0
$\begingroup$

I'm working on a previously bought recommendation system for a project. The list I'm trying to sort is static and does not change over time. Assuming each user purchases different items at different times, I'm searching for a function that captures both frequency and recency from a user's purchase history.

Is there a well documented function/research to solve this kind of problem?

Improve this question
$\endgroup$

1 Answer 1

Reset to default
1
$\begingroup$

There are many well-documented techniques to help you out with this. Collaborative filtering and even nearest neighbour search can help (given you have created good embeddings for the products using neural networks with multimodal input).

You would initially want to sort the list by frequency then date. Once, you have that you need to find related items to those at the top (let's say, top 5).

In order to find the similar products, you can use collaborative filtering or nearest neighbour search to find them.

Improve this answer
$\endgroup$
1
  • $\begingroup$ CF and nearest neighbours would definitely be useful but for sorting the items that the user hasn't interacted with before. Here I'm looking for a function that could sort the items user has previously bought, based on frequency and recency $\endgroup$
    – LucyDrops
    Commented Jul 21, 2021 at 9:46

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service and acknowledge you have read our privacy policy.

Not the answer you're looking for? Browse other questions tagged or ask your own question.