Goal-based Framework for cold-start problem using multi-user personalized similarities in e-Learning scenarios

This paper presents a prototype for a Web application recommendation system’s content applied to movies’ recommendations. It learns the pattern of user content consumption, predicting what he will consume in future based on similar items to those he has shown interest. It considers similarity with neighbor users, thus creating a user model. Content-based filtering, collaborative filtering, and memory-based on hybrid filtering techniques are used. Content-based filtering allows to extract the fundamental features or attributes of the items and select similar items. Moreover, it proposes predicted classifications for the items of interest not yet classified by the active user. Collaborative filtering allows applying the KNN methodology to identify the similarity between the active user located in the neighborhood and propose predicted classifications for items of interest not yet classified. Hybrid filtering combines the two methodologies to overcome their drawbacks. A weighted approach is applied, allowing a dynamic linear combination of collaborative and content-based filtering. The results obtained were empirically relevant in the experimental evaluation, matching with the results presented in similar studies validated with RMSE metrics.KeywordsInformation systemsRecommender systemsHuman centered computingUser modelsWeb-based interaction

Cooking your own food at home is a good step toward reducing fast food consumption. Fast food increases the risk of dangerous diseases. The diversity of recipe information available on the internet makes it difficult to choose recipes that match user preferences. Mobile technology can help with this by recommending recipes that better suit users' eating habits. This makes the transition to a healthier diet easier. Therefore, in this study, a recommendation system was developed that can recommend recipes based on the preferences of Android users. Two main recommendation methods are used in this study: content-based filtering and collaborative filtering. Using cosine similarity, a content-based recommendation system identifies the proximity between a recipe for food and its related context. The history of user comments on recipes serves as implicit feedback for the collaborative recommendation algorithm. This eliminates the need for explicit evaluations, such as ratings. This recommendation system generates recommendations in the form of the top ten food recipes with an evaluation matrix, referred to as NDCG@k and Hit-Ratio@k. The tests revealed that a content-based filtering technique may produce helpful recommendations, with the highest similarity score of 0.41 for the entry "chocolate cake that you can easily make at home." Meanwhile, in the collaborative filtering method using the Neural Collaborative Filtering (NCF) approach, the system shows consistent performance improvements, with the MAP@10 value increasing from 0.705 to 0.767 and the NDCG@10 from 0.78 to 0.83 after 10 training epochs. Keywords: Recommendation systems; content-based filtering; neural collaborative filtering; cosine similarity; implicit feedback

Recommender systems are the auto systems of providing appropriate information and removing unappropriate information for users. The recommender systems are built based on two main information filtering techniques: Collaborative filtering and content-based filtering. Content-based filtering performs effectively on documents representing as text but has problems to select information features on multimedia data. Collaborative filtering perform well on all types of information but had problems when sparse data, new uses and new items. In this paper, we propose a new unify model between collaborative filtering and content-based filtering by a semi-supervised learning method. The model is built based on two semi-supervised procedures: the first procedure semi-supervise ratings set between users and item’s features, the second procedure semi-supervise ratings set between items and users features. The first procedure allows us to detect new items that is high suitable capability with the users. The second procedure allows us to detect new users that is high suitable ability with the items. Two procedures performed simultaneously and complement each other for suitable predicted values to improve recommender results. The experimental results on real data sets show that the proposed methods utilize effectively the advantages and limit significant disadvantages of baseline filtering methods.

Context-aware recommender systems (CARSs) have emerged from traditional recommender systems (RSs) that provide several different opportunities in the area of personalized recommendations for online users. CARSs promote incorporation of additional contextual information such as time, day, season, user’s personality along with users and items related information into recommendation process that makes market based e-commerce sites more attractive to users. Content-based filtering (CBF) and collaborative filtering (CF) are two well-known and most implemented recommendation techniques that offer various hybridization approaches for producing quality recommendations. Moreover, contextual pre-filtering, contextual post-filtering and contextual modeling are some paradigms through which CARSs take advantages of user’s contextual preferences in recommendation process. In this paper, we introduce a decision tree based CARS framework that exploits the benefits of both CBF and CF techniques using contextual pre-filtering paradigm. We apply ID3 algorithm for learning a user model to exploit the user’s contextual preferences and utilizing rules extracted from decision tree to neighborhood formation. Experimental results using two real-world benchmark datasets clearly validate the effectiveness of our proposed scheme in comparison to traditional scheme.

