Questions tagged [recommender-system]

Everything related to recommender systems

150 questions with no upvoted or accepted answers
Filter by
Sorted by
Tagged with
4
votes
0answers
47 views

Can we use embeddings or latent vectors for a recommender system?

I'm having a hard time understanding why people use any vector they find as a candidate for a recommender system. In my mind, a recommender system requires a space where distance represents similarity....
4
votes
2answers
104 views

Evaluating recommendations quality and accuracy

I'm developing a recommendation system, that should provide my clients what actions they should take in order to hit certain targets. The underlying mechanics of the process is physical - where both ...
4
votes
1answer
111 views

Neural Network - Sparsity of collaborative based filtering and modelling the prediction problem

I'm fairly new to machine learning and for that matter, neural networks, but for the past couple of days I decided to take a stab at a fairly classical and practical problem of neural networks/machine ...
3
votes
0answers
51 views

What is the “matrix trick” in recommendation systems?

I just found slides from Matt Gormley (CMU) about recommendation systems. Under the heading "Unconstrained Matrix Factorization" he mentions: Optimization problem SGD SGD with Regularization ...
3
votes
0answers
98 views

Interpretation of Similarity Number generated by LogLikehood in Mahout

I have a pretty basic question and I was hoping someone could help me. I’m not a math person and I’m fairly new to mahout so I’m looking for a poor’s man explanation. It is a typical order ...
2
votes
0answers
25 views

Best way to evaluate interlaced recommendation system results while reducing bias

I already asked this question but I worded it in such a way that it was a completely different question to the one I want to ask. I have not deleted the old question in case someone finds it useful. ...
2
votes
1answer
116 views

precision@k and recall@k

Normally, I am familiar with precision and recall evaluation metrics but as you know recall@k and precision@k are different things and used in ranking evaluations especially recommendation systems. I ...
2
votes
0answers
28 views

Cross validation for Collaborative filter-based recommendation systems

I am an absolute beginner and am trying to implement collaborative filter for furniture ecommerce (think wayfair). I need some guidance about cross-validation strategy. Situation: I am working on a ...
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 ...
2
votes
2answers
132 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 ...
2
votes
2answers
36 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: ...
2
votes
0answers
31 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-...
2
votes
0answers
548 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 ...
2
votes
0answers
97 views

Multidimensional collaborative filtering model

I have a dataset that is approximately structured in the following way: 500 users, 500 products, 100 countries, 2 seasons, 300,000 ratings. Meaning that I have 300,000 rows containing unique ...
2
votes
0answers
26 views

Operations on Recommendation Embeddings

I've trained a recommendation system to recommend steam games based on game tags. An example output is shown below, where GAME is the game recommended based on the <...
2
votes
1answer
71 views

Item-based recommender using K-NN

I'm trying to build an item-based recommender using k-nn. I have a list of items, all of which have some properties (features) in common. ...
2
votes
1answer
220 views

How to use testing data set to measure recommender system algorithm

I am new to recommender systems and am trying to build one using item-to-time CF. Currently, I am trying to evaluate/measure results using MAE. I have one step which is unclear (after I managed to ...
2
votes
0answers
188 views

Regularization term in Matrix Factorization

I'm trying to build a naive recommender system using latent factor model for MovieLens dataset. From the observed set of ratings I'm trying to build a model which will decompose the sparse matrix to N ...
2
votes
1answer
592 views

How do I perform Leave One Out Cross Validation For Top n Recommendation Sytems?

I am new in making recommendation systems . I am using the surpriselib library to evaluate my recommendations. All the Accuracy Metrics are well supported in this library. But I also want to compute ...
2
votes
1answer
433 views

Neural network model for sparse multi-class classifier on Tensorflow

The problem I'm trying to solve is the following: the data is Movielens with N_users=6041 and N_movies=3953, ~1 million ratings. For each user, a vector of size N_movies is defined, and the values ...
2
votes
0answers
237 views

SVD++ vs wALS: Which is the more effective for implicit feedback in Recommendation system

As SVD++ can be used for implicit feedback, I would like to know whether SVD++ can gives better results than the wALS algorithm (paper: Collaborative Filtering for Implicit Feedback Datasets ). I can'...
2
votes
2answers
108 views

