Questions tagged [recommender-system]

Everything related to recommender systems

Filter by
Sorted by
Tagged with
1
vote
1answer
13 views

How to identify text similarity based on training data?

I have a set of documents (1 to 11) for which the labeling is done. Lets Assume: ...
1
vote
0answers
17 views

Predicting Item Ratings with the Log Likelihood Ratio

I'm trying to infer prediction ratings from an item-item similarity matrix where the similarity score is calculated via the log-likelihood ratio (LLR). I'm using this code snippet to calculate the LLR ...
0
votes
1answer
11 views

How to calculate similarity between 2 users based on the images they share?

Say there are 2 users, A and B, and they each shared 10 images (in some social media site), which I have collected in 2 folders separately. I want to calculate the similarity between the 2 users based ...
0
votes
1answer
20 views

Personalized Search based on client's purchase history and product preferences!

I am exploring approaches to build a model that shows personalized search results (with or without query) for a fashion eCommerce platform. The data that I have are: Client's purchase history i.e the ...
0
votes
0answers
9 views

How to use the position factor in known data as a feature in recommendation surfacing?

The problem is recommending stories on a website, just below each story based on how similar the stories are and some historic data based on what recommended stories were clicked or not clicked. So ...
2
votes
1answer
36 views

How to build recommendation model based on resume and job description?

How to build a model which will result in better recommendation of resumes based on the job description given? I am familiar with bow or tfidf (n-grams) approach and then take a cosine similarity but ...
1
vote
0answers
30 views

Should you cluster before performing collaborative filtering?

So I am building a recommendation model using customer and product information. This will be done via implicit, that is, a customer has a product or not as we don't have rating information about ...
0
votes
0answers
27 views

How to train a recommender system to improve the customer class?

Considering the definition of a recommending system A recommender system, is a subclass of information filtering system that seeks to predict the "rating" or "preference" a user ...
1
vote
1answer
45 views

How do I predict a set of frequently bought items?

I have a dataset of retail transactions wherein different users buy certain items together. For example, a user A buys a toothpaste, a toothbrush and a floss at the same time, and a user B buys a ...
0
votes
0answers
8 views

Perform collaborative recommender analysis without rating in a transactional data

I'm exploring options for recommender systems optimized for the online retail dataset, which would take into account that no product or user rating is available. Can collaborative recommender analysis ...
0
votes
0answers
39 views

How to calculate latent vector for a user in ALS based on some new input?

So I have an ALS trained in pyspark but then I get some interactions from a new user that wasn't in the training set. I want to give recommendations to that new user without retraining the ALS based ...
3
votes
2answers
146 views

How to use hashing trick with field-aware factorization machines

Field-aware factorization machines (FFM) have proved to be useful in click-through rate prediction tasks. One of their strengths comes from the hashing trick (feature hashing). When one uses hashing ...
0
votes
0answers
10 views

Approaches For Recommender System Using Complicated Novel Dataset

I have a question about the best approach(s) I should take in building a recommender system for a project I'm working on. I have created a dataset. The dataset has the following: 400,000 users For ...
0
votes
1answer
39 views

BPR TripletLoss Recommender System

I am trying to modify the code of this repo to build a recommender system based on BPR triplet loss. In particular I modified the TripletLoss layer class like this ...
0
votes
0answers
10 views

News Recommendation Engine with XGBoost

I want to build a news recommendation engine with XGBoost, but the data I have contains implicit user ratings, view history of a user. I know what my X's will(user embeddings + Item Embeddings) be but ...
1
vote
1answer
29 views

Learning Resources for Recommendation system

Beginner here: Could you please suggest some of the learning resources (books/youtube/articles) for beginners who want to build a recommendation system for their organization. Have no clue about it ...
0
votes
0answers
29 views

KNN() and SVD() for recommender system

I come here cause I have some troubles (or is it normal ?) with the rating predicted by SVD() and KNNWithMeans(), I'm using the Sckit-Surprise library . Here is context : I have 637 069 rating I ...
0
votes
0answers
10 views

Is there an experimental section for product recommendations?

