / FW / resort drops with short lifecycles — cold-start allocation, rapid transfer, and markdown scheduling that protect full-price sell-through.

02

Beauty · high-velocity SKUs

Skincare and fragrance with fast turnover, gift-with-purchase cadence, and dense store grids — hour-level stockout detection and recovery routing.

03

Lifestyle · 50+ store networks

Multi-city, multi-country networks where local demand shape differs per store — allocation respects regional size curves, local events, and weather outlooks.

04

New-launch planning

Pre-season planning and first-season allocation for SKUs with no historical signal — attribute similarity, wishlist match, and 48-hour early-read feedback.

05

Markdown + clearance

End-of-season markdown optimisation — cadence, depth, and location routing tuned against carry cost, recovery, and brand-equity constraints.

06

Shrinkage analytics

Shrinkage attribution by store, SKU family, and hour — pattern detection across checkout, stockroom, and transfer events with investigation-ready audit trails.

A walk-through

From ingest to forecast to learning — in five clear steps.

Follow an Asia-Pacific fashion retailer migrating from Excel-based allocation to AI-driven inventory optimisation — built around real stores, real SKUs, real outcomes.

DEPLOYMENT · DEP-7412
Kingston Apparel Holdings· 1,240 stores · 9 markets · 28k active SKUs
STEP 01 · 05
STEP 01 · INGEST
Bringing every signal in
Streaming POS sell-through, WMS positions, supplier lead times, promotional calendars, weather forecasts, and store footfall into one feature store — per SKU, per store, per day.
LIVE SOURCES
POS sell-through2.1M rows / day
WMS inventory position1,240 stores
Supplier lead-times146 suppliers
Promotion calendarQ3 loaded
Weather forecast9 markets · 14d
Footfall · sensors420 stores · LAG
FEATURE STORE
SKU × store × day72.4M rows
Feature freshnessavg 8 min
Schema versionv4.1 · stable
Partitioningby market × week
72M rows · avg 8-minute freshness

Model families we deploy

No single model covers every inventory decision. So we compose them.

Deep sequence models forecast, graph networks route, linear programming solves constraints, regression handles cold-start. Each model is evaluated and retrained independently, each contribution logged on every decision.

DEEP · SEQUENCE MODEL
Demand-forecast LSTM

Long-short-term-memory network over SKU × store × day features — promotional uplift, weather, footfall, local events. Quantile-regression output for probabilistic planning.

GRAPH NEURAL NETWORK
Transfer-recommendation GNN

Graph over stores with edges weighted by transfer cost and historical flow — computes optimal moves to rebalance inventory while respecting size curves and service levels.

LINEAR PROGRAMMING
Allocation-optimisation LP

Classical LP solver constrained by store capacity, size curve, service-level targets, and promotion calendar — fast enough to re-optimise on every receipt cycle.

ATTRIBUTE-SIMILARITY
New-launch cold-start regressor

Regression over product attributes (category, fabric, price band, design codes) and early sell-through feedback — produces first-week allocations for items with no history.

Data sources wired into every forecast

Every signal that moves a stock decision — integrated.

Pulled in real time, normalised into one SKU × store × day feature schema, versioned alongside the model that consumes them.

