August 21, 2023

OFM boost forecast

accuracy by 29,28%

The Challenge

OFM was using a traditional replenishment system to keep the initial distribution intact without adapting stock levels based on demand.

The Solution 

OFM transformed their stock management with WAIR’s AI Replenisher, leveraging accurate sales forecasts and seamless ERP integration to strategically allocate stock, improve sell-through rates, and achieve significant growth.

The Results 

Traditional vs AI Replenisher

Forecast accuracy:    66% vs. 95%
Overprediction:           34% vs 5%
Underprediction:        0% vs. 0%Amount

Amount increase of SKUs rightfully predicted: 299.000

About OFM 

OFM (Only For Men) is a popular Dutch men’s fashion retailer with 21 large stores and a webshop. OFM is a convenient one-stop shop where men can find outfits and accessories for any occasion. Some stores even offer services like haircuts and a place to relax with a  beer.  OFM sells 321k  items a year of the relevant seasons (in regular stores), with 5.2k styles and 25k SKUs.

The Challenge

OFM was using a traditional replenishment system that was not efficient in maximising  sell-through rates. The system set stock levels (minimum and maximum) based on the initial distribution of products and maintained those levels throughout the season. However, this system did not consider how well items performed in different stores.  This led to a stock push strategy while a pull strategy based on demand was preferred.

 As a result, the central warehouse was often out of stock for certain products and many stores there was clear overstock or understock. This led to the need to redistribute inventory, which proved to be a costly and time-consuming process. This situation always causes increased expenses for packaging, handling, and transportation. Moreover, when items are constantly

The Solution 

The Solution 
Based on a simulation of OFM’s retail operations, OFM revolutionised their replenishment process by adopting WAIR’s AI Replenisher, a cutting-edge solution that optimises revenue through efficient stock replenishment. By leveraging WAIR’s proprietary deep learning model designed specifically for fashion retail, OFM receives accurate sales forecasts to restock their physical stores. The AI model takes into account both external data resources and retailer specific data like  sales data, product information, local demand, and individual store performance, enabling SKU-level sales predictions. This empowers OFM to strategically allocate stock based on revenue potential, ensuring their physical stores are replenished in accordance with demand.
Through constant analysis of customer behaviour, the model consistently recommends incremental replenishment adjustments. These cumulative adjustments have a substantial impact, leading to notable improvements in sell-through rates untill sales, a decrease in both overstock and understock, and significant revenue growth.
The AI Replenisher seamlessly integrates with a company’s ERP software, providing teams with convenient access to WAIR’s complete functionalities directly from their familiar ERP interface. 

OFM successfully incorporated the AI Replenisher into their Microsoft Dynamics 365 system using ACA Fashion Software’s XPRT solution.

Via the implementation, the ERP system receives intelligent sales predictions, enabling automatic adjustments to the minimum and maximum stocking limits. OFM’s merchandisers have the flexibility to override recommendations, establish customised business rules, and seamlessly switch between algorithmic and manual control for specific stores, categories, or SKUs, catering to their unique requirements.

The Results

With the AI Replenisher, OFM transitioned from a standard rule-based replenishment process to implementing unique replenishment actions per SKU/store.

By significantly enhancing forecast accuracy from 65% to 95% and drastically reducing overpredictions from 34% to 5%, OFM has made substantial improvements in their stock profits.
Traditional replenisher



Over prediction


under prediction

The AI Replenisher



Over prediction


under prediction

34% to 5%

reducing overpredictions

65% to 95%

Replenishment forecast accuracy

0% to 0%

Under prediction - meaning zero risk when implemented

About WAIR

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.

Calculation sheet 

Below some additional calculations on the added value of the AI Replenisher at Shoeby. It’s important to note that these calculations make certain assumptions (conservatively estimated), as there are numerous other variables that can impact its performance.

For instance: 

1% increase in sell-through rate for full price is direct added revenue and margin.
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) 65,96% 33,90% 0,14%
AI Replenisher 95,3% 6,82% 0,3%
SKU Sales (new season & collections) Forecast Accuracy Overprediction Underprediction
Traditional replenishment (Min/Max) 212.364 109.144 451
AI Replenisher 306.956 14.037 966
Improvement in % 145%
Improvement in SKU 94.592 -95.107 515
What happens with only +1% 946
Sell-through improvement 0,3%
Original Price (incl VAT) € 98,22
Below the line profit - EBT (incl VAT)* € 92.908
Reduced SKUs sent from Warehouse to Store -10% -9.511
Picking costs (Warehouse) per SKU € 0,10 € -951
Transportation Costs per SKU € 0,19 € -1.807
Distribution Savings** € -2.758
Total €95.666

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.

We are more than happy to explain more about these calculations and our case studies please feel free to contact us

Related Cases

Van Dal mannenmodeCASE STUDY
January 23, 2024
August 19, 2023
August 19, 2023