Menu
Menu
Shoeby was using a traditional replenishment system that could not let the team work as efficiently as they wanted to. Stock levels (min/max) were based on the initial distribution of the product and replenishment was set to maintain these initial levels throughout the whole season. This system could not take into account how well items performed at different stores, which was especially frustrating when dealing with limited collections where the same SKU would be in-demand at one location and marked down at another.
With a team of 6 merchandisers responsible for managing inventory at all 240 stores there was only time to manually optimize the high and lowperforming products (+/- 5%). The team also did not have the resources to analyze unique sales trends
of specific stores, which led to inaccurate sales predictions.
Shoeby wanted a way to optimize replenishment for all products that would improve sell-through and reduce the cost and waste of overstock. The company also needed an efficient solution that could be operated by a small team. They believed in a completely data driven decision making solution where the merchandisers can really trust the automated output and only need to check the outcomes for future unique events..
Shoeby chose the WAIR AI Replenisher to efficiently maximize the revenue of their stock. The AI Replenisher provides Shoeby with a deep learning learning model for replenishment of physical stores. It takes into account external data sources and Shoeby’s own retail specific data likeÂ
sales data, product information, local demand and individual store performance from Shoeby to make SKU-level sales predictions on store level that allow maximum revenue potential.
The model continuously learns from customer behavior and recommends small adjustments to replenishment that add up to big bottom-line improvements in sell-through rates, overstock reduction, and revenue growth.
The AI Replenisher is a layer of intelligence that easily integrates with a company’s enterprise resource planning (ERP) software. This facilitates teams to leverage the full power of WAIR directly from a familiar ERP interface. Shoeby implemented the AI Replenisher with Microsoft Dynamics 365, powered by ACA Fashion Software’s XPRT solution, in just 10 days.Â
Now, intelligent sales predictions are sent directly to the ERP. The detailed predictions are used to automatically adjust the minimum and maximum stocking limits. Shoeby merchandisers have the freedom to override recommendations, set business rules, and switch between algorithmic and manual control of any store, category, or SKU if needed.
With the AI Replenisher Shoeby is now able to execute a replenishment strategy that boosts the full-price sell-through rate of all products, in a fraction of the time it previously took them to only optimize the high and low performing articles.Â
Overstock
Understock
Overstock
Understock
WAIR is an Amsterdam based startup founded in 2019 with the idea that top-shelf technologies should be accessible to retailers of all sizes. With a team of retail experts and machine learning engineers working side-by-side, WAIR designs solutions that allow businesses to add automated intelligence without breaking processes or platforms and with low investment and high ROI.
1% increase in sell-through rate for full price is direct added revenue and margin. This is because the sky wouldn’t have sold as in mid season it was a stockout because the stock was laying in another store nor it was available in the warehouse.
The initial 1% (as showcased below) serves as a baseline figure. However, considering the demonstrated improvement in accuracy and the absence of any decrease in underprediction, this represents only the minimum expected outcome. The potential increase in the sell-through rate percentage can range anywhere from 1% to 20%.
| Calculation sheet | Forecast Accuracy | Overprediction | Underprediction |
|---|---|---|---|
| Traditional replenishment (Min/Max) | 78,1% | 21,8% | 0,1% |
| AI Replenisher | 95,4% | 4,4% | 0,3% |
| SKU Sales (new season & collections) | Forecast Accuracy | Overprediction | Underprediction |
| Traditional replenishment (Min/Max)Â | 2.460.410 | 687.037 | 4.097 |
| AI Replenisher | 3.005.312 | 138.668 | 7.879 |
| Improvement in % | 112% | ||
| Improvement in SKU | 544.902 | -548.369 | 3.782 |
| What happens with only +1% | 5.449 | ||
| Sell-through improvement | 0,2 % | ||
| Original Price (incl VAT) | € 35,66 | ||
| Below the line profit - EBT (incl VAT)* | € 194.312 | ||
| Reduced SKUs sent from Warehouse to Store | -10% | -54.837 | |
| Picking costs (Warehouse) per SKU | € 0,10 | € -5.484 | |
| Transportation Costs per SKU | € 0,19 | € -10.419 | |
| Distribution Savings** | € -15.903 | ||
| Total | €210.215 |
Additional Revenue /Margin (incl VAT)* – This is the expected additional revenue from the AI Replenisher. Distribution Savings** – Assuming 10% fewer overpredicted SKUs, which will save on distribution costs. Added benefits like: FTE automation, instore efficiency, customer experience improvement are not taken
At WAIR, we consider the 1% as the minimum benchmark due to the ever-changing dynamics of the fashion retail industry, making it challenging to precisely quantify our contributions. Our approach is to underpromise and overdeliver, ensuring we exceed expectations in our efforts.