We already know that the recommendation engines are trained on basis of several factors and they come up with Top N best product recommendations. For eg: The Netflix Top N Video Ranker. Now, my ...
1
vote
0answers
12 views

Recommendation system with active learning

I have data where companies ask users to score a bunch of questions but some items may be randomly chosen while others are personalized. Users score higher in personalized questions on average. I have ...
0
votes
1answer
57 views

How to train-test split and cross validate in Surprise?

I wrote the following code below which works: ...
0
votes
0answers
5 views

When is sparsity becoming a problem when building recommender system?

When building a recommender system the rating matrix is usually quite sparse. Sparse means that such a matrix contains mostly empty values (or 0s for that matter, although these could also be ...
0
votes
0answers
13 views

How to obtain 5 star rating predictions from content-based filtering

I am attempting to compare multiple recommender system approaches, including content-based filtering and collaborative filtering. My plan is to predict 5 star ratings and use MAE and RMSE as metrics ...
0
votes
1answer
27 views

Building a content-based music recommendation system

I am trying to build a recommendation system in Python that recommends songs based on a playlist. What I have is two datasets: 1. One dataset consists of 350 songs from my playlist and 13 acoustic ...
1
vote
0answers
23 views

ML recommendation system with items organized in a tree

I would like to develop a recommendation system (probably hybrid, user-based and feature-based) for items which are organized in a tree (there are categories, divided in sub-categories, divided in sub-...
0
votes
0answers
52 views

System Requirement to train BERT model

How much Hardware is required to train it well?(My current PC specs: 8GB RAM, i5 2 core Processor, Standard GPU (No work going on GPU)) I have a dataset of approx 1lakh records.Is it is necessary to ...
0
votes
0answers
44 views

How to create a model and make predictions with LightFM?

I've been researching on how to develop a hybrid recommender system for a simple book dataset, the main goal is to use both explicit data (purchases) and latent factors (features) to make the ...
0
votes
0answers
5 views

Manipulating the relative weight of tokens inside CountVectorizer

This is transparently a classic IMDB data recommender question. I'm trying to build a recommender system that suggests movies that a user is likely to enjoy. If I have my terminology correct I am ...
0
votes
0answers
9 views

Training a cosine similarity matrix for similar text recommendation

I'm working on similar movie names recommender system. I have a dataset of only movie_titles that I converted into matrix using tfidf and then computed the cosine ...
0
votes
0answers
12 views

Ranking graph's nodes by score propagation

Problem I have the following directed tripartite graph $G(E\cup V\cup P, A)$, where there is a many-to-one symmetric relationship between the subsets V and E - $e\in E,v\in V,[e, v]\in A \iff [v, e]\...
0
votes
0answers
86 views

Recommender System Web Application

First of all I apologize if posting such thing is against the rules here, but I did a Google research, and actually did lots of it, however couldn't get the answer I wanted and wouldn't know where to ...
0
votes
0answers
15 views

How to make a popularity-based recommender system having data on posts and number of likes? Please review a code

I'm writing a popularity-based recommendation system, where I have data on posts and likes the posts have. I need to recommend posts to a user based on their popularity (obtained likes). Packages and ...
0
votes
0answers
10 views

Factorization Machines with some some pairwaise effects and some linear effects

I have some covariates $x_1$, $x_2$, $x_3$, .., $x_{10}$. I want a linear term for all these covariates and a pairwise effect for $x_1$ and $x_2$, and I do not want any other pairwise effect. Is there ...
0
votes
0answers
15 views

Upsell project based on sales records

in my company we are working on a upset project in which we are trying to solve the following problem: What we propose to our customer that he/she may be interested in based on the fact that he/she ...
0
votes
0answers
13 views

How effective would this pseudo-LDA2Vec implementation be?