When we buy items in online stores, it is common to face recommended items that meet our interest. These recommendation system help users not only to find out related items, but also find new things that may interest users. Recommendation system has been widely studied and various models has been suggested such as, collaborative filtering and content-based filtering. Though collaborative filtering shows good performance for predicting users preference, there are some conditions where collaborative filtering cannot be applied. Sparsity in user data causes problems in comparing users. Systems which are newly starting or companies having small number of users are also hard to apply collaborative filtering. Content-based filtering should be used to support this conditions, but content-based filtering has some drawbacks and weakness which are tendency of recommending similar items, and keeping history of a user makes recommendation simple and not able to follow up users preference changes. To overcome this drawbacks and limitations, we suggest weighted window assisted user history based recommendation system, which captures user’s purchase patterns and applies them to window weight adjustment. The system is capable of following current preference of a user, removing useless recommendation and suggesting items which cannot be simply found by users. To examine the performance under user and data sparsity environment, we applied data from start-up trading company. Through the experiments, we evaluate the operation of the proposed recommendation system.

Collaborative filtering (CF), the most successful and widely used technique, recommends items based on the preferences of similar users. The main potentials of CF are its cross-genre recommendation ability, and that it is completely independent of representation of the items being recommended. However, CF suffers from sparsity and cold start problems. On the other hand, a highly effective variant of content-based filtering (CBF), reclusive methods (RMs) based on the preference of the single individual for whom recommendations to be made, provides a methodology that considers uncertainty and the multivalued nature of item features as well as user preferences in a content-based framework using fuzzy logic approaches. The adoption of RM paradigm has several advantages when compared to CF such as sparsity and new item problem, but it suffers from overspecialization and limited content analysis. In view of the complementary nature of CF and RM, we develop a hybrid recommender system (RS) that helps in alleviating aforementioned problems in each approach. First, we propose fuzzy naïve Bayesian classifier based CF (FNB-CF) and RM (FNB-RM) for handling correlation-based similarity problems. To overcome individual weaknesses of FNB-CF and FNB-RM, we develop a hybrid RS, FNB-CF-RM. Effectiveness of our proposed hybrid RS is demonstrated through experimental results using the MovieLens and IMDb data sets.

Item-based recommender systems suggest products based on the similarities between items computed either from past user preferences (collaborative filtering) or from item content features (content-based filtering). Collaborative filtering has been proven to outperform content-based filtering in a variety of scenarios. However, in item cold-start, collaborative filtering cannot be used directly since past user interactions are not available for the newly added items. Hence, content-based filtering is usually the only viable option left.

Recommender systems are called information filtering tools, which use big data to recommend likes of the user according to their preference and interest. Moreover, they also help in matching users with similar tastes and interests. Due to this, a central part of websites and e-commerce applications is taken up by the recommender systems. Systems using recommendation algorithms like Collaborative Filtering, Content-Based Filtering, etc., are called Recommendation systems. Recommendation systems are transforming the way quiescent websites corresponds with their users. Rather than providing an orthodox experience in which users search for the products which they want and potentially buy products, recommender systems increase communication to provide a better experience. The work would be to implement both collaborative as well as content-based recommenders available and try to extend the knowledge obtained to a more efficient hybrid model. Then benchmark these hybrid algorithms for accuracy and computation time as well.

