How To Use Vector Search To Quickly Build A Content-Based Filtering Recommender System

Author(s): ___

Originally published on Towards AI.

Qualitative Evaluation

Visualizing some results (all movie posters are from imdb)

In this article, I will share how a vector search engine like weaviate can be used to quickly build a content-based filtering recommender system.

The code to reproduce the solution described in this article is in this repo.

We will demonstrate how the solution works using the MovieLens 1M Dataset.

A movie has the following properties:

TitlePlotSummaryGenres (list of strings)

The solution is really simple.

Given a movie and its properties, we simply turn it into a single vector using the sentence-transformers/msmarco-distilroberta-base-v2 model and store the results in the database.

To generate a recommendation, we take:

the last n movies… Read the full blog for free on Medium.

Join thousands of data leaders on the AI newsletter. Join over 80,000 subscribers and keep up to date with the latest developments in AI. From research to projects and ideas. If you are building an AI startup, an AI-related product, or a service, we invite you to consider becoming a sponsor.

Published via Towards AI