Taxonomies have been in use for a long time on e-commerce websites. They help users find the products they want to buy by means of organized categories and subcategories of product types, and the feature of filtering by product attributes. In fact, when we explain taxonomies to those new to the concept, we often reference the e-commerce websites, such as Amazon.com, with which they are likely familiar.
Companies that sell products, however, can further improve product management and sales if they implement customer-facing taxonomies along with other semantic structures, such as metadata sourced from other systems and ontologies, as a part of a larger information/data management strategy. The best way to do this is to take a semantic layer approach, in which the semantic components (taxonomies, metadata, glossaries, ontology, etc.) connect to each other and connect across different systems and data repositories.
Uses of Product Taxonomies and Metadata
Product taxonomies have multiple uses beyond browsing through product categories on an e-commerce website. Both customers and product managers may benefit from taxonomies in a variety of ways.
Sometimes, users want to browse and explore types of products, and that is when a hierarchical taxonomy of product categories is most useful. Other times, users know the product they want and would like to see if the e-commerce vendor has the specifications they desire. In such cases, the users enter a description in the search box and then refine their search results by selecting among various attributes, which are managed as product metadata and are presented to the user as a faceted form of taxonomy. Attributes may include size, color, material, and category-specific features.
Taxonomies also support user discovery of new or related products. Users search when they know what they want, and browse when they have an idea or want to better understand the overall offerings available. “Discovery,” alternatively, refers to when users find things that they did not initially look for but are still of interest. Retailers can sell more products when they support discovery. This can be done in different ways:
- By properly displaying taxonomy category names and allowing users to navigate up and down the hierarchy;
- By including and enabling “related category” relationships in the user interface to let users navigate laterally across the taxonomy to find related products;
- By implementing a supplemental taxonomy, such as for product function and not just for product type, users can discover different products for the same purpose.
Taxonomies and metadata for products are not just for the customers. Product vendors need to manage products by means of their metadata for various purposes: purchasing from suppliers or wholesalers, controlling inventory, fulfilling orders, or updating images of products. While detailed metadata is key, category taxonomies are also useful, such as for identifying closely related substitute products or vendors for the same product line.
Uses of Ontologies for E-Commerce
An ontology extends a taxonomy by providing greater semantic enrichment in the forms of custom relationships and custom properties. Custom relationships between taxonomy terms or categories go beyond “broader/narrower” and generic “related,” and may include relationships for products such as “goes with,” “compliments,” “has parts,” “has add-ons,” or “has optional services.” Custom properties can be used as attributes for terms or categories, comprising metadata and controlled values, such as size, which can be applied to filter product search results.
Custom relationships between product categories support more options for discovery than a basic taxonomy can do. Not everyone agrees on what “related” means, and users may not agree with what someone else suggests is related. Defined relationships based on an ontology, such as “compliments,” or “has add-ons,” lets the user discover the types of related products of interest. Custom relationships may also link product categories to related services offered, such as product installation and product support, and to different types of content about products.
For custom attributes, each search filter/refinement is a metadata property with controlled values, and the metadata properties and values available depend on the product category. For example, “material” is an attribute for clothing, accessories, and furniture, but it is not for consumer electronics. Furthermore, the types of material available for clothing are not the same as for furniture, and they are not even the same for all types of clothing. Leather, for example, may be available for jackets but not for shirts. This can become quite complex to manage, but an ontology, which systematically links properties with categories, manages this task well.
Related to discovery is recommendation, which directly presents the recommended related products to the user. There are different kinds of recommendation methods. Common methods that base recommendations on past searches by the customer or other customers are not as beneficial if the customer has already purchased the searched product and does not need more. Recommendations based on the custom relationships of an ontology, however, such as “goes with,” are more useful. Recommendations may also be based on certain attributes, such as products with the same style or pattern.
Connecting Product Systems
Multiple different systems within an organization may deal with product data, metadata, and taxonomies. The most common are web content management systems (CMSs) for the e-commerce website, product information management (PIM) systems for the backend management of all product data, and digital asset management (DAM) systems for product images and videos. Some organizations also have data catalogs, master data management systems, media asset management systems, and product data may also be stored in a customer relationships management system used by sales and marketing people. Meanwhile, any product technical documentation is likely stored in another CMS. If an ontology is in use to model product data, then it is likely to be managed, along with a taxonomy in a dedicated taxonomy/ontology management system.
The problem is that each of these different systems tends to be siloed, so their data and metadata is separate and thus not the same nor in sync. Products may have slightly different names in different systems, and they may have slightly different metadata property names and even varying metadata values. For example, one system could have category sizes of small, medium, and large, while another uses numerical sizes for the same product category. Taxonomies could vary even more greatly than the metadata. One system may have a flat list of product categories, whereas another system has a 2-level hierarchy of categories and subcategories. It is typical to have different taxonomies and metadata in different systems because they support different users and use cases.
If the same data in these different systems is not described consistently and not connected, problems could arise from incomplete and missing data about product supplies and sales, such as poor decisions and missed opportunities. Trying to execute consecutive searches in multiple systems is very inefficient and is also prone to overlooking information. Finally, incomplete or inaccurate product information can result in a poor user experience for the customers.
A semantic layer framework provides a method to link data in different systems with a shared common metadata set and taxonomy.
Semantic Layer Benefits
A semantic layer is a standardized framework that organizes and abstracts organizational knowledge and data (structured, unstructured, and semi-structured) and serves as a data connector for all organizational knowledge assets. A semantic layer enables data federation and virtualization of semantic labels or rules to capture and connect data based on business or domain meaning and value. It’s a method to bridge content and data silos through a structured and consistent approach to connecting, instead of consolidating, data. It is called a “layer” because in the larger framework, it is a middle layer between the content/data repositories and one or more front-end applications for users to search, browse, analyze, or receive recommendations of information.
There are different approaches to implementing a semantic layer but the most common is a “metadata-first” logical architecture, which creates a logical layer that abstracts the underlying data sources by focusing on the metadata. Since product information is rich in metadata, this approach is most suitable for linking product systems and their data.
Systems connected through a semantic layer offer various benefits. For managing products and e-commerce, these include the following:
- When PIM or fulfillment systems are connected to the e-commerce platform, new products and product updates can be added more quickly, and specific product availability can be indicated in real time, rather than later;
- When a DAM is connected to the e-commerce platform, product images can easily and quickly be refreshed with the latest versions, which is especially beneficial for seasonal items and promotions;
- When a CRM and an e-commerce platform are connected, sales people know all the product details including the customer-facing product name and can better facilitate sales to prospects;
- When technical documentation CMS and an e-commerce platform are connected, customers have access to product data sheets, and customer support representatives can better serve customers.
A semantic layer allows an organization to build applications for users to access and interact with various sets of connected data and content better. For product information, such applications include search interfaces that seamlessly integrate product categories and attributes along with add-on services, recommendation systems for customers to discover products, chatbots for customers to get support, and data dashboards for product managers to track product data.