Source
What it unlocks
Providers
POS sell-through
Every unit sold, returned, or voided — SKU × store × day × hour. The ground truth behind every forecast, allocation, and sell-through diagnostic.
SAP CAROracle XstoreLightspeediVendSAP IS-Retail
Inventory position (WMS)
On-hand, on-order, in-transit, and reserved positions per SKU × location — updated multiple times an hour so the allocation engine never works from stale state.
Manhattan ActiveSAP EWMBlue Yonder WMSHighJumpInfor WMS
Supplier lead-time feed
Rolling supplier-performance and carrier-delivery signal — feeding replenishment lead-time assumptions and supplier-SLA performance scoring.
EDI 855/856ASN streamsSupplier portalsShipping trackersCarrier APIs
Marketing promotion calendar
Planned promotions, price changes, and GWP attachment by region — so forecasts and allocations anticipate promotional uplift instead of being surprised by it.
Trade calendarPrice fileGWP scheduleBundle rulesCountry-specific
Weather forecast
Per-store 14-day weather outlook — demand for certain categories (outerwear, footwear, cooling beauty) shifts materially with temperature and rainfall signals.
AccuWeatherWeather.com APIMet MalaysiaLocal bureaus14-day outlook
Store footfall
Hour-level traffic per store — the conversion denominator behind every sell-through metric and the leading signal behind local demand surprises.
Door countersCamera AIWi-Fi pingsMall reportsHour-level

Explainable forecasts, not black boxes

A number isn't enough. A merchant needs the drivers behind it.

Every forecast ships with its top drivers — promotion, weather, trend, cannibalisation, cold-start feedback — ranked and quantified. Merchants can trust it, challenge it, and override it with a full audit trail attached.

  • Top drivers per forecast with contribution weight
  • MAE / MAPE / bias reported per SKU × store × week
  • Override reasoning logged with approver chain
  • Weekly cycle review with merchandising leadership
FORECAST RECORD · FCR-7412
forecast.explain v4.1
SKU × store441 · KLCC
WeekW36 2026
Forecast units58 (p50)
Top driver 1trend · +0.34
Top driver 2promo · +0.22
Top driver 3weather · -0.08
Audit SHAc21a…8f40

Governance & audit

Defensible to merchandising, finance, and audit.

Every forecast accuracy band, every allocation decision, every markdown rule, every shrinkage investigation — logged immutably with audit export on demand. Merchants trust the recommendations. Finance trusts the trail.

Every point ships with the model. Audit-ready from day one.

Forecast-accuracy disclosure (MAE/MAPE)

Every forecast published with its accuracy band — MAE, MAPE, bias, and calibration. Disclosed to merchandising leadership weekly; defensible at board reviews.

Allocation-decision audit

Every allocation decision logged with feature inputs, model version, and constraint set. Traceable per SKU × store × cycle so overrides are explainable.

New-launch bias review

Cold-start allocations independently reviewed for brand, category, and region bias before dispatch — so first-season launches don't inherit the wrong history.

Supplier-data confidentiality

Supplier-specific cost, lead-time, and performance data segregated with role-based access. Cross-supplier comparisons aggregated only; never exposed raw.

Markdown-policy version control

Markdown rules versioned with reason codes, effective-date stamps, and approver chain — so pricing decisions at season-end are defensible and repeatable.

Shrinkage-investigation chain

Every shrinkage flag opens an investigation record — evidence, store-ops response, resolution, and outcome — retained for internal audit and insurance claims.

Frameworks we align to

GS1 standardsISO 28219SCOR modelEDI ANSI X.12ISO 27001SOC 2RSCTFairWorks

Why Axccelerate for inventory analytics

Not a forecasting module.
A decisioning plane.

A forecasting module gives you a number. Our decisioning plane gives you the forecast, the allocation, the transfer, the replenishment, and the reason codes — all wired to your existing RELEX / Blue Yonder / Oracle / SAP estate.

Feature
Axccelerate
Planning vendor
In-house
Per-SKU × store × day probabilistic forecasts
Varies
Transfer recommendations across locations
Varies
Cold-start allocation for new launches
Varies
Stockout detection + recovery plans · real-time
Varies
Markdown scheduling optimisation
Varies
Varies
Weather + footfall + calendar signal integration
Varies
Supplier SLA scoring + EDI lead-time feed
Varies
Varies
Shrinkage analytics + investigation chain
Varies
Integrates with RELEX · Blue Yonder · Oracle · SAP
Varies
No vendor lock-in · forecasts stay with the retailer

Pricing

Priced to the catalogue and fleet, not the forecast volume.

