Velasca: MMM + GeoMatch to unlock incremental sales

Introduction

Velasca is an Italian-based high-end lifestyle brand for men and women and is known for its handcrafted shoes, apparel and accessories. 

It uses a direct supply chain that is responsible and that delivers high quality apparel at a fair value for both consumers and the craftsmen who invest their hard work into these.

Velasca is selling directly to consumers and has grown in 10 years into a global brand. All Velasca’s products bear the “Made in Italy” badge and are recognized for their style, quality and tradition. It now operates in numerous markets worldwide, across Europe and the United States. 

Challenge

Velasca adopted Cassandra, an AI-based Marketing Mix Modeling (MMM) and incrementality testing software, to plan its media allocation monthly. 

Velasca was faced with multiple challenges all at once: 

• A growing and diversified set of products, from shoes, to clothing and other accessories for men and women. This has had an impact on the average order value or the revenue generated from each order. How much advertising contributed to incremental revenue outside of seasonality and new assortment became a critical need. 

• A growing number of markets, each with its own specificities and media mix made it difficult to manage media allocation at scale.

• Numerous stores opening across key markets (Paris, Italy, Denmark, and New York in the United States) further complicated the challenge of understanding which part of the media mix was generating incremental top line commercial gains.

Solution & Impact

Velasca turned to an AI-based Marketing Mix solution in a very methodical way ensuring a data driven view of incremental performance for each channel in each market. 

1. First, Velasca started by reducing uncertainty for the channels with large spend and low confidence level on the Estimated Incremental ROI. It found out that experiments run using Cassandra’s GeoMatch in specific combinations of markets and channels help reduce the uncertainty around specific market and channel’s iROI. It built confidence in understanding whether there was room to invest more or if the saturation point was close to current investment.  

   
   
   

2. Second, they used the MMM outputs to identify the most impactful channels for each market. It means understanding which channel drives the higher Incremental Revenue estimates with low level of saturation. For instance, Search Advertising in Italy had an incremental ROI (iROI) between 3X and 9X, the highest of all channels for this market. 

   For the US, it was Social Media that had an incremental ROI (iROI) between 1.4 and 2.2: highest iROI of all Paid Marketing channels, but also the smallest confidence interval. It increased confidence in current and future investment in this channel and unlocked incremental sales.
   
   
   
   

   

   
   
   
   

3. Third, the Marketing team set up a process internally to leverage the Budget Allocator feature from the Cassandra platform, to continuously re-assess marketing investments on a monthly basis by market and by objective. It led to media mix allocation strategies that supported Velasca’s growth targets for each market.