Questions tagged [recommender-system]

A recommendation engine tries to predict how much a user will enjoy certain goods (movies, books, songs, etc) and makes recommendations. They are often used by online vendors to suggest new purchases.

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

How to manage the influence of variables for lsa cosine?

I'm building reccomendation system for movies and the following data ...
0
votes
0answers
24 views

Find correlation between million of users (user-user similarity) in pyhton 3.x [closed]

I have a pandas dataframe as given below, and in which I would like to find the correlation between the customers based on the rating. As per my knowledge, I would have to pivot the dataframe in order ...
1
vote
1answer
59 views

Bayesian matrix factorization

I am working with Bayesian matrix factorization using the MovieLens database. Data consist of a matrix $n \times d$ of $n=943$ users and $d=1682$ movies where users assign a rate (1-5) to movies. ...
0
votes
0answers
4 views

Accounting for link order for a navigational recommender system for mobile app

I've been asked to look at a navigational recommender system for a mobile app. Basically, they have a fairly unwieldy navigation section and lots of recurring users. Users typically just use some ...
0
votes
0answers
13 views

How to build a recommendation system for users outside of original model data?

I am creating a collaborative filtering model in Python to recommend possible movies a user may like. So, using typical methods in this field, I have a sparse matrix nxm with n users and m movies. ...
1
vote
1answer
11 views

What models/algorithms should I research to make a community-driven movie recommendation system?

Pretty new to ML so sorry if this question has been answered before. Dataset of: users (100,000 unique) movies (7000 unique) w/ genre data (action, comedy) and plot summary for each user, a list of ...
1
vote
0answers
7 views

Can a matrix factorization algorithm be guaranteed to converge to a global minimum?

Collaborative filtering is a common technique used by recommender systems. Matrix factorization is a common way to do collaborative filtering. The problem of matrix factorization for recommender ...
0
votes
0answers
7 views

Matching varying amounts of attributes for an user

Background: We are trying to build a system that ranks created content to match user's needs. We have 5 attributes to match for each user but varying amounts of attributes for each content (1-5). The ...
0
votes
1answer
44 views

Mean Percentage Ranking in implicit feedback ALS

What is Mean Percentage Ranking in implcit feedback recommendation systems. Why should it be less than 50%? There are vague definitions in many forums. But, no clear cut examples. Can someone explain ...
0
votes
1answer
15 views

How to define precision@k in this KDD paper?

I am following this KDD paper trying to learn new things: http://keg.cs.tsinghua.edu.cn/jietang/publications/KDD12-Tang-et-al-Cross-Domain-Collaboration-Recommendation.pdf In the results section they ...
1
vote
0answers
51 views

User-based vs Clustering-based Collaborative Filtering

Reading about recommender systems in this blog, i found that KNN (k-nearest neighbors) can be used for user-item (user-based) collaborative filtering to find similar users. But in another category of ...
0
votes
0answers
19 views

Ranking based on explicit feedback, user features and item features

Consider the following matrix of scores for user-item pairs: ...
1
vote
1answer
17 views

Is Matrix Factorization also going to work with one feature?

I need to fill missing values. I have found that there are many approaches such as the mean and the median of the feature as well as using Matrix Factorization. However, I am kind of wondering if I ...
0
votes
0answers
6 views

Recommending without knowing the clusters

I've heard of some methods to produce recommendations based on clustering: if many of the users who enjoy A also enjoy B, and you enjoy A, then you are likely to enjoy B. A and B in this case form a "...
1
vote
2answers
66 views

Is there a method to compare prediction from different models?

I have a problem where I need to classify whether a client is likely to buy or not a service, I have around 10 service and 10.000 times more clients than service, and also rules that do not allow ...
1
vote
1answer
16 views

Normalizing product quantities to use them as implicit ratings in Product Recommendation

I am running a product recommendation using ALS method on retail transaction data. A simple question struck my mind on the using the methodology in case of implicit ratings. In my case I am using the ...
0
votes
0answers
15 views

Why to say neural network can extract implicit feature combinations?

