MFMAP: Learning to Maximize MAP with Matrix Factorization for Implicit Feedback in Recommender System

Recommender systems are increasingly being used in university or online education. However, recommender systems still have not found major usage in K12 education. This may be because of the unique challenges that recommender systems face when used by a young and diverse population. However, recommender systems for K12 education could provide many benefits for students and teachers, such as the simplification of personalized learning. Some of the issues with K12 educational recommender systems may be solved by the use of deep learning and implicit feedback. As such, we investigated the use of deep recommendation algorithms and implicit feedback for K12 educational recommender systems. To do this, we compared metrics for highly cited traditional and deep recommendation algorithms trained on explicit and implicit data. We found that recommendation algorithms using deep learning as a group do not differ in performance compared to traditional recommendation algorithms. We also found that the use of implicit feedback led to higher performance than using explicit feedback. The best performing algorithm used both deep learning and implicit feedback. We conclude that deep learning can be a benefit for K12 recommender systems, particularly when the ordered sequence of items is carefully accounted for. We also conclude that researchers and developers must carefully consider which feedback contributes the most information for learning.

The two main tasks addressed by collaborative filtering approaches are rating prediction and ranking. Rating prediction models leverage explicit feedback (e.g. ratings), and aim to estimate the rating a user would assign to an unseen item. In contrast, ranking models leverage implicit feedback (e.g. clicks) in order to provide the user with a personalized ranked list of recommended items. Several previous approaches have been proposed that learn from both explicit and implicit feedback to optimize the task of ranking or rating prediction at the level of recommendation algorithm. Yet we argue that these two tasks are not completely separate, but are part of a unified process: a user first interacts with a set of items and then might decide to provide explicit feedback on a subset of items. We propose to bridge the gap between the tasks of rating prediction and ranking through the use of a novel weak supervision approach that unifies both explicit and implicit feedback datasets. The key aspects of the proposed model is that (1) it is applied at the level of data pre-processing and (2) it increases the representation of less popular items in recommendations while maintaining reasonable recommendation performance. Our experimental results - on six datasets covering different types of heterogeneous user's interactions and using a wide range of evaluation metrics - show that, our proposed approach can effectively combine explicit and implicit feedback and improve the effectiveness of the baseline explicit model on the ranking task by covering a broader range of long-tail items.

A recommendation system is a method that provides suggestions of items that might users like. There are many domains that can be recommended, one of the most demanded domains by users today is food. In the era of big data, food choices from the large amount of data make it difficult for users to choose the right food for them. The collaborative filtering (CF) approach is considered capable of providing accurate and high quality item suggestions. One of the algorithms that can provide good performance results from the CF approach is Matrix Factorization (MF). This study aims to test a dataset that contains product ratings of food items using three MF algorithms, which are Singular Value Decomposition (SVD), SVD with Implicit Ratings (SVD++), and Non-Negative Matrix Factorization (NMF). Different latent factors are also used for the purpose of improving the performance of the proposed recommendation system algorithm. The dataset used is Amazon Fine Food Reviews. The study shows NMF and SVD++ as the best algorithm for generating user rating predictions for items. NMF has the smallest average prediction error as measured by MAE which is 0.7311. While SVD++ obtains the smallest prediction error value of 1.0607 as measured using RMSE. In addition to these results, the top-n evaluation also shows that the proposed algorithm performs quite well. The hit ratio value for each different n-item always increases proportionally to the number of recommended n-items. The highest hit ratio value is generated from the SVD++ algorithm of 0.0025 on n-item recommendations of 25 items. Overall it can be said that the proposed algorithm has good performance in providing item recommendations.

Recommender systems aim to help users to find items that fit their requirements and preferences. In that field, the collaborative filtering (CF) approach is considered as a widely used one. There are two main approaches for CF: memory-based and model-based. Both of the two approaches are based on the use of users' ratings to predict the top-N recommendation for the active user. Despite its simplicity and efficiency, The CF approach stills suffer from many drawbacks including sparsity, gray sheep and scalability. The aim of this work is to deal with the gray sheep problem, by proposing a novel collaborative filtering approach. This novel approach aims to enhance the accuracy of prediction by turning the users whose preferences disagree with the target user, into new similar neighbors. For instance, if a user X is dissimilar to a user Y then the user $\lnot$X is similar to the user Y.To evaluate the performance of the proposed approach, we have used two datasets including MovieLens and FilmTrust. The Experimental results show that our approach outperforms many traditional recommendation techniques.

