Let us show you how to get assortment optimized for local demand in minutes. Download the case study to see why it makes sense.
Winning assortment starts from understanding the customer and changes in the demand. By default it means local customers, local demand – and local competition. And hence local stores.
That’s a far cry from present cluster approach that’s driven by summarized data and averages.
Our optimization algorithm calculates your next assortment in minutes, taking into account local demand and available space, enabling you to sell what people want to buy in right volumes.
Assortment optimized to local demand speaks volumes to your customers: it shows that you're listening and understand their needs.
Avoiding out-of-stock situations enhances your customer loyalty. Nothing makes a customer jump ship faster than empty shelf space.
With all the macro space data, factual category space data, your tactics and rules in one easy-to-access place you gain the capability to efficiently manage your store.
All the key data elements are stored in one place and visualized as Digital Twin of the store(s) allowing an efficient approach through the entire process of strategy planning, analyses and in-store implementation with digital planograms and instructions.
The benefits of moving from once siloed and manual processes to data driven, coherent and transparent workflow will empower everyone in your team to come up with new and creative solutions.
Efficient assortment means less missed sales opportunities and less capital tied to over-stocking your products.
Our optimization algorithm calculates exactly which products can be cut with an average of 10% margin increase estimation to a chosen planning period against the benchmark period.
Assortment in Space is a state-of-the-art, cloud-based SaaS service designed to optimize your assortment and shelf spacing.
It offers End-to-End process that takes you all the way from sales predictions to executing your assortment and space scenarios in stores.
A Modular Toolkit is designed to manage and execute at individual store level as well as clusters and chains of stores.
Store’s assortment or product mix is one of the key building blocks of your retail concept, your sales & bottom line and it is the key driver of your store’s differentiation in the market place.
Assortment in Space leverages data from different data sources.
The data typically includes store, shelf, module, loyalty card, shopper, POS, product etc. information which will be synchronized and enriched for Assortment in Space data model.
The category shelf space in stores vary, which makes it challenging to optimize the assortment and shelf space in stores. Therefore, having the true space data in digitalized format is essential for advanced store specific assortment and space optimization.
Assortment in Space leverages Artificial Intelligence, Machine Learning and state-of-the-art mathematical optimization model and predictive analytics - ensuring you to meet your local, store specific, shopper demand according to your strategy. You do not need to react to market – you’ll start to drive it.
Assortment in Space enables you to digitalize your true store space and manage both macro- & micro-level assortment and space, create your assortment and space scenarios based on your local shopper needs and your category assortment strategies.
It enables you to execute unique double loop optimization: First Assortment in Space enables you to optimize your store specific assortment based on each store’s local demand. Secondly, it enables you to combine optimized store specific assortment with each store’s true shelf space and optimize the space for each SKU based on you space management tactics and rules.
Like the name implies, it helps you to optimize assortment to local demand and factual store space.
Houston Analytics has a separate solution to find optimal store locations called Store Network Optimizer.
A mix of commercially available and open source technologies have been used. IBM Decision Optimization Studio (CPLEX) has been used for optimizations and IBM SPSS Modeler and IBM SPSS Collaboration & Deployment Services for predictive analytics. As the data warehouse IBM DB2 Enterprise Server has been used. Alternatively, Oracle Database or Microsoft Database can be used.