Web personalization is the customization of information or services provided by the Web site according to user needs, through the knowledge of the navigational habits of users and individual interest, combined with the content and structure of Web sites. Objective of Web personalization is to provide information needed by user, without having to ask the user explicitly. In this paper we present analysis and implementation of Web personalization for Web site that sells used cars in Japan. Used cars dealers in Japan mostly sell their cars to other dealers located overseas. Web site is a very effective method to sell because it can be easily accessed by people from all over the world. Since their Web site contains vast amount of cars, Web personalization is expected to facilitate users in finding the desired item. There are a number of aspects and techniques in the development of Web personalization system. The aspects are: the approach of interaction with users, the information used to form the user model, user model renewal time, personalization system architecture, and personalization techniques. Among other Web personalization techniques, we perform analysis for two techniques, namely content-based filtering and collaborative filtering. Based on the analysis of the characteristics of the case (used-cars ecommerce site), content-based filtering is more appropriate than collaborative filtering. The result of Web personalization implementation was tested using k-fold cross validation and variation in the number of training set. Performance accuracy of Web personalization will be calculated using precision and recall, which is commonly applied in information retrieval field. Test with k-fold cross validation produces precision value of 0.322 and the recall of 0.322. Test with variation in the number of training set results that precision and recall values are greater as number of training set increased.

The recommendation system is an application model based on observations of the circumstances and customer desires. In the recommendation system, several methods are used to support how the system works in producing information. One method of recommendation system that is quite popular is the method Hybrid. Several researchers have successfully applied this method in developing a tourism recommendation system, therefore to achieve the goal of implementing a tourism recommendation, it is better to take advantage of a marketing technique such as promotion in order to increase sales and attract more comprehensive customers. Therefore, a literature review on the method hybrid (Collaborative Filtering & Content-Based Filtering) of this travel recommendation system is carried out to collaborate between methods, algorithms, and a tool or media marketing applied in a recommendation system.

Each and every day, a lot of courses are published online by various mentors to help the interested people learn online. But the students who are interested may find it difficult to associate themselves with appropriate course they want as there are so many courses available, even under just a single topic. To help select the best courses for the respective candidate, here a course recommendation system is designed with the concept of hybrid recommender system. Recommendation systems such Content-Based filtering and Collaborative filtering have their own advantages and disadvantages. So, to compensate the shot comes of the respective filtering models, both the models are combined to realize a hybrid recommender system for the Course Recommendation in the Social Learning network. Here, the content-based filtering uses Lasso algorithm and collaborative filtering uses KNN algorithm, and to combine the result obtained by both the filtering methods, weighted average method is used to gain the result as a hybrid result from both the filtering models. This will prove to perform very well with great efficiency for the Course Recommendation in Social Learning Network.

The success of current e-commerce relies on exact and varied recommendations which understand user context to enhance both user satisfaction and engagement levels. This research creates a deep learning-enhanced hybrid recommender system (DL-EHRS), which represents a deep learning-enhanced combination of recommendation systems specifically designed to operate in dynamic e-commerce environments. The proposed model connects Neural Collaborative Filtering (NCF) to Collaborative Filtering (CF) while using Deep Neural Networks (DNNs) together with Content-Based Filtering (CBF) to tackle existing recommendation system shortcomings. The performance benchmark of the DL-EHRS resulted in superior results than baseline models during all evaluation assessments. The recommendations produced through this system achieved high-quality performance at 98.1% accuracy, along with 97.9% precision and 97.8% recall and 97.9% F1-score. The proposed algorithm showed better processing speed than CF, CBF, and NCF because it completed operations in 0.9 seconds on average while readying real-time applications. The fast and stable training process of the model with minimum residual error proved its learning efficiency and ability to generalise through error convergence analysis. The proposed system meets user needs through a combination of latent factor learning techniques, content similarity analysis, along temporal context examination in its recommendation process. The integrated framework shows broad compatibility in online shopping environments because it produces precise predictions and deals with sparse data while generating better interfaces for users.

