Natalia Connolly

[🐛BUG] full_sort_topk for k = 10 produces a list with 22 elements, each element a 10-item list, per user

3

I am trying to follow this [example](https://recbole.io/docs/user_guide/usage/case_study.html) to get top k items recommended for a single user. My code is: ``` external_user_ids = ['1234'] dataset.token2id(dataset.uid_field, external_user_ids) topk_score, topk_iid_list = full_sort_topk(uid_series,...

Scoring of users using predict_for_all_items is too slow

1

Hello, I am trying to use a RecBole model to score a dataset of about 1.5M users. I used predict_for_all_item. But it's very slow (after running for 10 hours it...

Inversion of the predicted TTE

1

Hi Egil, Thanks so much for creating the examples repo, this is super helpful! One thing caught my attention in your data_pipeline_template notebook: the plot of predicted vs. actual TTE...

Two questions - Plotting decomposition over time, and comparing adstock parameter for Robyn vs. lightweight MMM

3

Hi Team, I just had two questions about Robyn, and wasn't sure where to post them. Hopefully this is the right place. 1. Is there a way to get the...

Recovering adstock parameters from simulated dataset?

1

Hi All, I am trying to reconcile the output from lightweight MMM with known inputs from a simulated dataset. I used [https://github.com/facebookexperimental/siMMMulator/blob/main/siMMMulator-website/docs/step_by_step_guide.md](siMMMulator) to create a simple dataset with 3 media...

Channel by channel scenario modeling & response curve questions

2

Hello, I have two questions that I would really appreciate your help with: 1. For the media response curves generated by robyn_allocator, are those incremental or absolute values? Meaning, a...

Hi All, I had a question about robyn_allocator. Right now, it looks like there are only two scenarios that are possible, max_response or target_efficiency. Is it possible to do a...