Collaborative filtering (CF) approach is successfully applied in the rating prediction of personal recommendation. But individual information source is leveraged in many of them, i.e., the information derived from single perspective is used in the user-item matrix for recommendation, such as user-based CF method mainly utilizing the information of user view, item-based CF method mainly exploiting the information of item view. In this paper, in order to take full advantage of multiple information sources embedded in user-item rating matrix, we proposed a rating-based integrated recommendation framework of CF approaches to improve the rating prediction accuracy. Firstly, as for the sparsity of the conventional item-based CF method, we improved it by fusing the inner similarity and outer similarity based on the local sparsity factor. Meanwhile, we also proposed the improved user-based CF method in line with the user-item-interest model (UIIM) by preliminary rating. Second, we put forward a background method called user-item-based improved CF (UIBCF-I), which utilizes the information source of both similar items and similar users, to smooth itembased and user-based CF methods. Lastly, we leveraged the three information sources and fused their corresponding ratings into an Integrated CF model (INTE-CF). Experiments demonstrate that the proposed rating-based INTE-CF indeed improves the prediction accuracy and has strong robustness and low sensitivity to sparsity of dataset by comparisons to other mainstream CF approaches.

The Recommendation System plays an increasingly important role in our daily lives. With the increasing amount of information on the internet, the recommendation system can also solve problems caused by increasing information quickly. Collaborative filtering is one method in the recommendation system that makes recommendations by analyzing correlations between users. Collaborative filtering accumulates customer item ratings, identifies customers with common ratings, and offers recommendations based on inter-customer comparisons. This study aims to build a system that can provide recommendations to users who want to order or choose fast food menus. This recommendation system provides recommendations based on item data calculations with customer review data using a collaborative filtering approach. The results of applying cosine similarity calculation to determine fast food menu recommendations obtained for the item-based recommendation is Pizza Frankfurter BBQ Large with a value of 1.0, item-based with genre recommendation is Calblend Float with value 1.0 and user-based recommendation is Pizza Black Pepper Beef / Chicken Large with mean score 2.5.

Recommendation technology is an essential component of the Internet of Things (IoT) services that can help users get information at any time and from any place. Traditional recommendation algorithms, on the other hand, are unable to satisfy the IoT environment’s swift and reliable recommendation criteria. The use of mathematical and information discovery methods to overcome the relationship with target consumers in order to have desired items is known as a recommendation system. In this paper, a recommendation algorithm based on collaborative filtering is proposed. In this sense, the recommendation method (Recommender Systems) was developed; it is focused on the user’s characteristics, such as hobbies, and it is recommended to satisfy the object’s user specifications, also known as customized recommendation system (Personalized Recommender Systems), The majority of modern e-commerce recommender programs tend to recommend the best goods to a customer, believing that each product’s properties remain constant. Some properties, such as price discounts, can, however, be customized to respond to the preferences of each customer..

In order to tackle the problem of information overload and effective recommendation based on users' preference, need, and interest a number of research contributions has been made for the development of recommender systems. However, certain challenges, such as data sparsity, profiling attack, and black-box recommendation still exist and hamper their prediction accuracy. In this paper, we propose a hybrid approach to predict user ratings by incorporating both trust and context of the users in traditional recommender systems using collaborative filtering method. The similarity between two users is computed using both trust value and context-based similarity. The trust value is based on three trust statements -- rating deviation, emotions, and reviews helpfulness. On the other hand, context-based similarity is based on four contextual features -- companion, place, day, and priority. The performance of the proposed trust- and context-based hybrid approach is analyzed using mean absolute error and root mean square error on a real dataset generated from two movie data sources (IMDB and Rotten Tomatoes), and it performs significantly better in comparison to some of the standard baseline methods. The rating prediction using only trust statements gives better results in comparison to other collaborative filtering approaches, such as user-based and item-based filtering approaches. Similarly, context-based collaborative filtering approach also outperforms standard collaborative filtering approaches. In addition, rating prediction using both trust- and context-based features performs better in comparison to only trust-based or context-based approaches.

The Indian market for internet shopping has already been penetrated by E-Commerce. People are increasingly attracted to shop online, which has altered the market landscape. Amazon, Snap deal, Flipkart, and more companies offer online shopping sites that are gaining traction. As the number of online buyers and dealers grows, smart business approaches are required to deal with the massive amounts of data generated every day. Recommendation systems play a crucial role in sifting this data and giving consumers with relevant information. Various strategies for recommender systems have been used, such as Collaborative Filtering, Content-based, and Demographic, but these techniques have a number of flaws that make them ineffective. Among these collaborative filtering approach is widely popular because of its simplicity and accuracy. But still these systems can be improved in their accuracy when used for multiple domains. As a result, more distinguishing traits must be identified in order to optimize these procedures. This can be accomplished by combining the benefits of multiple strategies in a hybrid approach. This paper describes a hybrid approach that identifies the users with shared preferences (semantic users) and their dynamic interests with parallel training to improve recommendation efficiency. Results were compared with other state of art techniques and the accuracy of our system is found to be improved by 2% and seems to give promising results for multiple domains.

