Image by Curtis MacNewton

Assortment planning

Fulfill customer needs and increase store sales, profit, inventory turnover with optimal product mix. 

 

Our SOLUTION

We developed three service AI empowered solution, each covering a certain stage of assortment management decisions, which ensures accurate demand planning, increases On-Shelf Availability, and develops Optimal Assortments - both at macro and SKU levels. It is achieved using Data Science and Machine Learning algorithms allowing at the same time to balance customer needs, store financial targets, merchandising rules and capacity constraints, commercial and delivery terms with suppliers, syndicated market data. 

Image by Peter Bond

1. Macro – level product mix

Allocate appropriate store space to different categories depending on shopper needs and store attributes (size, format, location features). Group stores to category specific clusters. 

Define each category assortment structure at sub-category and product attribute (taste, price, size, etc.) levels ensuring that it meets maximum shopper needs and maximize store financial KPIs.

Image by Franki Chamaki

2. SKU – level product mix

Choose correct single SKUs to satisfy shopper needs, maximize store sales, profit and inventory turnover, considering assortment structure, merchandising rules, available store space, as well as commercial terms with suppliers and syndicated market data. Take listing and de-listing decisions on single SKUs, brands, suppliers. Optimize assortment fulfilling costumer needs with less number of SKUs and minimize sales cannibalization. Prepare merchandising recommendations at SKU level with facings and shelf inventory. Provide continued assortment improvement insights. Evaluate decisions effect using What If... scenarios.

Image by Austin Distel

3. Inventory buying optimization

 

 

Optimize inventory in sales area and back rooms. Develop purchase plans which allow to avoid both Out of Stock and overstock based on accurate demand prognosis and existing supply chain terms. Simulate and optimize various supply chain scenarios. Estimate adequate safety stock based on supplier service level and sales volatility. Start auto ordering. 

WHY US

Shopping Basket
pirmas.png

Satisfied customers:

 

  • Segmented stores to category specific clusters 

  • Localized assortment 

  • Satisfied maximum shopper needs

  • Higher On-Shelf Availability (lower Out of Stock for about 30 – 60%

Investment Chart
antras.png

Better financial results:

  • Higher sales up to 4%

  • Higher gross margin up to 2.5 pp

  • Lower overstock for about 35 – 60%

  • Less capital invested in stock for about 10 – 20%

Financial Report
trecias.png

EFFECTIVE assortment MANAGEMENT:

  • Faster data driven decision making (about 4 times)

  • Efficient utilization of store space 

  • Shopper needs satisfied with less quantity of SKUs

  • Automated category manager's technical work

  • Evaluated decision's effect before it's implementation