I just couldn't understand why to say neural network layers can extract implicit feature interactions in the DeepFM model. What does the keyword, implicit feature interactions, exactly mean here? And ...
0
votes
0answers
13 views

How to recommend display advertisements to users based on highest click-trough-rate for multiple banners?

I have several ideas and questions but I'm not sure what is the best approach for this. Any help or feedback would be greatly appreciated! Problem description For a company I want to build a ...
0
votes
0answers
10 views

Context-aware recommender systems for same sets of users

I understand the basic premise of recommendation systems that recommend let's say, products ($X$) to users ($Y$). However, what if the sets $X$ and $Y$ are the same? For example, let's say users have ...
0
votes
0answers
8 views

Recommender System that gives rating and confidence of rating for implicit data

I am trying to find a model that, given an implicit user-item matrix, will return rating estimates for items for a user and some measure of confidence or uncertainty in the score. I am thinking along ...
0
votes
0answers
12 views

Compare similarity between two different clusters having few similar fields?

I have two datasets, one is mentor dataset another is jobseeker dataset. My ultimate goal is to recommend a jobseeker to mentor based on skills and location (skills jobseeker has but need mentorship ...
0
votes
1answer
49 views

A/B testing and Multi-armed bandit algorithms in a recommender system

I was reading about these two algorithms, but I don't understand how they can be used in a recommender system because using the MovieLens dataset these algorithms recommend the best movie for all the ...
0
votes
0answers
4 views

Association Rule Learning to recommend distinct categories---avoiding similar items

I would like to use association rule mining on my orders dataset, however, I want to avoid recommending two similar items. For example, recommending two loaves of bread with butter. I want to ...
0
votes
0answers
10 views

more then one user based Collaborative filtering

I want to get a movie recommendation by selecting multiple users. Usually, it takes one user ID and gives a recommendation. I thought user-based collaborative filtering with KNN is a good idea. I have ...
0
votes
0answers
9 views

How to get recommended users for an item with a matrix factorization recommender system?

Any tutorial or guide I've seen is for recommending items to a user, but how can I recommend users for an item? I am currently using the implicit library alternating least squares model. I have ...
1
vote
0answers
9 views

recommendation based on multiple user

I am learning about the recommendation system. How can I make a system where it takes multiple users as input and based on the rating and another attribute it gives recommendation? I have data sets ...
0
votes
1answer
51 views

How to interpret recommender scores in implicit matrix factorization?

I am using Alternating Least Squares model from the Implicit library on the LastFM dataset, recommending artists to various users. The input data is simply a sparse matrix of users, artists, number ...
0
votes
1answer
30 views

Recommendation system

Hello! In the context of collaborative filtering we must find the elements of the svd matrices that minimize the objective function attached. Since the majority of the actual rankings are missing (...
2
votes
0answers
91 views

Row similarity in matrix vs in different factorizations

Suppose an arbitrary $m \times n$ matrix $M$ and the factorizations: Arbitrary: $M = U_a V_a^T$, where $U_a$ is $m \times k$, $V_a$ is $n \times k$ ($k < m,n$), and $rank(U_a)=rank(V_a)=k$. SVD: $...
0
votes
0answers
16 views

How to build a recommender system?

I am starting a new feature for our startup product and we're trying to build a recommender system. Here's an overview of our product: Users are not related to each other (no friends relation ...
-1
votes
1answer
18 views

Recommender Engine for documents VS Search engine indexing

I have a lot of books and I want to make recommendations to users based on the description and the title of those books. I think that one way is to preprocess the content of the title and ...
1
vote
0answers
23 views

Ranking metric that takes into account length of result list?

I would like to evaluate a problem where the user select an option from a list of variable length. The task is to provide a ranked list so that the item lower in rank is the most relevant. If I use a ...
1
vote
1answer
20 views

How does increasing the rank of latent factor model affect the bias-variance trade off in a recommender system?

