At India Fashion Forum 2025, our CTO & Co-founder, Tusheet Shrivastava, highlighted the crucial problem of optimising merchandise planning for real-time store-level interventions.
- 40% of inventory never sells at full price
- 30% of styles fail to resonate with the local market
Why?
- Poor demand estimations
- Lengthy supply chain and production cycles
- Rapidly shifting customer preferences
- Inadequate SKU allocation at store level
The missing link? Real-time customer market trends and hyperlocal intelligence
GeoIQ bridges this gap by integrating:
Brands’ own data + Consumer preferences + Local market context + Footfall & store popularity dynamics
The result?
Optimised merchandise planning that maximises throughput, prevents over stocking and under stocking, and eliminates the inventory shuffle across stores.
Watch this snippet to see how data-driven interventions are shaping the future of fashion retail!
#GeoIQ#IndiaFashionForum#RetailTech#FashionRetail#MerchandisePlanning#RetailAnalytics#LocationIntelligence
So a big problem that we always hear from our clients is like almost 40% of their inventory doesn't get sold at full price. And this is like a industry wide worldwide problem and even like 30% of the of the styles, they failed to resonate with the local market. The primary reason why such a thing happens is because of poor demand estimations. And demand estimations are particularly harder in this industry because of such long sales, such long complex supply chain cycles, like most brands operate with six months to even nine months long planning and production cycles. This combined with the fact that there's a rapidly changing customer preferences even complicates the problem. And even if you estimate the demand correctly, whether one more important aspect is you have to place the correct items at the correct stores. So the allocation is also a big challenge. The current demand process usually only takes into account the internal data of the company, the historical sales performance data of the company. So they just they look at what kind of styles and sizes have sold this year and they will plan for them accordingly in the next year. What this whole process fails to incorporate is there, there's no market context, there's no data around what kind of friends are actually going to go up next year, whether they will go down next year, even if they sold better this year. All of this is completely missing. And this is what causes the errors in the demand estimations. So what the future of merchandise planning would look like and this every retailer I believe wants to do, but they are not able to. So of course there's this brand's own internal data, the loyalty data, the seasonality, weather patterns that brands also somewhat take into account. But this data needs to be combined with the consumer preferences and the particularly the location context of the of each and every store. And how the brands presence and popularity and footballs are changing in an across all the different stores that they have.