Inventory deployments are custom — we scope against your category count, store count, and planning-system shape before quoting.

Launch
Enquirefor pricing
Single category pilot

One category (footwear, RTW, beauty, or similar) piloted across your store network — forecast, allocation, and replenishment live within the first 8 weeks.

1 category · up to 50 stores
Demand forecast + allocation
POS + WMS integration
Weekly accuracy reporting
InsightAX reporting access
Enquire for pricing
Most popular
Scale
Enquirefor pricing
Full-catalogue forecasting

All active categories forecast across the store network — transfer recommendations, cold-start allocations, and markdown scheduling in the same orchestration plane.

Full catalogue · up to 500 stores
Transfer + replen + markdown
Cold-start new-launch engine
Supplier SLA scoring
Bi-weekly model reviews
Enquire for pricing
Fleet
Enquirefor pricing
Enterprise with transfer + replen

Enterprise deployment with dedicated forecasting engineering, custom model families, and regional sovereign hosting — for groups running 500+ stores across markets.

Unlimited stores + categories
Dedicated engineering team
Custom model families
24/7 monitoring + on-call
Regional sovereign hosting
Talk to us

FAQ

Common questions.

Don't see your question here?

Ask us directly

Glossary

The vocabulary behind every stock decision.

A quick reference for the language your merchandising, allocation, and planning teams use — and the terminology your planning-system vendors will reach for in conversations.

SKU
Stock Keeping Unit

The most granular product identifier — one variant (colour × size × pack) of a style. Forecasts, allocations, and replenishment all operate at SKU grain.

Sell-through
Units sold / units received

The share of received inventory that has actually been sold in a window. The headline health metric for seasonal and collection-driven categories.

Lead time
Order-to-delivery duration

Days between placing a replenishment order and receiving it at the destination. Drives safety-stock calculations and replenishment timing.

Safety stock
Buffer against demand variance

Extra inventory held to cover the uncertainty in demand between replenishment cycles. Sized from demand σ, service-level target, and lead time.

Replenishment
Restocking flow from DC to store

The regular cycle of moving inventory from distribution centres to stores to match forward demand — typically daily for fast-movers, weekly for slow ones.

Allocation
First-receipt store distribution

The decision of how many units of a newly received shipment to send to each store. Drives opening sell-through for new launches.

Transfer
Store-to-store inventory move

A sideways move of inventory between stores to correct allocation mistakes or respond to localised demand surges. Cheaper than markdown; faster than DC replen.

Markdown
Price reduction to clear

A deliberate price cut to accelerate sell-through on slow-moving or end-of-season inventory. Tradeoff between recovered revenue and brand-equity cost.

WOS
Weeks of Supply

On-hand inventory divided by average weekly demand — the headline measure of how long current stock will last. Key input to replenishment triggers.

Stockout
Zero on-hand at shelf

A SKU × store at zero on-hand while demand still exists. Direct lost sales, and a leading indicator of basket abandonment and channel switching.

Cold start
No historical signal

Allocation or forecasting for items with no (or near-zero) sales history. Requires attribute-similarity modelling, early-read feedback, and human-plus-AI review.

Cannibalisation
Uplift stealing from self-portfolio

When a new or promoted SKU's sales come at the expense of another SKU in the same portfolio rather than from new demand. Must be netted out of uplift calcs.

Size curve
Distribution of units across sizes

The expected proportion of demand by size within a style — varies by category, region, and customer profile. Wrong size curves cause breakage and lost sales.

Shrinkage
Inventory loss not explained by sale

The gap between book inventory and physical stock that isn't accounted for by legitimate sales, returns, or transfers — theft, damage, or process error.

Forecast-backed · audit-ready

Your inventory plane, engineered.

30-minute scoping with a senior engineer and an inventory-systems operator. You'll leave with a forecast plan, integration sketch, and realistic timeline — not a sales pitch.