With the introduction of Product Forecasting to Style Arcade’s suite of AI-driven and intelligent automation tools, this case study reveals how our analysis uncovered untapped revenue and operational blind spots for the first 10 brands to use the tool.
The Numbers
Number of brands: 10
Average business size: $76m
Average core lines: 106
Average lost revenue: $4.1m, 5% company revenue
Using Style Arcade Forecasting: 5% average additional company revenue
The Challenge
The operational blind spot
The first ten brands to adopt Style Arcade's Product Forecasting tool had to begin by making a fundamental shift in how they approached forecasting.
These teams were manually forecasting in spreadsheets, without forecasting by size. This is detrimental to accurate forecasting, because, firstly, trying to forecast this way is a near-impossible task.
No buyer or planner can quickly or accurately calculate hundreds of core lines by size with manual BI tools. For a size curve with 7 sizes, for example, the planner would have to multiply every plan 7 times to accommodate the numbers in an Excel spreadsheet. This is why planners simply don't have the capacity to complete their forecasting plans by size.
The cost of size breaks
Secondly, many retailers are still comparing the sales units versus the intake units in each size across a given timeframe, to determine the rate of sale and make new size ratio decisions. However, this method does not take into account when the size curve broke, if the size sold was out, if the product was discounted, or how aged the stock was.
When a size breaks in the curve, the product’s Size Availability immediately drops to 80%, or for popular products, as low as 40%. In modern retail, forecasting blanket quantities across sizes just won’t cut it.
"...they found they were losing, on average, not 5% of their core line revenue, but 5% of their total company revenue using manual forecasting."
With this in mind, the brands began by assessing the missed sales opportunities created by stockouts over the last 12 months, broken down by product and size.
That number, if managed well, should be close to zero.
All the brands on average, had a turnover of 75 million and around 106 core lines. By assessing the opportunities, they found they were losing, on average, not 5% of their core line revenue, but 5% of their total company revenue using manual forecasting.
The Solution
When it comes to manual forecasting, most brands and retailers are just looking at the top line. From the top line view, planners are only seeing the number of weeks of stock cover, where most brands consider 12-16 weeks cover as sufficient.
However, the brands had been overlooking Size Availability, down to Store Size Availability.
Had they considered how fragmented the sizes are for this product across the entire fleet of stores, including online?
The missing KPI
There's a store size availability metric that is clearly missing as a key KPI for fashion retailers.
Store Size Availability should always be 100%.
The current weeks cover for these brands masked the fact that while a whole lot of stores were sitting on technically ‘available’ sizes, they weren’t the sizes that were actually in-demand from customers. When you have a large amount of units sitting in the low-demand sizes, this gives you an inflated cover metric and the appearance of healthy stock cover.
However, the true data, masked by the inflated weeks of cover, will tell you that the highest-demand sizes were fragmented by product and by store. This results in frequent stock-outs. When you multiply these missed sales opportunities across every core product and every store, the scale of the untapped revenue becomes significant.
The Results
The 10 brands, though varying in production lead times, experienced rapid turnaround on gaining opportunities with their size curves using Style Arcade’s Product Forecasting tool and gain an avergae of 5% additional company revenue.
The study found brands and retailers can, within 12 weeks, get back to the key KPI: 100% in-stock rate, for all core lines in all stores, as the planners are now only ordering the sizes the sales channels actually need.
Once you stop ordering by a bell curve, you start ordering only the exact sizes that you need, by product and by store.
"Once you stop ordering by a bell curve, you start ordering only the exact sizes that you need, by product and by store."
This will fix the revenue gap, where you have the opportunity to gain the extra 5% of revenue.
By keeping the key KPI, core line in stock rate, on track (meaning: Size Availability by product, by store, and by core line is 100%), then your weeks of stock cover will begin to decrease as you’re only ordering the sizes that you need.
The Benefits
Style Arcade’s AI-driven Product Forecasting tool allows brands and retailers to benefit from:
- Smarter size curves: Predict demand based on the True Rate of Sale of the product, that is, when all sizes were in stock, not when sizes have been fragmented or discounting has occurred.
- Automatic demand forecasts by product, size, and location. Granular forecasting is essential, by SKU, category, size, and geography, with the flexibility to adjust for current assortment changes and external factors.
- Aligning delivery and supply chain timelines: Customizable weeks cover, lead times, and delivery frequencies based on specific periods to optimize sales to ensure you have inventory when you need it.
- Visualizing future cash flow: Seeing when sales are set to peak and trough enables brands to drive revenue through smarter stock planning and financial alignment with sales events.
Key Takeaways
1. Manual forecasting was costing brands millions in missed revenue
- 10 brands with an average turnover of $76 million and 106 core lines were found to be losing an average of $4.1 million per year.
- This equated to 5% of total company revenue as a result of forecasting without accounting for size-level demand.
2. Traditional stock cover metrics were masking stock availability issues
- Despite carrying what appeared to be a healthy 12–16 weeks of stock cover, brands were frequently out of the sizes customers actually wanted.
- Once a size breaks in the curve, Size Availability immediately drops to around 80%, creating hidden lost sales despite inventory appearing available.
3. Core line size availability by store can recover quickly with AI-driven forecasting
- Within 12 weeks (subject to production lead times), brands could return to a target of 100% in-stock availability for core lines across stores
- This unlocked an average 5% uplift in company revenue while reducing unnecessary stock cover.
.avif)
.avif)