m-way – 100% E-BIKE

Categories

Attributes

SKU attribute values processed

expert-feedback-onedot-in-action-create-an-accurate-product-categorisation-system-using-accurate-and-up-to-date-product-information

CHALLENGES

  • Replacement of the existing webshop.
  • Expandable product data model.
  • Existing data must be enriched.
  • Data cleansing necessary.
  • Different data structure of the suppliers.
-onedot-intelligently-adapts-to-changes-in-the-data-and-continuously-learns-from-business

HOW ONEDOT HELPED

  • Product data model for webshop specified.
  • Definition of relevant attributes per category.
  • Matching of products with supplier catalogs.
  • Existing data enriched and cleansed with supplier data.

m-way was founded in 2010 to promote environmentally friendly and sustainable mobility. Within a very short time, the subsidiary of the Migros-Genossenschafts-Bund developed into the market leader in the electrical two-wheeler trade. As a driving force in the growing e-bike market, the Swiss market leader in e-bike trading influences society’s mobility behaviour.

CLEANED PRODUCT DATA FOR M-WAY WEBSHOP

The Migros subsidiary m-way has a wide range of products in the e-bike sector with 28 shops and a high-quality consulting and repair service. The e-bike-oriented company wants to extend its reach with a revised web shop.

In order to achieve this goal, the current webshop software should first be replaced and the product data model refined and expanded with additional filters. Various filters lead the end user more quickly to his product. Filters are based on existing attributes, which are filled with consistent value lists. The new filters were not sufficiently covered by existing data.

Therefore, it made sense to enrich the product data with raw supplier data, to standardize and clean up the different attribute values. This allowed the facet search to be expanded, leading to a better user experience and a higher conversion for the newly established multilingual web shop.

A m-way internal manual data preparation would have been very extensive due to the partially disordered product data received from various sources. Since the new webshop software was to go online promptly, m-way turned to the data experts at Onedot.

mway-Head-of-Product-Purchasing-Management

“Onedot helped to detail our product data model and improve our customers’ shopping experience. This has made it easier and faster for customers to find the right products at m-way’s web shop”

Fulvio D’Aurelio, Head of Marketing & Product Management, Member of the Management Board at m-way ag

HOW ONEDOT HELPED

In the first step, the existing product data from the ERP and the external supplier data were automatically checked for data quality in order to recognize which attributes are available from the supplier, how structured the product data is and what can be extracted from texts. This is necessary because, for example, a helmet model offers different ventilation holes, visor sizes or closure system adjustment options and these attributes must be classified and correctly assigned.

Based on existing products and raw supplier data, the product data model was defined and product families formed. Products with the same attributes were grouped into product families to simplify the complexity of the product data model. In addition, attributes were defined for each category and value lists, units and data types were defined. The extension of the categorization to further levels, for example from two categories to now four, increased the findability of the products.

In the next step, the product data model had to be filled with product data, which is why the existing products were enriched with the additional supplier data. The enriched data was then normalized and unified by artificial intelligence (AI). As a result, more information is available for the purchase decision in the web shop, which increases conversion in the m-way web shop.

mway-Head-of-Product-Purchasing-Management

“The data quality of the existing products could be significantly improved, which considerably improves the conversion.”

Fulvio D’Aurelio, Head of Marketing & Product Management, Member of the Management Board ati m-way ag

THE RESULT

Onedot was able to refine the product data model using specially developed artificial intelligence (AI) and machine learning (ML) algorithms. On average, up to 20 additional attributes were added per category and over 100 value lists were defined. Subsequently, an efficient product matching, a precise attribute mapping and a comprehensive cleanup were carried out. The supplier products were matched with the existing products individually for each supplier on the basis of various identification options. Then over 14,000 supplier attributes from over 20 different suppliers were mapped to the m-way category specific attributes. The almost 100,000 SKUs in over 175 categories were cleaned up in several iterations according to category. The cleanup included various data types, such as numbers, units or value lists. For example, 600 supplier colors were standardized to 16 filter colors. This higher data quality forms the basis for increased conversion and higher sales at m-way Webshop.

READ ZAGENO SUCCESS STORY

TEST ONEDOT WITH YOUR OWN DATA

Contact us to find out how Onedot can help you.

CONTACT