Random Walks on Human Knowledge: Incorporating Human Knowledge into Data-Driven Recommenders

New Hybrid Techniques for Business Recommender Systems

“…for optimal cross-selling opportunities [31] or for obtaining a consistent complex cloud service configuration [34]. This is also the case for our BI consultancy service, see Section 1.1 and [32].…”

“…Obviously, all of these approaches employ and model various types of knowledge. An overview of the different kinds of knowledge that recommenders may use can be found in [12,32]. What distinguishes the business recommenders from most others is the use of domain knowledge.…”

“…As we have laid out in our previous work [32], a recommender that suggests solution components to companies are different in several respects from the typical B2C recommenders that help users in finding e.g. books, movies or music that fits their preferences (see also [12]):…”

“…In our previous work [32], we used a graph, as a simple, flexible and easily extensible means of representing both historic user choices and explicit human knowledge about a business domain, together with a random walk approach to generate recommendations. We found that especially explicit knowledge about associations between solution elements improves the recommender performance.…”

“…While our previous work was able to benefit from a graph's flexibility and ease of incorporating new domain knowledge easily [32,22], it is not perfectly suited to accommodate and make use of all possibly relevant attributes of a company's context. For instance, it does not easily allow to represent and compare numeric attributes (such as company size) or simple string attributes containing longer passages of text.…”