For my site I'm working on a chat recommender that would recommend chats to users. Each chat has a title and description and my corpus is composed of many of these title and description documents. I ...
0
votes
0answers
40 views

Combine features in Machine Learning KNN

I'm trying to build a simple book recommendation system, where I don't have any kind of ratings (no comments, no likes, no 1-5 stars, ...). The information I can use is the following: Book metadata ...
0
votes
0answers
22 views

Time aware recommender system

I plan to design a recommendation system, especially with Scikit-Surprise. A bit of background: I want to recommend products to shop. Here, the user is the shop and the items are products (water, ...
0
votes
1answer
21 views

Call routing using AI

I'm trying to find out how AI can help with efficient customer service, in fact call routing to the right agent. My usecase is given context of a query from a customer and agents' expertise, how can ...
1
vote
1answer
29 views

Offline evaluation of recommender systems

Let's say I want to compare whether one recommender system (A) is better than the other (B). One approach is to let people rate recommendations returned by both systems. However, there situations ...
3
votes
2answers
388 views

Building a tag-based recommendation engine given a set of user tags?

Basically, the idea is to have users following tags on the site, so each users has a set of tags they are following. And then there is a document collection where each document in the collection has a ...
0
votes
1answer
220 views

how to build word2vec content based recommendation?

I am building a content-based recommendation system for hotel accommodation. I have a hotel name, hotel description and location. I combined hotel name, description and location. Then, applied NLP and ...
1
vote
1answer
41 views

Recommendations based on other products seen

I am trying to develop a basic book recommender system to get in touch with the field and start learning methods and how to prepare the data. The Dataframe I am using is pretty plain, it has the ...
1
vote
0answers
47 views

Building a recommender system [closed]

I want to build a recommender system for shops, where I recommend items. I've learned about these systems like with content-based, collaborative filtering and so on. But now I want to make one on a ...
1
vote
1answer
48 views

In recommender systems, how to avoid recommending a product that the user has just bought?

Suppose I'm running an online store that sells many products, but from only a couple of categories, say: $A$, $B$, or $C$. Let's say a user has bought a product in the A category, and there's no ...
1
vote
0answers
54 views

Deal with huge amount of data

I'm writing to get advices about my project. I want to make recommander system for shop with some products. In fact i want to recommand to shop A to take item X because shop B sell this item and ...
1
vote
1answer
22 views

Recommendation Engine - Content based and Collaborative recommendation?

I am building a recommendation system for hotel accommodation. I scraped data from online booking portal and now my data has Name of the hotel, review, description and location. I built a simple ...
0
votes
0answers
19 views

Learn recommendations from dataset

I have a corpus of news articles and 6 annotations indicating whether a pair of documents are related or not. Not all possible pairs are annotated. Since a vectorised representation can find out the ...
0
votes
0answers
22 views

Code freezes and never returns when linear_kernel (sklearn.metrics.pairwise) is used on 20M Movielens dataset

I'm fairly new to ML/AI, i'm trying learn the content based recommendation - here is my source code - https://github.com/jaganlal/content-based-recommender I'm using MovieLens 20M dataset - tags.csv ...
2
votes
1answer
19 views

Recommender system that matches similar customers with similar highly rated products?

I have a dataset of 1,000 customers that bought 20 distinct phones and rated them 1-5. I have several demographic attributes for these customers (gender, age). My website offers 100 distinct devices, ...
1
vote
1answer
47 views

NCF Recommender- The target encoded within the model input, why doesn't it overfit easily?

In the recommender system NCF, the input is a batch of user-item interactions (one-hot encoded) and the output is a 0-1 score of whether the item has been bought or not: This seems to indicate that ...
1
vote
1answer
249 views

Train-Test split for a recommender system

In all implementations of recommender systems I've seen so far, the train-test split is performed in this manner: ...

1
2 3 4 5
7