PERIOD: 2018


Due to the critical role of key franchises for overall commercial success (Top 10 franchises make between 40-70% of overall revenue across the top sportswear brands), adidas wanted to gain deeper insights on how franchises should be managed and tracked along their lifecycles in the market.

Specifically, the client wanted to:

  • Understand Market Mechanics
  • Review Competitor Best Practices
  • Improve Franchise Management


As the scope of the analysis was on understanding life cycle mechanics and patterns one key challenge was to gain “long enough” historical timeseries data, especially for key franchises that are at later stages of the life cycle.

Another challenge was to identify success factors and leading indicators for franchises success across brands and categories.


TD Reply conducted an extensive Research Project analyzing 52 Franchises across 7 Brands in 5 sportswear categories.

Understand: Identification and fitting of franchise curves to statistical distributions, clustering of franchises by distribution parameters and splitting life cycles into stages

Locate: Creating a KPI set with benchmarks based on average stage performance to track franchise performance

Predict: Prediction of life cycle development in terms of the height & length of life cycles and stage entries

Steer: Development of lifecycle & portfolio frameworks (product launches, iterations, activations, …) to advance franchise management & planning

The analysis and modeling were based on around 1 Mio. data points and 17 KPIs including internal client’s data (e.g. article invest, sales and discounts), external market data (e.g. market shares) as well as digital data generated by TD Reply (e.g. google search, social media buzz and franchise image buzz).

Results of the project have been presented to the board and senior management across key business units and are used for portfolio and franchise lifecycle management decisions.




Drive strategy and execution from a brand perspective through a digital brand tracking system that can:

  • Measure the level of brand equity for adidas and competitors in near real-time 
  • Gives insights on how products, assets and campaigns are perceived and how they contribute to the overall brand perception
  • Measure the contribution of the brand to overall marketing success and sales


The initial challenge was to translate abstract brand personality and image items that have been tracked through traditional surveys into consumer language that enables us to track and analyze consumer conversations related to the brand drivers on a very granular level (besides overall brand perception we are able to understand how individual franchises, drops, technologies, assets etc. are perceived by consumers).

Another challenge within the project was to drive change and acceptance within the organization. As we know data projects are change projects, thus the internal communication together with the owner on the client side, was and still is a key aspect of the overall project.


TD Reply developed a new approach to track the brand values of adidas and key competitors by analyzing digital data. The process involved the following steps:

Brand Meaning: Itemization of adidas brand values by translating all brand-relevant dimensions into consumer language and identifying key digital brand drivers.

Brand Performance: Data Gathering and analysis of the Digital Brand Perception for adidas and Competitors on different levels:

  • Brand Level
  • Sport Category Level
  • Franchise / Asset Level
  • Campaign Level

Brand Mechanics: Creation of an Input-Output-Outcome Model to better understand Marketing Cause-and-effect relationships and optimize the allocation of brand assets to maximize brand impact.

The approach was developed and tested in the US as pilot market and is rolled out across markets (Germany, UK, France, Japan, China).




The main goal of adidas was the development of a forecasting engine and ongoing measurement approach that:

  • Can predict national footwear and apparel sales per sports category on a 5-year horizon more accurately and granular than existing forecasting data
  • Delivers deeper insights into the underlying category drivers
  • Can be scaled across key countries


  • Finding a proxy for the overall market development across multiple sport categories (like soccer footwear or basketball apparel).
  • Developing a prediction engine that is not only more accurate and granular than existing forecasting data, but also gives the client an understanding of category drivers.


TD Reply improved the existing forecasting results at adidas by applying a hypothesis-driven, advanced analytics process and by integrating new indicators and data sources (especially digital soundbox data sources like google search data as well as macro-economic indicators) into an enhanced forecasting engine.

Category Sales & Search Matching: Identification of google search term pairings that proxy category sales data. Creation of proxied category sales from 2004 to allow highly significant driver analysis.

5-Year Trend Driver Identification: Using macroeconomic and independent search data ruling out autoregressive predictions to identify category drivers.

5-Year Category Sales Prediction: Applying ensemble effect (3 overlaying models per category) for stable and actionable predictions

The approach was developed and tested in the US as pilot market and is now rolled out across EU 5 markets (Germany, UK, France, Spain and Italy).