I know overfitting means low bias and high variance while under-fitting means high bias and low variance. I want to understand how does increasing the rank of latent factor model affect the bias-...
0
votes
0answers
9 views

Collaborative filtering movie recommender: how to account for missing ratings implying information about user preference?

I'm trying to learn about recommender systems with a fairly standard data set: I have a matrix with thousands of users, thousands of movies, and the ratings that users give to each movie. Obviously, ...
0
votes
0answers
21 views

What is the standard metric used in recommendation systems to evaluate the rankings?

I was searching for a metric to do this for a while and still could not find. More specifically, my problem is as follows. I have a ranked golden corpus. For example, consider that it looks as ...
0
votes
0answers
44 views

Item Based Collaborative Filtering vs Association Rules In Data Mining vs Normalised Co-occurrence Similarity Matrix

Requirement: Find out how similar any two products are, in an e-commerce database, to suggest to the users, similar products, when they've added any product to the cart. Much similar to Amazon's ...
0
votes
0answers
7 views

What is the difference between SVD and Collabarative filtering precisely?

Both are sometimes used interchangebly but still there is a difference between them .
0
votes
0answers
10 views

Good way to solve product recommendation

I need to recommend products based on top selling products for a given day in the past. The only independent variable is date which i can derive some information from such as weekday, month etc. The ...
0
votes
1answer
46 views

Cosine similarity for recommendation systems

Recently picked up recommendation systems and was going through User Based Collaborative Filtering(UB-CF). Somewhere in the text, it specified that cosine similarity is one of the measures to find ...
0
votes
0answers
121 views

Quiz based recommendation system

For my project I would like to make a 'quiz' based recommendation system (for books for example). If a new user comes to the website I want to find out his taste based on some questions, in which I ...
1
vote
1answer
26 views

Concept drift in in user interaction data

concept drift usually refers to the change in the relationship between input and output data over time. I do have dataset of users' activity in an e-commerce website. Let's say we have a sequence of ...
0
votes
0answers
18 views

Can I use learning to rank to recommend products to customers?

I am working on a project to recommend products to customers. I knew the traditional methods was to use recommendation systems. I wonder if I could use learning to rank to provide the best-ranked ...
0
votes
1answer
25 views

N-dimension one hot features representation

I was trying to understand the features representation in this paper: DRN: A Deep Reinforcement Learning Framework for News Recommendation In 4.2 Feature construction, the news features is News ...
0
votes
1answer
37 views

Training classifier on randomly generated negative samples

I have $M$ (~dozen million) feature vectors. There are $F$ (~several dozen thousand) binary features, but in each vector, only $H$ (~several hundred) of them would be 1, the rest are 0. Now, for a ...
1
vote
0answers
9 views

Recommendation Engine and Text Analytics

I am looking for a dataset on which I can use Collaborative filtering and Content based filtering along with Text Mining. Could anybody please suggest , is there any dataset on which I can apply ...
1
vote
0answers
19 views

How to validate Item-Based Collaborative Filtering?

So, I made an books recommender system engine (with R) which based on item-item matrix. I've made the whole system fully works the output will give 5 recommender system. But, the question is how can I ...
0
votes
0answers
26 views

Best Statistical Test for my situation?

For an upcoming project we are trying to create a recommendation algorithm for customers and providers. I will have some number of service providers, probably hundreds to thousands, and some number ...
0
votes
0answers
28 views

Teaching movie recommendation network to avoid duplicates

I'm trying to implement a simple movie recommender using a neural network and collaborative filtering, i.e. given a list of movies the user has watched, what is a good movie recommendation. Results ...
2
votes
1answer
145 views

FindSimilar items in a complex dataset

I'm a Machine Learning newbie, but I want to learn more about this interesting topic using a practical example, on which I would appreciate any theoretical and practical help: I have a database of "...
2
votes
1answer
81 views

Overfitting in recommender systems

So I want to know whether or not my models are overfitting or the difference between train and validation errors are decent. $L$: is the number of neighbors The first column is the train error ...

1
2 3 4 5
8