MySales modules

AI Assortment PlanningCapabilities

AI-powered assortment planning that helps retailers decide which SKUs each store should keep, add, localize, or delist, balancing customer relevance, shelf space, and profitability.

94%
Forecast Accuracy

Established product accuracy at Drogas

15-20%
Revenue Growth

Turnover increase at Chudo Market after deployment

40%
Waste Reduction

Fresh write-off reduction at Blyzenko

AI Platform

One AI platform connects forecasting, replenishment, pricing, and promos - signals flow automatically between modules, so orders, prices, and campaigns stay in sync.

Module overview

Why retailers need AI assortment planning

Assortment decisions are rarely chain-wide in practice.

Store size, mission, region, customer profile, local competition, and space constraints all change what the right range looks like.

Without modelling, retailers often keep duplicate SKUs, miss local demand, and overload stores with low-productivity items.

  • Chain-wide assortments often ignore local demand differences.
  • Duplicate variants add complexity without incremental value.
  • Low-rotation SKUs consume working capital and shelf space.
  • New item and delisting decisions are hard to validate in advance.
Key capabilities

Key capabilities

MySales supports assortment planning as a continuous decision process rather than a once-a-year reset.

Teams can review recommendations at category, cluster, store, and SKU level.

Forecast expected sales by SKU, store, cluster, and season to recommend where each item belongs.

Estimate what customers buy instead when a SKU is missing, and where similar products are stealing volume from each other.

Balance category width, variant depth, facings, and shelf constraints to improve sales density and reduce shelf waste.

Identify low-value duplication, support delisting decisions, and estimate likely performance of new SKUs before rollout.

Business impact

Business impact

Retailers use assortment planning to increase relevance without increasing complexity. The objective is not more SKUs, but a better mix of SKUs by store.

  • Higher sales per square meter
  • Better gross margin and GMROI
  • Lower dead stock and markdown risk
  • Stronger local relevance by store cluster
  • Faster, more defensible category reviews
Operating model

Workflow

A typical assortment planning cycle combines model outputs with merchant review and operational constraints.

Cluster stores by format, size, region, and customer mission.

Model baseline demand, seasonality, substitution, and cannibalization.

Simulate add, keep, reduce, and delist scenarios at SKU and category level.

Apply shelf space, supplier, and commercial constraints.

Publish store- or cluster-level recommendations and track post-change performance.

Implementation & data

Data and implementation

The module works best when connected to transaction history, inventory, product hierarchy, promotions, store attributes, and planogram or space constraints where available.

It can be deployed alongside Forecasting and Replenishment so assortment decisions translate into better ordering, stock targets, and category execution.

  • POS sales and stock history
  • Product hierarchy and attributes
  • Store metadata and clustering inputs
  • Price and promotion history
  • Supplier constraints and commercial rules
  • Shelf capacity or planogram data, if available
Insight

Recommended modules

Assortment planning is strongest when connected to the rest of the MySales decision stack.

Module
How it helps
Forecasting
Quantifies localized demand and seasonal demand shifts before assortment changes are rolled out.
Replenishment
Turns the chosen assortment into store-level ordering logic and service-level control.
Promo
Evaluates how campaigns affect permanent assortment value, substitution, and category mix.