Stack Exchange Network

Stack Exchange network consists of 175 Q&A communities including Stack Overflow, the largest, most trusted online community for developers to learn, share their knowledge, and build their careers.

Visit Stack Exchange

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.

0
votes
0answers
15 views

State of the art on the recommendation system [on hold]

I want to create an ambitious recommendation system. My objective is to approach the state of the art in this field. I have identified 2 interesting approaches: The customer data based approach (...
0
votes
0answers
15 views

Recommender system with extra variables

I would like to to create a recommendation engine that makes use of a utility matrix (user-item interactions) as well as supplementary features (user features, item features and time-based features). ...
0
votes
0answers
17 views

Is it useful to add a proportion hyperparameter in the concatenation layer?

I'm reading a paper on deep learning-based recommender systems: Neural Collaborative Filtering. There are two sub-networks, GMF and MLP, which are fused into a unified model, by a concatenation layer. ...
0
votes
0answers
15 views

Matrix formation and calculation for Collaborative filtering in Neural Network

Intution I am trying to implement Collaborative Filtering (User Based and Item Based) in Python Keras with neural networks. For user based CF with neural network, my input is rating matrix with ...
2
votes
0answers
16 views

Building a job recommendation system [closed]

I am building a job recommendation system where in i have the required skills for each role along with the value of the skill relevant for the role. Example of the dataset is as shown in the image. ...
5
votes
1answer
67 views

Implicit Feedback Factorization Machines : Format of Input and Recommendations

I am looking at methods for making product recommendations to customers based on attributes of the customer (e.g. demographics) and past product interactions (e.g. did or did not buy). There are ~250 ...
0
votes
0answers
14 views

Algorithmic recommendations for adaptive content suggestion

I am interested in learning the ins and outs of adaptive content suggestion (similar to what facebook, google ads, youtube, netflix, linkedin and similar services typically do). I am new to the topic ...
0
votes
0answers
16 views

Clustering/Similarity between drivers

I have a dataset that contains initial and ending points of car trips: ...
1
vote
0answers
18 views

How SVD factorisation -based recomendation algos deal with new user interaction

Classic SVD and SVD++ alogritms generate predictions based on a current known ratings only for known users and known items. But I need to make prediction for some new user on the old items. In the ...
0
votes
0answers
11 views

Assigning weights to the features used in content based recommendation

I am trying to make a recommendation engine for book business which has following features associated with the books: Book Region Book Market Segment Publish Date Book Genre Book Type and so on ...
0
votes
0answers
21 views

Factorized matrix for recommendations, what then?

I have a dataset that looks like this: Image taken from this blog Let's assume that I have applied Matrix factorization and have learned the zero values for the items missing for every user. I now ...
2
votes
0answers
103 views

Does anyone know the rank of the Netflix Prize dataset?

I'm looking into the Netflix Prize at the moment. We model the dataset as an $n \times m$ matrix, where $n$ is the number of users and $m$ is the number of movies. Does anyone know the rank of the ...
0
votes
0answers
45 views

Learning similarity of representations

I am interested in a framework for mapping together input representations based on some common context. I have looked into word2vec, which does more or less what I want, but I want to know if anyone ...
0
votes
0answers
41 views

Data normalization for recommender system

Does anyone know whether it's a good idea to standardize your data by replacing it with the percentile which it occupies in a distribution? Instead of substracting the mean and dividing by standard ...
0
votes
1answer
43 views

Offline evaluation of Counter factual data for Recommendation

I am building new model and facing at offline evaluation tasks. My goal is to predict higher CTR(=click/impression) advertisement, and improve sales.(sales would improve if user watch more ...
0
votes
0answers
22 views

How to evaluate the goodness of a KNN-based recommender system?

I'm building a content-based recommender system and I'm using KNN. That means, for each test instance I'm using KNN to find the most similar objects, and then come up with a recommendation. However I'...
2
votes
0answers
37 views

Is there a well established algorithm to match two documents on a semantic level?

I have a set of documents from a wide variety of topics and I would like to retrieve the ones that are more similar to a new document provided. A search based on common words is not good enough, so ...
0
votes
0answers
34 views

Classification model for recommender system?

I have some data for various customers choosing one of 'n' products or no product. I have some useful features for each customer. I can build a multi-class classification problem out of this data and ...
0
votes
0answers
19 views

Build customer ratings from subscription datetime data for a recommendation system

I want to build a recommendation system with only some customer's subscription and unsubscription date. I have a database that looks like: ...
0
votes
0answers
28 views

How to build a recommendation engine using a regression algorithm?

I'm working on a recommendation problem in which I want to recommend the best setting/configuration for a machine, i.e. what wheel material results in longer run life for a machine (machine can be ...
0
votes
0answers
7 views

Predict / recommend products based user historic purchases

I am making a trend based product recommendation based on order data of users. I have users which has a trend of buying item A everyday, item B every third day, item c after 10 days and so on. I ...
0
votes
0answers
24 views

Recommender using classification

Hi I'm tasked with building a recommender for predicting item categories to users. I have data about which items the user has viewed and bought respectively. I'm interested in turning this into a ...
0
votes
1answer
63 views

what is latent feature in collaborative filtering

What are latent features in collaborative filtering algorithms? I've been reading about it but don't really understand it. Are latent features the learned matrices from matrix factorization; the ...
0
votes
0answers
23 views

How to tune an exponential smothing function pon implicit feedback collaborative filtering recommenders

I am developing a recommender based on implicit feedback. The feedback is mainly the time someone spends on a product in a day. Then I transform this feedback to a rating matrix in order to implement ...
1
vote
1answer
48 views

How can I build a recommender system that accepts data of varying granularity?

