3

You can use Collaborative Filtering, and specifically its memory based approach. The problem that you have discussed in the question should probably be solved using User-Item collaborative filtering which will calculate similarity between users and then recommend the item. The similarity can be be calculated using cosine similarity or Pearson's similarity ...


3

Recommendation systems can be applied for anything, as long as you have sufficient training data. The most important inputs to the recommendation system are not "audio files or video files". Wikipedia gives you the list: Similarity matrix Item attributes User activities and behaviours User profile https://en.wikipedia.org/wiki/Recommender_system


3

Let me try to explain how recommender systems work in production, as intuitively as possible: Let's say we want to build a rec sys. for a restaurant discovery product, where users can rate restaurants, add reviews, photos, etc and also order food from there. So, the user's feed will have a list of restaurants in his/her area. But, as I gain money from ...


2

From what I understood you will not have any cold start problem because you basically process the user preferences description against movies descriptions to get recommendations. So you don't use other users feedback at any time of the process which is not collaborative filtering. Here is instead the approach I would suggest in your case to get movies ...


2

I found the answer further into the paper! I'll post it here for everyone. Given any user, there is no pre-known targeted item in the KGRE-Rec (Knowledge Graph Reasoning for Explainable Recommendation) problem, so it is unfeasible to consider binary rewards indicating whether the agent has reached a target or not. Instead, the agent is encouraged to ...


2

You're looking for a heatmap. Check out e.g. https://stackoverflow.com/q/33282368/3924118 (if you like Python more than the others). See also this documentation.


1

$\text{rank}(f((r,e)|u))$ in $A_t(u)$ means to compute the value of scoring function $f$ for all pairs $(r,e)\in A_t$ which are conditioned by $u$, then sort them in a descending order. The rank of the $f((r,e)|u)$ in this order is equal to $\text{rank}(f((r,e)|u))$. Hence $\text{rank}(f((r,e)|u)) \leqslant \alpha$ means to select the $\alpha$ top most ...


1

To put this insert to context, we should take at least this much of text from the paper: One line of research focuses on making recommendations using knowledge graph embedding models, such as TransE [2] and node2vec [5]. These approaches align the knowledge graph in a regularized vector space and uncover the similarity between entities by calculating ...


1

I would say that your intuition is correct: the model associated with the first plot is likely to generalise more than the one associated with the second plot. In both cases, it doesn't seem that your model has overfitted the training data. Overfitting often occurs when the training error keeps decreasing but the validation error starts to increase. In both ...


1

Before trying to explain this term in your context, let me briefly describe the term in other contexts. In computer networking, the term "hop" refers to a node (e.g. a router) that a packet goes through before reaching its destination from its source. In a multi-hop situation, you have several nodes involved in the process of sending the packet from the ...


1

AI can transform the customer experience is by providing personalized content. For example, When you see video recommendation on YouTube, you'll know that it's from AI technology. I recommend you to read this article for knowing how they work: A Sentiment-Enhanced Hybrid Recommender System for Movie Recommendation: A Big Data Analytics Framework (abstract, ...


1

This sounds to me like a use case for a chatbot. You would have different intents reflecting the types of user queries that your system can respond to. The intent matching can be done by pattern matching, machine learning (classification), or a combination of the two (hybrid). You can then use the chatbot to ask clarification questions or elicit more ...


1

That is not what an auto-encoder is doing. An auto-encoder gives you a compressed representation of the input. It is trained by mapping the input data to itself, with the compressed form in between. To predict recommendations, you need to train your input data on existing user recommendations.


1

I would suggest to convert the documents into TF-IDF(use Gensim) vectors and then compare them using various similarity calculating techniques like cosine similarity. You should read this amazing article for the same. I once used it while working on my project. https://medium.com/@adriensieg/text-similarities-da019229c894


1

I did it! A = importdata('u.data'); user_id = A(:, 1); movie_id = A(:, 2); rating = A(:, 3); % Build matrix R and w (weights matrix) R = zeros(943, 1682); w = zeros(943, 1682); for i=1:100000 R(user_id(i), movie_id(i)) = rating(i); w(user_id(i), movie_id(i)) = 1; end m = HeatMap(R) ax = hm.plot; % 'ax' will be a handle to a standard MATLAB axes. ...


1

Some of the cases content-based filtering is useful is: Cold-start problem: it happens when no previous information about user history is available to build collaborative filtering, so in this case, we offer to the user some items then recommend based on the similarity between these items and other items in the dataset alternate of recommending any items ...


Only top voted, non community-wiki answers of a minimum length are eligible