Five Recommendation Algorithms No Recommendation Engine Is Whole Without | Hacker News Reader

Five Recommendation Algorithms No Recommendation Engine Is Whole Without

memgraph.com

27 pointskobaroko10 comments

I feel like these click-baity titles have finally reached a state in which they work inversely for me. I have recently noticed that I would never click on something that promises "X things you must know" because I have finally internalized that the article behind will be superficial and useless at best. The impulse of "let's at least skim it in case it includes something useful", that used to be triggered by the clickbait has disappeared almost entirely.

For this particular example, I wonder how it was upvoted. But I am not going to click on it for reasons stated above.

Yes, the title signals low quality content.

Scanning the text, I think it is the typical SEO fluff that a whole industry has evolved around in the last decades.

Corporate blogs can be a wonderful thing. When they are written by actual employees of a company and describing how they did something.

But they are a bane of the internet when they are written by "SEO content writers" who's job it is to take a bunch of keywords and prop them up to a multiple pages long article that looks and feels authoritative but is just a potpourri of information taken from other sites.

If you look the article as a single piece of content, it may look like a clickbait. If combined into a Solutions page where several blog posts are outlined about how to solve particular problems, it actually makes sense.

Maybe.

Maybe my reaction was to harsh.

The enumerated listicle, you mean? Those seem so oldie oughties! Surprising they still work.

I skipped the article and came here for the comments in case there was anything useful to learn.

>The most powerful recommendation algorithms are made especially for graph data

This isn't true. The most powerful recommendation systems don't use graph algorithms. What recommendation system is using breadth first search over vector search for doing candidate generation?

Hey! I read many papers that say that graph algorithms and graph neural networks have very good results in this area. In this article I explained just few of them and gave some examples how to use them for this use case. Of course if you combine different algorithms and techniques you might get better results depending on what you want to achieve.

Not being familiar with recommendation engines at all, this article does a decent job showing some of the basics in a bird’s eye view, at least to my untrained eye.

That said, it’s still a promo piece for their graph database.

I've had some dealings with them (almost became a customer but the project went away), they're smart cookies and their DB is a nice alternative to Neo4j (seems a bit faster, a bit, C++ rather than Java, implements most of the Cypher query language).

off topic, but Dominik, the founder of Memgraph here. If we didn't connect yet, I'd love to learn how was your experience using Memgraph if you're up for sharing some feedback? DM me on any of the social sites or our community Discord if you've joined :)

Reply on news.ycombinator.com