I'm tasked with building a recommender system that can make recommendations based on input data of varying levels of granularity. To explain what I mean, let's use a running example of a Movie Title ...
2
votes
0answers
16 views

Pairwise recommender system

How can I model the following situation? I am looking for high level recommendations. if say a man with certain attributes (income, age, etc ...) rates a car with a given attributes (color, ...
0
votes
0answers
9 views

Learn mapping function item to item

I'm trying to resolve a problem in which a set of items have to be mapped to another set of items. The mapping has to be one to one and the items have attributes that describe them (e.g. name, ...
0
votes
0answers
49 views

How to normalize data while training implicit data by Alternating Least Squares

I have an order table stored user buying history. I want to use Alternating Least Squares to do collaborative filtering, but there is no score, which make me have to use product buying count as score....
1
vote
0answers
39 views

Personalize Recommendations for small dataset

I'm working on a recommender system for a set of niche products. These are products that don't have a large number of customers. Does anyone have any tips on algorithms or approaches that work well ...
2
votes
1answer
77 views

Amount and sparsity of data for recommender systems

I'm starting to work in a project that will have a recommender system as one of its components. I'm trying to figure out if I have the right type of data for the recommender. The data contains ...
0
votes
1answer
113 views

Why the maximum sparsity is 99.5% in collaborative filtering? [duplicate]

From https://jessesw.com/Rec-System/ says 98.3% of the interaction matrix is sparse. For collaborative filtering to work, the maximum sparsity you could get away with would probably be about 99.5% ...
1
vote
1answer
48 views

How do recommender systems incorporate user characteristics?

I'm new to recommender systems, and I've been reading about how user-based collaborative filtering can group similar users together and (for example) use their ratings to suggest movies to other ...
1
vote
0answers
49 views

Extracting latent vectors from autoencoder similar to SVD

I have read that there is an equivalency between a linear autoencoder and performing SVD. SVD can be used in collaborative filtering, for example, factorization of a user-movies matrix $\mathbf{M}$ ...
0
votes
0answers
7 views

Does increasing the number of users improve BPR

I'm trying to improve recommendations for my recommender system using Bayesian personalized ranking. I've tried increasing the amount of seen and unseen items I'm training my model on for a small ...
0
votes
0answers
5 views

Has there been research on “Hierachical / Adaptive” Context-Aware Recommendation Systems

In many machine learning fields we tend to have "BigDataset", from which we try to extract meaningful signals. In general we attempt to increase valuable data density for an User Interface. ...
0
votes
1answer
299 views

Training and testing an autoencoder on very sparsely populated data

I am exploring the possibility of using a deep autoencoder neural net to build a recommender system. I am firstly testing the model's performance on the traditionally used benchmark of the Movielens ...
2
votes
1answer
150 views

How to rank products using deep learning for recommender systems?

I am going to implement a recommender system based on this paper. It basically uses a double embedding technique, one for the user representation and another one for the products (movies, clothes, ...
0
votes
1answer
24 views

Which Recommendation Algorithm for Sending Offers to Clients?

We are trying to identify which offers to send to our clients through email. Suppose we have offers with the following data: Offers: [ {
 id: 1, countriesVisited: { ...
0
votes
0answers
141 views

Type of Recommendation engine algorithm to use

I'm planning to build a recommendation engine for a market place. The market place has User1,User2,,,,,,,UserN (with new users joining all the time). Each user has city and state information. Market ...
3
votes
1answer
193 views

Autoencoders and Collaborative Filtering: Is one network per training sample really necessary?

I have been researching on how to apply neural networks to recommender systems and have come across this paper (AutoRec: Autoencoders Meet Collaborative Filtering by Sedhain et al.) where they model ...
0
votes
0answers
24 views

Deep VBPR Regularization Term question

I'm trying to understand/run the code in the repo below: https://github.com/kang205/DVBPR It's a tensorflow implementation in python of the model described in this paper: "Visually-Aware Fashion ...
0
votes
0answers
18 views

Which curve comparison should I use to evaluate the performance of a recommender?

I am building a recommender system on the Last.FM dataset (link here) (1,892 users and 17,632 artists and the number of times a particular artist was listened to by a user). Next, the raw dataset was ...
3
votes
1answer
954 views

What is the relation between SVD and ALS?

I am trying to build a simple CF-recommender system using the small MovieLens data set. In order to do this, I tried to use ALS to factor my (user, item) matrix $A$ into a (user, latent-space) matrix $...
0
votes
0answers
93 views

How to build a User Profile in Recommendation Systems?

I am building a recommendation system using tf-idf technique and cosine similarity. So far I am already recommending items given an item information. My concern is more about the learning part. I know ...
0
votes
0answers
29 views

Improving cold-start recommend systems

I am using tensorrec (python framework for recommendation, based on tensorflow) to predict a users choice of content, based on the users meta-data. My current accuracy is at about 2,5% *. Since this ...
0
votes
1answer
123 views

Why RMSE over MAE for matrix factorisation?

I have been trying to compare several matrix factorization algorithms and I've noticed that all the papers and libraries I've seen measure the Root Mean Square Error(RMSE) when intuitively I would ...
0
votes
0answers
73 views

Customer similarity for customer-product interactions over time

I have a table that has 3 columns: Customer, Item and Date of Interaction between customer and item. I would like to calculate a similarity between customers based on how these customers interact with ...
0
votes
1answer
412 views

MAE and Precision for Collaborative Filtering Recommender Systems

I have got a question concerning Recommender Systems and Evaluation Metrics. I tested a few collaborative filtering recommendation algorithms on dataset containing amazon ratings. Here you can see MAE ...
0
votes
2answers
70 views

How good is my recommender?

I implemented a recommender using tensorflow, based on e-commerce data. This recommender is predicting the next item a user will buy. I will judge the performance of my fitted model, by getting the ...