Recommender Systems (RSs) have emerged as powerful tools to provide the users with personalized recommendations and to guide them in their decision making process. Among the various recommendation approaches, Collaborative Filtering (CF) is considered as one of the most popular techniques in RSs. CF techniques are categorized into model-based and memory-based. Model-based approaches consist in learning a model from past ratings to perform predictions while memory-based ones predict ratings by selecting the most similar users (user-based) or the most similar items (item-based). In both types, recommendations are fully based on users’ past ratings. However, aside from users’ ratings, exploiting additional information such as items’ features would enhance the accuracy of the provided predictions. Another crucial challenge in the RSs area would be to handle uncertainty arising throughout the prediction process. That is why, in this paper, we propose an item-based Collaborative Filtering under the belief function theory that not only takes advantages of both model- and memory- based CF approaches but also integrates items’ contents in the recommendation process.

Recommender systems are essential engines to deliver product recommendations for e-commerce businesses. Successful adoption of recommender systems could significantly influence the growth of marketing targets. Collaborative filtering is a type of recommender system model that uses customers' activities in the past, such as ratings. Unfortunately, the number of ratings collected from customers is sparse, amounting to less than 4%. The latent factor model is a kind of collaborative filtering that involves matrix factorization to generate rating predictions. However, using only matrix factorization would result in an inaccurate recommendation. Several models include product review documents to increase the effectiveness of their rating prediction. Most of them use methods such as TF-IDF and LDA to interpret product review documents. However, traditional models such as LDA and TF-IDF face some shortcomings, in that they show a less contextual understanding of the document. This research integrated matrix factorization and novel models to interpret and understand product review documents using LSTM and word embedding. According to the experiment report, this model significantly outperformed the traditional latent factor model by more than 16% on an average and achieved 1% on an average based on RMSE evaluation metrics, compared to the previous best performance. Contextual insight of the product review document is an important aspect to improve performance in a sparse rating matrix. In the future work, generating contextual insight using bidirectional word sequential is required to increase the performance of e-commerce recommender systems with sparse data issues.

Collaborative filtering and deep learning based recommendation system for cold start items

With the arrival of the era of big data, recommendation algorithm has become a hot research field in internet life and social business. However, the traditional recommendation algorithms have problems of cold start, scoring matrix data sparse, affecting the accuracy of recommendation. This paper proposes a hybrid recommendation algorithm based on the SVD (singular value decomposition) and Slope One algorithm, experiments results show that the algorithm proposed by this paper has superior performance compared with the traditional collaborative filtering recommendation algorithm. Keywords-SVD; Slope-One; Recommendation Algorithm; Collaborative Filtering

Traditional recommendation algorithms, such as collaborative filtering, make recommendations by learning the relevant relationships between users and items. However, considering only the relationships without considering the underlying causal mechanisms would be unfair, uninterpretable, and would lead to bias. In this paper, we propose bias-based denoising causal recommendation algorithm (BDCR) . First, the method dynamically transforms the explicit user-item feedback into implicit feedback with an embedded representation. Then, a truncation function based on causal inference is constructed to remove false positive noise. In addition, traditional recommendations and denoised causal recommendations are aggregated to obtain predictive scores. Finally, experimental results on two real datasets show that the BDCR algorithm outperforms the classical algorithm in terms of recall and NDCG metrics.

With the speedy development of network, information technology has provided an unmatched amount of information resources. It has also led to the problem of information overload. However, people experiences and knowledge often do not enough to process the vast amount of usable information. Thus, approaches to help find resources of interest have attracted much attention from researchers. And recommender systems have arrived to solve this problem. Recommender system plays an important role mainly in an electronic commerce environment as a new marketing strategy. Although a varied of recommendation techniques has been developed recently, collaborative filtering has been known to be the most successful recommendation techniques and has been used in a number of different applications. But traditional collaborative filtering recommendation algorithm has the problem of sparsity. Aiming at the problem of data sparsity for personalized filtering systems, a collaborative filtering recommendation algorithm based on user rating similarity and user attribute similarity is given. This approach not only considers the user item rating information, but also takes into account the user attribute.