Purpose – Project ATHENA aims to develop an application to address information overload, primarily focused on Recommendation Systems (RSs) with the personalization and user experience design of a modern system. Method – Two machine learning (ML) algorithms were used: (1) TF-IDF for Content-based filtering (CBF); (2) Classification with Matrix Factorization- Singular Value Decomposition (SVD) applied with Collaborative filtering (CF) and mean (normalization) for prediction accuracy of the CF. Data sampling in academic Research and Development (R&D) of Philippine Council for Agriculture, Aquatic, and Natural Resources Research and Development (PCAARRD) e-Library and Project SARAI publications plus simulated data used as training sets to generate a recommendation of items that uses the three RS filtering (CF, CBF, and personalized version of item recommendations). Series of Testing and TAM performed and discussed. Results – Findings allow users to engage in online information and quickly evaluate retrieved items produced by the application. Compatibility-testing (CoT) shows the application is compatible with all major browsers and mobile-friendly. Performance-testing (PT) recommended v-parameter specs and TAM evaluations results indicate strongly associated with overall positive feedback, thoroughly enough to address the information-overload problem as the core of the paper. Conclusion – A modular architecture presented addressing the information overload, primarily focused on RSs with the personalization and design of modern systems. Developers utilized Two ML algorithms and prototyped a simplified version of the architecture. Series of testing (CoT and PT) and evaluations with TAM were performed and discussed. Project ATHENA added a UX feature design of a modern system. Recommendations – High-end hardware specs of v-Parameter are recommended, at least 8-cores of vCPU with 16GiB of memory and sufficient driver-type size to run the model and End-to-end jobs execution for continuously maintaining the application. Research Implications – Future Developers must use/integrate a large dataset. Other ML approaches can expand Hybrid-RS better. Implicit data and additional filtering methods may enhance the application in the future.

Recommender systems (RSs) have become pillars of personalization in contemporary retail that is improving customer experience and business value. With the help of sophisticated algorithms, retailers will be able to offer personalized product recommendations taking into account the personal preferences of consumers and thus minimizing the information overload and making decisions more easily. Most recommender systems are based on two major approaches, which are Collaborative Filtering (CF) and Content-Based Filtering (CBF). Unlike CBF which pays attention to item attributes and individual interactions of a user to create an item, CF examines user behaviors and preferences of a population to determine the relevant items. The hybrid models unify these two methods in an attempt to ease their disadvantages, which include cold-start, sparsity, and lack of diversity. In addition to the development of algorithms, combination of deep learning and diversification methods has also contributed to the relevance, novelty, and adaptability of recommendations. This review explores the application of recommender system in retail with an overview of the principles of CF and CBF, their contribution to customer engagement, and the latest trends in hybrid and AI-driven recommendation systems. This paper synthesizes the main body of research to show the potential transformational nature of personalized recommendations in maximizing customer satisfaction, loyalty, and revenue generation and outlining the challenges and future research opportunities to further enhance the use of personalized recommendations in retail.

The popularity of movies has increased in recent years. There are thousands of films produced each year. These films make it challenging for movie lovers to pick the ideal film to see. We propose a recommendation system that strives to offer guidance in selecting films. Depending on the method employed, recommendation systems can be categorized into three groups: collaborative filtering, content-based filtering, and hybrid filtering. In this work, collaborative filtering, one of the methods frequently used in recommendation systems was used. There are two ways to the Collaborative Filtering approach: User-Based Collaborative Filtering (UBCF) and Item-Based Collaborative Filtering (IBCF). There are two methods for finding similar items or users: Cosine and Pearson similarities. The Cosine similarity approach is one way to determine how similar two items are. Additionally, the Pearson Correlation Coefficient approach, which determines similarities between objects by calculating linear correlations between two sets, is the most widely employed. This study aims to determine which system produces the highest item similarity in IBCF and predicted ratings to actual ratings using 90% training and 10% testing data. The data set taken from MovieLens.org consists of 943 users from 1664 movies with 99392 ratings. The MovieLens data collection will be analyzed with the RStudio and the R package recommenderlab. The results reveal that the IBCF with Cosine similarities shows the number of items recommended n top-rated movies to each user for 10 movies. The IBCF can identify the most recommended films and creates a frequency distribution of items.