Photo Based Gallery Recommendations

Similarity algorithms and Label Propagation overview

In this section you will use the Label Propagation algorithm to recommend photos.

Useful Resources

Exercise

  1. In Neo4j Browser, perform the steps in the Neo4j Browser guide section Photo Recommendations. (:play applied_graph_algorithms/05_photo_recommendations.html)

  2. In CodeSandbox, edit the FETCH_PHOTO_RECOMMENDATIONS Cypher query in src/exercises/exercise4.js to recommend businesses whose photos belong to the same community.

  3. Save this file.

  4. In the CodeSandbox Browser, click Photos and select five random photos. Then the application presents restaurants based upon the photos selected.

Solution

If you get stuck, watch this video for a walk-through of the solution:

Photo based recommendations solution

Check your understanding

Question 1

Algorithm Understanding: LPA

Which category of algorithms best describes LPA?

Select the correct answer.

  • Centrality

  • Similarity & ML Workflow

  • Community Detection

  • Pathfinding and Search

Question 2

Running the algorithm in Neo4j

Which voting mechanism does Neo4j’s Label Propagation algorithm use?

Select the correct answer.

  • Random Walk Method

  • Pull Method

  • Push Method

  • Modularity Optimization Method

Summary

You should now be able to:

  • Use the Jaccard similarity algorithm.

  • Use the Label Propagation Community Detection algorithm with Neo4j.