recommenders-team/recommenders

[ASK] [DISCUSSION] What kind of news is recommended

Open

#1,251 opened on Nov 26, 2020

View on GitHub
 (0 comments) (0 reactions) (0 assignees)Python (2,972 forks)batch import
help wanted

Repository metrics

Stars
 (17,706 stars)
PR merge metrics
 (Avg merge 6d 16h) (10 merged PRs in 30d)

Description

Scorer and recommendation items

if you look in the function run_fast_eval what exactly we recommend and add the following changes:

        for (
            impr_index,
            news_index,
            user_index,
            label,
        ) in tqdm(self.test_iterator.load_impression_from_file(behaviors_file)):
            pred = np.dot(
                **np.stack(news_vecs.values(), axis=0),**
                user_vecs[impr_index],
            )
           **pred = np.argsort(pred)[::-1]**

it will become clear that at the beginning of the list of recommendations there will ALWAYS be those articles, the number of which on the train as 1 was greater. which means, in fact, not quite relevant items are recommended. and not even the most popular, since this is only the number in the target, and not in all sessions

similarly, if you shoot a metric in a slice not an impression but in a user slice, that is, for 1 user and several 1 targets, then the metric will immediately drop by more than 2 times

Contributor guide

Research direction
Investigate the scoring function in ` run fast eval ` to understand why articles with more training targets are ranked higher. Consider implementing alternative scoring that accounts for popularity or relevance normalization.
Tech stack
pythonnumpy
Domain
machine learningbackend
Issue type
Bug
DifficultyEstimated implementation difficulty for a new contributor, from 1 for very small changes to 5 for expert-level work.
3
Estimated timeA rough time range for an experienced contributor to investigate, implement, test, and prepare a pull request.
Half day
Activity statusHow available the issue appears right now: fresh, active, stale, blocked, or waiting on maintainer input.
Active
ClarityHow clearly the issue explains the expected change, acceptance criteria, and next step.
Needs investigation
Prerequisites
Pythonnumpy
Newbie friendlinessA 1-100 score estimating how approachable this issue is for first-time contributors.
45