Services for the European Open Science Cloud

Furniture Enterprise Analytics - DataFurn

Platform-as-a-Service data analytics for the furniture industry

Thanks to the spread of social media and on-line communities, furniture manufacturers now have access to a pool of readily available data on end-users’ preferences, opinions about brands and products, as well as to users willing to provide new ideas, assess solutions and co-design new products.

Manufacturers can extract a lot of value from contact with their customers, moving away from an outdated mass manufacturing scenario towards a more individualized production.

Furniture  designers can now take customers’ opinions into account in the design of innovative, more customized and trending products that customers demand.

In other words, companies will produce better products for more commercial value is they have a broader and clearer view of what their customers are discussing online.


Despite the tremendous data overflow our world witnesses, the furniture industry lags behind due to several inherent challenges:

  • (a) Social media tools monitor the global trends but they do not provide actionable insights to the domain’s SMEs;
  • (b) Furniture SMEs have a limited online presence and therefore the current content is biased towards larger brands;
  • (c) Trend prediction methods cannot easily distinguish between promotional and genuine content while facing significant difficulties when it comes to image recognition.
  • (d) Lack of a formalized digital strategy in the majority of furniture manufacturers

Work plan

The Furniture Enterprise Analytics pilot aims at designing and deploying a furniture analytics platform-as-a-service that collects, analyzes and visualizes online content (from popular social media platforms and blogs to online portals, in general), detects useful product-related content, extracts relevant furniture product-service topics/features, monitors brand influence and customer interactions and early predicts furniture trends for the upcoming seasons (e.g. regarding colors, styles and textiles).

In particular, the objectives of the pilot are:

  1. To specify and develop a data science-oriented, analytics dashboard that will leverage untapped furniture-related information, transform it into actionable knowledge through intuitive and user-friendly (not requiring any technical background) interfaces and act as a decision support system for any furniture SME.
  2. To experiment with state-of-the art prescriptive analytics techniques in the furniture domain (including semi-supervised machine learning algorithms for multi-lingual emotion analysis and multimedia & multi-source trend analysis).
  3. To pilot the outcomes in real-life with the help of a leading furniture association, that will populate a Linked-Big Furniture Data Infrastructure that stores, links and properly analyzes the right types of data at real-time in accordance with the specific needs of the furniture industry.