Matrix Factorisation Improvement

I am using SGD matrix factorisation (python) using the movielens dataset to make recommendations. I have a website which allows users to give feedback which is positive or negative to whether an item ...
2
votes
0answers
49 views

How does SVD actually provide the recommendations? I seem to get conflicting answers

I am reading a text book that basically says the following: Given a matrix A where A is USERS x ITEMS we can use SVD to decompose the matrix into: $$A = U \times \Sigma \times V^T$$ Then we can take ...
2
votes
1answer
329 views

Use of negative correlation coefficient in pearson correlation algorithm for recommender systems

I'm new in recommender systems and I try to find similar users of a base users for user-based collaborative filtering. When I calculated the similarity score now between two users (based on there ...
2
votes
0answers
315 views

Recommendation matrix as a product of User Similarity and Ratings

For both item-item and user-user collaborative filtering the recommendation matrix $Γ_{m x n}$, which is an (m x n) matrix, can be defined as: $$Γ(i,j)=r_{ij}$$ For user-user collaborative ...
2
votes
0answers
353 views

wrong prediction from graphlab.recommender.item_similarity_recommender

I have a question about basic understanding of how item-item collaborative filtering of "Graphlab" library works. I run this code: ...
2
votes
0answers
362 views

Taxonomy of recommender system methodologies

There's tons of material online but yet I can't reconcile the different definitions for recommender system methodologies / strategies. I think we can identify several axes: memory vs model based; ...
2
votes
0answers
1k views

How to use Python's FastFM library (factorization machines) for recommendation tasks?

I have a dataset of <user, item> pairs where each entry records which user bought which item. e.g. ...
2
votes
0answers
98 views

Selecting the number of hashes for minhash? Working with extremely sparse data and want more collisions

I'm attempting to use minhash to generate clusters and similarities, and I am primarily using ideas from these resources. http://www2007.org/papers/paper570.pdf https://chrisjmccormick.wordpress.com/...
2
votes
0answers
399 views

Spark ALS-WR giving the same recommended items for all users

We are trying to build a recommendation system for a supermarket with diverse item types (ranging from fast-moving grocery to low-moving electronic items). Some items are purchased more frequently in ...
2
votes
0answers
202 views

How to create Self learning data product

I am trying to build price recommendation solution for clients in a scalable manner. I have two choices as below. Professional service: Statistician involvement to build regression model or any ...
2
votes
0answers
319 views

Creating Data model for mahout recommendation engine

I am trying to build an item-item similarity matching recommendation engine with mahout. The data set is as in the following format ( attributes are in text not in numerals format ) ...
2
votes
0answers
46 views

Modeling Pipeline Budget

I have been tasked with creating a pipeline chart with the live data and the budgeted numbers. I know what probability of each phase of reaching the next. The problem is I have no Idea what to do ...
2
votes
3answers
1k views

Cosine similarity with arrays contaning NaN

I am trying to calculate a cosine similarity using Python in order to find similar users basing on ratings they have given to movies. As it can be expected there are a lot of NaN values. I am using ...
1
vote
0answers
18 views

How to get KNN linearly hybridised by two similarities?

I'm writing a KNN (collaborative filtering) hybrid similarity recommender and I need some advice. It is based on this paper. I've currently got 2 datasets. The first one is ...
1
vote
0answers
32 views

How does an autoencoder 'fill in the blanks' in the context of a recommender system?

My understanding is that an autoencoder takes an input, produces a lower dimensional representation of the input, which should explain the original features in the dataset, and then reconstructs the ...
1
vote
0answers
22 views

How to use sklearn's Matrix factorization to predict new users' scores

I'm trying to use sklearn.decomposition.NMF to a matrix R that contains data on how users rated items to predict user ratings ...
1
vote
1answer
43 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 ...
1
vote
1answer
27 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 ...
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 ...
1
vote
1answer
169 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 ...
1
vote
1answer
85 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 ...
1
vote
0answers
15 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
0answers
28 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 ...
1
vote
0answers
127 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
vote
1answer
66 views

How do I build a recommend system based on user's past purchases?

I am exploring approaches to build a model that shows personalized search results (with or without query) for a fashion eCommerce platform. For that I am first working on coming up with a bunch of ...
1
vote
0answers
62 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 ...
1
vote
0answers
17 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 ...
1
vote
0answers
37 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 ...