Questions tagged [recommender-system]

Everything related to recommender systems

Filter by
Sorted by
Tagged with
0
votes
0answers
20 views

Weighting of features in Recommender Systems

I'm new to Recommender Systems, and wanted to figure some things out in order to make the best possible Content Ranking System. I want to make a ranking of all the content (and content providers) ...
1
vote
0answers
10 views

What are the business metrics I should track to evaluate a recommender model deployed on an e-commerce website? [closed]

Can you suggest some google analytics metrics such as (click or impressions etc) to evaluate a recommender model deployed on an e-commerce website.
1
vote
1answer
23 views

How to find coherence between a large number of sentences

I have a list of sentences returned as a result of a document search algorithm. I want to determine if the results returned are semantically close/similar/coherent using some sort of metric. For a ...
0
votes
0answers
15 views

Can latent factor model work for new users?

I am studying latent factor model for recommendor system. It does matrix factorization(like SVD) on the user-item rating matrix. What I am not sure is, does a trained model work for a new user that is ...
1
vote
0answers
19 views

(Graph Convolutional Network (GCN) based recommender system maintenance issue [closed]

I have built an item-item recommender model using (Graph Convolutional Network (GCN) for an E-commerce website. Could you please help me with the maintenance of the model. How often should I retrain ...
0
votes
0answers
13 views

estimate user's satisfaction of a video based on how much of it they watched - normalization

I am trying to estimate how much a user liked a video using how much of the video they watched. Let's say, on the scale of 1 to 10, 1 means that the user didn't like it at all, and 10 means they ...
0
votes
0answers
4 views

How is SVD from scikit-surprise handles empty values

I am studying the surprise lib for recommender system. SVD from this lib doesn't require all value input in user-item matrix. But it is a must of the original SVD method. The official doc doesn't ...
2
votes
1answer
23 views

Reduce serving time complexity for real-time recommender systems

I am working on a real-time recommender system predicting a product to a user using deep learning techniques (like wide & deep learning, deep & cross-network etc). Product catalogue can be ...
1
vote
1answer
39 views

How to model a supervised recommender system with varying data

Suppose there are 2000 movies and a company wants to recommend some movies (for example, at most 5 movies) to each visitor. The objective is to learn how to predict which movie will be selected if a ...
0
votes
0answers
11 views

Top n products as a kind of recommendation system

I'm looking for a paper, book or something similar that describes only the top products as a kind of recommendation in a recommender system. The top products can be determined with a simple counter. ...
1
vote
0answers
13 views

Why I need to generate train instances and load negative samples?

If you look at this GitHub link ( here is the paper link for the implementation ) you can see that the get_train_instances method generates trainingns instances. In ...
2
votes
1answer
23 views

Recommender/Clustering data to support a hypothesis. Is this a valid use-case for unsupervised ML?

I have a dataset where some items have been labelled (categorized into 4 classes [A,B,C,D]). However, there is a vast majority of the dataset which has not been labelled. My hypothesis is that there ...
8
votes
3answers
444 views

Why is deep learning used in recommender systems?

I am currently reading a lot about recommender systems (RS) and came across that many RS are based on deep learning. However, I never find a good scientific article why deep learning is used in RS and ...
1
vote
0answers
21 views

Scoring metric for recommendation system

I'm working on a project that involves building a news recommendation system. I've come as far as quantifying user interaction with different articles on the site into user's affinity towards atopic ...
0
votes
1answer
27 views

How to grade an interaction that a user had with a post with an AI based on big data?

Context I'm creating a social network. The thing is, I don't want to order posts by likes, or something like that, I'm using an AI (lightfm in ...
1
vote
1answer
26 views

Finding and ranking best semantic matches between two sets of phrases

I'm looking for a proper definition for what sort of problem this is, so I can further research it on my own - though I will, for sure, appreciate any specific advice on what are industry standard ...
4
votes
2answers
81 views

What is the best model for a recommendation system using implicit ratings?

