Companies that supply product data to their customers or receive data from various sources are familiar with the problem: every company has its own unique data structure. Often, classifications have grown historically, reflect the company's way of thinking or are highly granular. However, structures that make sense for your own company can represent major obstacles in data exchange. For example, different product group structures come together, but in the target system, such as a web store or an electronic catalog, they must be merged into a single, comprehensible system.
In e-commerce in particular, the volume of data and the requirements of customers, buyers and retailers make it crucial that products are available in very clear structures. After all, products should be able to be found, filtered and compared quickly and easily in the fast-paced (working) world. Standardized data structures also bring great advantages to those who work with data. This is because if the product and catalog database is the same, formatting and adjustments are not necessary and there are standards for everyone involved to use as a guide, this reduces the high workload in product data management.
In order to meet these requirements for common structures, a large number of product classifications have been created in recent years. These can be managed in addition to the company's own data structure and classify products according to a system based on characteristics. In most cases, the classifications are structured hierarchically so that the products can be clearly found by all users across several levels. Together with clear descriptions, keywords and explanations, goods from different manufacturers can be identified quickly and easily in this standardized system.
Both suppliers and customers benefit from this standardized classification of all items. For example, purchasing is made easier as the portfolio can be bundled according to matching criteria, which makes it easier to compare items in day-to-day business or for tenders. The products can be easily found and identified, which ensures significantly more speed and security, especially in complex processes such as delivery or processing. However, the visibility of items on marketplaces is also increased by the clear description and integration into store systems is made easier, which strengthens sales and increases customer satisfaction. Three classification systems in particular have become established on the market: the UNSPSC classification originating from the USA, the European ETIM system and the ECLASS classification established in Germany.
The most comprehensive of these three classifications is the United Nations Standard Productsand Services Code, or UNSPSC for short. This code can be used to classify both goods and services. It is used and required internationally, but is mainly used in the USA. UNSPSC-classified articles are given an 8- to 10-digit code, which is made up of 4 to 5 descriptive hierarchical levels. The code is free to use, but the extensive, annually updated complete code sets with around 157,000 different article classes are only available to members, which makes it difficult to assign your own products.
The European Technical Information Model(ETIM) is another system that was originally very specifically geared towards electrical engineering and is increasingly being extended to other product classes. In contrast to UNSPCS, the 5,500 product groups are organized without a hierarchy. Although the classes are roughly grouped thematically, the lack of a hierarchy, which could guide the user from the general to the specific, makes manual assignment of the 8-digit codes more difficult, especially with large amounts of data. Articles in the classes can be described more specifically using attributes. The standard can be used without license fees and is regularly expanded.
ECLASS is another comprehensive standard that has established itself on the market and combines the features of the other two systems. Like UNSPSC, it uses a hierarchical classification over 4 levels so that items are described with an 8-digit code. Similar to ETIM, the articles can be provided with attributes, the so-called unique characteristics. With around 45,000 product classes and 19,000 characteristics as well as the annual new releases, ECLASS offers a comprehensive classification option. Its use requires a license and the division into new classes or subclasses in particular poses major challenges for users with new releases.
A look at the systems shows that classifications offer a solid and general standard for e-commerce. They simplify the exchange of data and its use in different systems. However, a standardized classification system with its high requirements, special hierarchies and annual changes leads to additional maintenance effort. As the company's own structures rarely correspond to the standardized classifications and cannot be transferred directly, the articles are usually classified manually. This monotonous task, which is carried out in PIM systems or Excel, for example, requires a great deal of time and therefore personnel capacity.
Even if service providers can assist with classification, a high level of product expertise is often required for correct classification, which cannot always be accessed. This results in lengthy queries or items being classified differently by different people, which leads to misunderstandings and inaccurate data. In addition, products often have to be classified in several versions of the standard, which makes it necessary to maintain several data fields in parallel. Mapping tables are rarely freely available and operating all standards is extremely complex due to the amount of data and the large number of hierarchies and requirements.
Onedot has developed automatic product classification to meet these requirements and challenges. With AI support, large volumes of product data can be assigned to the appropriate hierarchies and product codes. The final check is carried out by the users, which improves the assignment with each use. The machine learning model was trained with classification data from public sources so that the AI is familiar with the most common sales channels and marketplaces right from the start. However, the high potential of machine learning is only realized when the amount of high-quality learning data increases. For this reason, Onedot offers you the opportunity to benefit from the community with opt-in product classification.
The classification data from the entire Onedot community is made available to the AI in anonymized form and used internally for training. This leads to very accurate and high-quality suggestions. If you do not wish to use this option, you can continue to receive classification suggestions based on public data via our opt-out option. However, with the opt-in option, you as a member benefit directly and also in the future from the community-supported, more precise automated classification, so that you are also excellently positioned in the field of standardized product data.
Would you like to benefit from our platform and the community in order to be able to react agilely and reliably to market requirements? Then please get in touch with us.
