ARROWS – Aesthetics-based recommender
system for web shops
In ARROWS we will develop technology for web shops that recommends products to
customers based on their individual aesthetic preferences. As small shopping systems do not
possess a sufficiently large database for state of the art item-to-item or user-to-user
recommendations, we will develop prediction models that do not require existing databases.
When visiting a furniture store such as IKEA we can observe an interesting phenomenon.
Although we wanted to buy a single, specific product we also add items such as candles, an
indoor palm tree, napkins, a wooden box, and a pillow. Within ARES we want to address the
question of how such buying behaviour can be elicited in online shops.
The choice of additional items that we buy is not based on functionality or product categories,
but on aesthetic preference. Recommendation systems of online shops (“costumers who
bought this item also bought ….” or “… frequently bought together”) that fail to capture the
aesthetics of a product will miss an opportunity of selling such additional products.
In ARROWS we will develop technology for online shopping portals that recommends
products to customers based on their individual aesthetic preferences.
The major benefits of ARROWS are
- an individual product collection is presented to the customer
- the recommendation system works on the personal preference level and is not
bound to product categories or functionality
- products can be grouped and visualized according to their aesthetic properties
- small online shops rarely own a large database to allow product specific
recommendation systems – here more general prediction models can offer
recommendations without requiring an initial database
- in contrast to existing item-to-item or user-to-user recommendations, new products
can be integrated without additional efforts such as definition of meta-information or
assignment to product categories into the recommendation system
The main technical result of ARROWS will be software libraries that are able to predict
aesthetic properties of products based on images of the products. A predictive model that is
calibrated through experimental procedures will use colour, texture and shape information to
predict aesthetic properties.
The main benefit of ARROWS for SMEs (designers and operators of online shopping
systems) is that customized product recommendations are available from the very first
customer, without requiring an existing database of user preferences. Once the predictive
model is calibrated for a particular context (e.g. furniture stores), it can be easily transferred
between different online shops and refined based on collected user preferences.
confidential project idea
partners sought and role in the project
We are looking for 2-3 partners in the following fields, to complete our consortium:
- design and implementation of online shopping systems / portals
- end-users that operate online shops with medium to large product collections
Role of the partners within the project:
- provide specification for software that will be developed within ARROWS
- provide typical use cases and sample data (e.g. product catalogue)
- provide information on target consumer groups
- evaluation of system prototypes developed during the project
Benefits for the project partners:
- access to a database of experiments of higher level (aesthetic) product preferences
- owner of an evolving recommendation system that works even for small initial
databases of user-preferences
- owner of software for product grouping and visualization according to higher level
(aesthetic) product properties
The use cases of the project will be adjusted to match the needs of the SME partners. As the
consortium is not fixed yet, established cooperation with research institutes could be
continued within ARROWS.
The project will be submitted in the EUROSTARS-Eureka framework program of the EC.
Submission date is 24 of March 2011.
Further information: http://www.eurostars-eureka.eu/
A Eurostars project is a European research and development project. It can address
any technological area, but must be aimed at the development of a new product,
process or service. A Eurostars project is collaborative, meaning it must involve at
least two participants (legal entities) from two different countries.
A Eurostars project should be market-driven: it must have a maximum duration of
three years, and within two years of project completion, the product of the research
should be ready for launch onto the market. The exception to this rule applies to
biomedical or medical projects, where clinical trials must be started within two years
of project completion.
Depends on country: - please check http://www.eurostars-eureka.eu/where.do
Project start (est.): Sept. 2011
Project duration: 2 years
Project size: ~1.0 MEUR
confidential project idea
Large Company 25%
University, Research Center 100%
Research Organisation 100%
Im Stadtgut A2
A-4407 Steyr-Gleink, Austria
mobile: +43 664 815 7895
confidential project idea