I have a similariy matrix that looks like this: I have a bunch of user vectors with 1s and 0s, with a 1 indicating that someone has clicked on an email (as part of a campaign) and zero to indicate ...
1
vote
1answer
20 views

Evaluation of recommendation systems

I have developed a content-based recommendation system and it is working fine. The input is a set of documents={d1,d2,d3,...,dn} and the output will be Top N similar documents for a given document ...
1
vote
0answers
10 views

Predict the target audience for a new brand using data from other brands and customers buying behavior

Assume a company has a large database about wine, including brand, the taste of the wine, year, place of production, etc, and data of customers' purchase behavior. Now if there is a new brand coming ...
0
votes
1answer
34 views

How can collaborative filtering be extended to include more features?

Looking at the following: https://realpython.com/build-recommendation-engine-collaborative-filtering/#using-python-to-build-recommenders I can see that userID, itemID, rating are the standard features ...
1
vote
1answer
33 views

Recommender System for mostly unique user and items

I am trying to develop a recommender system for a job matching problem. My data consists of past matched candidate profiles and job profiles as well as if there was a success such that both, candidate ...
1
vote
2answers
45 views

Evaluate document similarity / content-based recommender system

I'm planning on building a basic content-based recommender system with word2vec and cosine similarity. The data consists of 300k documents in varying length. How do I evaluate my model if I have no ...
0
votes
1answer
34 views

LightFm - replicate precision@k score with predict vs. predict_rank method

LightFm has two methods to predict: predict() and predict_rank(). The evaluation function ...
4
votes
1answer
44 views

Why softmax in YouTube’s DNN recommender

I am confused about the softmax layer of YouTube’s DNN candidate generation. A user may interact with many videos. Softmax is assuming classes are exclusive. For example, logits = [[4.0, 4.0, 1.0]], ...
0
votes
1answer
31 views

How to estimate missing values when calculating NDCG

I would like to compare recommendations methods using NDCG metric on MovieLens dataset. In ranking problem, the goal is to rank items based on their relevance for user. Ranking models can be learned ...
2
votes
2answers
91 views

Which metrics for evaluating a recommender system with implicit data?

I am currently in the process of creating a recommender system. This recommender system works with a neural network and then searches for the closest neighbors and thus gives recommendations for a ...
0
votes
0answers
11 views

Adding additional information in content-based recommendations

I have a book dataset where 100 users have rated the books as like/dislike. Each observation with features Table1 : ['user_id','book_name', 'book_genre','author','date_published','like/dislike'] These ...
1
vote
1answer
54 views

Proper evaluation method for recommendation system with implicit feedback?

I am trying to implement a recommendation system for a live-streaming website. Here "users" are simply the website users and "items" are streamers that they should watch. I ...
0
votes
1answer
20 views

finding similarity of a new datapoint

I have built a recommendation engine using cosine similarity. When I want to find all the records similar to a given record that is already present in the dataset it works. Consider a case, a user ...
1
vote
1answer
34 views

Click Through Rate calculation (CTR) calculation problem

So I'm doing a use case for a company interview and one of the questions is to calculate the CTR for a sorting algorithm. My question would be: Should I remove the operations where there were no ...
0
votes
1answer
25 views

How to represent genre or artist name in a neural network

I am writing a music recommendation system using machine learning. I'm attempting to make sense of ensemble networks to allow the system to learn from both the content-based features, as well as the ...
4
votes
1answer
40 views

User-to-item and item-to-user recommendations

I'm currently creating a recommender system and there are different types of the systems. Does anyone know something about the user-to-item and ...
0
votes
1answer
23 views

Item-to-Item recommendation using DNN

I am new to DNN still learning, have a need to build item-to-item content based recommendation using DNN. For example, say I have a column of strings where each row represents a document I need to ...
3
votes
1answer
66 views

Recommender Model for Human Action in Income Protection

Problem Domain I'm working on a project that involves building a model to provide recommendations on the next best step for Human supervisors to take on income protection claims. Income protection is ...
0
votes
0answers
16 views

product recommendation of a single product based on customer similarity?

