How to calculate the weight of an inferred edge based on the existing-edge weights

[charlie_close]

Hi, all.

Suppose I have this:

(a:Reader)
(b:Book)
(c:Book)

(a)-[:LIKES {weight:5}]->(b)
(a)-[:LIKES {weight:13}]->(c)

And now I want to infer the edge (b)-[:SIMILAR_TO {weight?}]->(c).

That is, I want infer that two books are similar because the same reader liked both of them. The reader liked each book with a different intensity (LIKES(weight)), and I want these weights to influence how similar I think the books are (SIMILAR_TO(weight)).

My question: are there any best practices for inferring SIMILAR_WEIGHT(weight) from the two LIKES(weight) values?

Thanks.

Charlie

[niclasko]

Hi,

The following article might provide some insights:

Neo4j Graph Database Platform – 5 Sep 19

Creating an Intelligent Recommendation Framework

Read this blog to learn more about the benefits of using a native graph database to build a real-time recommendation engine with personalization.

Also this about triadic closure:

Data Science With Python – 23 Sep 17

Triadic Closure (Clustering)

Measuring network clustering

en.m.wikipedia.org

Triadic closure

Triadic closure is a concept in social network theory, first suggested by German sociologist Georg Simmel in his 1908 book Soziologie [Sociology: Investigations on the Forms of Sociation]. Triadic closure is the property among three nodes A, B, and C, such that if a strong tie exists between A-B and A-C, there is only a strong tie between B-C. This property is too extreme to hold true across very large, complex networks, but it is a useful simplification of reality that can be used to under Triad...

[charlie_close]

Thanks, Niklas, I'll look.