I have been wondering how you can build a model to recommend only one single product to a bunch of customers. So basically the question that I would like to answer with this model is to have a ranking ...
0
votes
0answers
20 views

Learning to Rank vs Reinforcement Learning in Information Retrieval - which one is preferable and why?

I am trying to create an information retrieval system which can benefit from user feedback (either implicit, through e.g., click-through data) or explicit (e.g., binary feedback on irrelevant ...
2
votes
0answers
13 views

Item-to-Item similarity: is weighted sum the most popular approach?

In content-based filtering (CBF) recommenders, when there are is no user profile, similar items are recommended an item that a user is currently inspecting. For instance, if you are looking for a ...
1
vote
0answers
20 views

Recommendation Systems User Profile Streaming Data on GCP

I have a recommendation system that recommends articles to different users. I am planning to provide the recommendations in an off-line fashion. Where I already have a table in BigQuery which has the ...
1
vote
1answer
35 views

How to include user features in a recommender system?

I'm novice in that matter but I was thinking about the formulation of a recommender system. Let's take the example of a movie recommendation system. We have a column dedicated to movies ID (or names), ...
0
votes
0answers
8 views

Get latest Item by Date for a Recommender System

I am building a Recommender System where I am giving the User 3 Recommendations depending upon for the Webpage he is on. Let's say My model gives me 3 Recommendations from 2020, 2019, 2015. I would ...
0
votes
0answers
14 views

Classify Spanish Text into different Categories

I want to recommend articles to users depending upon what type of article is user reading, Music, Movies, Politics, etc. I have 3 features: Page Title, Labels, article content. I am using an API (...
0
votes
1answer
22 views

How to filter Items in Recommender Systems?

I have a Recommender System which recommends Articles based on Similarity from 3 Features, "Page-Title, Article Content, Tags". But some of the Articles are NSFW(Related to Adult Topics). I ...
0
votes
0answers
13 views

What are the Objectives for Recommendation Systems and what Key Results should a Recommendation System focus on?

I know that a Recommendation system helps in the engagement of the users and helps users find more relevant content but I am in search of more complex objectives and key results with regards to ...
0
votes
0answers
9 views

Link Recommendation System

I am trying to build a Recommendation system on my website for recommending similar articles to the user. Eg: Lets say a user is reading an article about sports on a news website. The next article ...
0
votes
0answers
35 views

Human intuition behind SVD in case of recommendation system

I checked the SVD for recommendation engine thread but it does not answer my question. I struggled very hard to understand the SVD from a linear-algebra point of view. But in some cases I failed to ...
0
votes
0answers
18 views

Recommend System AB test metric events

I build personal recomendation system for choosing games. In website on main page on special place there is collection of personal games recomendation. And after AB test(between 2 recommend system) I ...
1
vote
0answers
26 views

Building a content-based recommendation system using products' metadata as features?

I am currently working on an apparel recommendation system, where I have tabulated data containing a list of products with their respective metadata (brand, category, color etc.) I have an additional ...
0
votes
0answers
19 views

Can previous successful actions be used as input to policy model in contextual bandits?

In a recommender application, I apply contextual bandits using logged propensity scores similar to this. The model is retrained daily. The application recommends images on an e-commerce website. Each ...
0
votes
0answers
7 views

Can I use LSI (Latent Semantic indexing) to get similar docs for several documents at the same time?

I'm working on a Recommander system in which I'm using LSI to get similarities between videos. I wonder if I can provide to LSI matrix more than one document and get similar docs for all those. In the ...
1
vote
0answers
75 views

Data augmentation for recommendation systems

I have a user-item matrix that I use to train a denoising autoencoder to predict the top-k items to recommend to the different users. The idea is to corrupt the matrix by erasing a percentage ...

1
2 3 4 5
8