Analysis of Prediction Accuracies for Memory Based and Model-Based Collaborative Filtering Models

Recommender Systems are used for finding the needle in the haystack. Recommender systems are of one the innovations in this revolution, which addresses the problem of filtering the data/information that is more likely to. Collaborative filtering is a technique which makes automatic predictions, by collecting the preferences for the users. But collecting the preferences from the user is no easy task. The Collaborative Filtering can also be a user based k-NN collaborative filtering algorithm or an item based k-NN collaborative filtering algorithm. Each type has its merits and demerits. Aiming at this concern, an ensemble based k-NN collaborative filtering is proposed. This work fuses the merits of the user based k-NN algorithm and item-based algorithm. The experiment analysis on the MovieLens dataset gives a consistent model that is accurate and results in better personalized movie recommendations than other conventional models. The experimental results show that ensemble based k-NN algorithm clearly improves enhances the recommender system's performance, and give better recommendation quality.

Evaluation Of Recommendation System On A Movie Dataset

Recommender system is the system which, by using automated information filtering technology, recommends products or services to the customers who are likely to be interested in. Those systems are widely used in many different Web retailers such as Amazon.com, Netfix.com, and CDNow.com. Various recommender systems have been developed. Among them, Collaborative Filtering (CF) has been known as the most successful and commonly used approach. CF identifies customers whose tastes are similar to those of a given customer, and recommends items those customers have liked in the past. Numerous CF algorithms have been developed to increase the performance of recommender systems. However, the relative performances of CF algorithms are known to be domain and data dependent. It is very time-consuming and expensive to implement and launce a CF recommender system, and also the system unsuited for the given domain provides customers with poor quality recommendations that make them easily annoyed. Therefore, predicting in advance whether the performance of CF recommender system is acceptable or not is practically important and needed. In this study, we propose a decision making guideline which helps decide whether CF is adoptable for a given application with certain transaction data characteristics. Several previous studies reported that sparsity, gray sheep, cold-start, coverage, and serendipity could affect the performance of CF, but the theoretical and empirical justification of such factors is lacking. Recently there are many studies paying attention to Social Network Analysis (SNA) as a method to analyze social relationships among people. SNA is a method to measure and visualize the linkage structure and status focusing on interaction among objects within communication group. CF analyzes the similarity among previous ratings or purchases of each customer, finds the relationships among the customers who have similarities, and then uses the relationships for recommendations. Thus CF can be modeled as a social network in which customers are nodes and purchase relationships between customers are links. Under the assumption that SNA could facilitate an exploration of the topological properties of the network structure that are implicit in transaction data for CF recommendations, we focus on density, clustering coefficient, and centralization which are ones of the most commonly used measures to capture topological properties of the social network structure. While network density, expressed as a proportion of the maximum possible number of links, captures the density of the whole network, the clustering coefficient captures the degree to which the overall network contains localized pockets of dense connectivity. Centralization reflects the extent to which connections are concentrated in a small number of nodes rather than distributed equally among all nodes. We explore how these SNA measures affect the performance of CF performance and how they interact to each other. Our experiments used sales transaction data from H department store, one of the well?known department stores in Korea. Total 396 data set were sampled to construct various types of social networks. The dependant variable measuring process consists of three steps; analysis of customer similarities, construction of a social network, and analysis of social network patterns. We used UCINET 6.0 for SNA. The experiments conducted the 3-way ANOVA which employs three SNA measures as dependant variables, and the recommendation accuracy measured by F1-measure as an independent variable. The experiments report that 1) each of three SNA measures affects the recommendation accuracy, 2) the density's effect to the performance overrides those of clustering coefficient and centralization (i.e., CF adoption is not a good decision if the density is low), and 3) however though the density is low, the performance of CF is comparatively good when the clustering coefficient is low. We expect that these experiment results help firms decide whether CF recommender system is adoptable for their business domain with certain transaction data characteristics.

Collaborative filtering method is based on users with similar interests to provide recommendations. At present most collaborative filtering algorithms consider the similarity among users or the similarity among items without the consideration of the similarity between users and items. In this paper, biclustering algorithms based on Bimax and Order-Preserving Submatrix are introduced to measure the similarity from both the users and the items, compared with the traditional collaborative filtering algorithm proposed by Paul Resnick (1994), the Root mean square error (RMSE) and the Mean absolute error (MAE) of the former are lower than the latter's. The experiments implemented on the datasets Movielens (100k) and Movielens (1M) proves that the collaborative filtering algorithm based on OPSM has a comparative advantage in the recommendation system. Meanwhile the larger the dataset is, the more accurate the prediction will be.

A key challenge of the collaborative filtering (CF) information filtering is how to obtain the reliable and accurate results with the help of peers' recommendation. Since the similarities from small-degree users to large-degree users would be larger than the ones in opposite direction, the large-degree users' selections are recommended extensively by the traditional second-order CF algorithms. By considering the users' similarity direction and the second-order correlations to depress the influence of mainstream preferences, we present the directed second-order CF (HDCF) algorithm specifically to address the challenge of accuracy and diversity of the CF algorithm. The numerical results for two benchmark data sets, MovieLens and Netflix, show that the accuracy of the new algorithm outperforms the state-of-the-art CF algorithms. Comparing with the CF algorithm based on random walks proposed by Liu et al. (Int. J. Mod. Phys. C, 20 (2009) 285) the average ranking score could reach 0.0767 and 0.0402, which is enhanced by 27.3% and 19.1% for MovieLens and Netflix, respectively. In addition, the diversity, precision and recall are also enhanced greatly. Without relying on any context-specific information, tuning the similarity direction of CF algorithms could obtain accurate and diverse recommendations. This work suggests that the user similarity direction is an important factor to improve the personalized recommendation performance.

Collaborative Filtering (CF) Recommendation System is a prominent technology which is widely online. Large variety of available CF algorithms and the multitude of their possible parameters have a huge impact on quality of the outcome on ECommerce. Unfortunately, the literature on CF recommender system evaluation presents different evaluation metrics at different situation and could not provide any suggestion about the best. At the same time, it is a fact to accept that the accuracy measure should be different for each CF algorithm and depends upon the classification accuracy of that particular algorithm. As an initiative to address this problem in the present research paper, predictive accuracy metrics, classification accuracy metrics and rank accuracy metrics are considered as the classification accuracy metrics to know the overall competence for significant features of the chosen CF algorithms. At this juncture, normalization, a distinctive evaluation methodology, has been adopted to accomplish unique evaluation results of recommender systems. In this research paper, different accuracy metrics assessment would be brought into a common scale by taking into consideration of normalization process to evaluate metrics of the CF algorithms. A comprehensive comparative analysis is carried out and tabulated.

Collaborative filtering is the most widely used and successful technology for building recommender systems. However it faces challenges of scalability and recommendation accuracy. Collaborative filtering can be divided into memory based and model based. The former is more accurate while the latter performs better in scalability. This paper proposes a hybrid user model. The recommender system based on this model not only holds the advantage of recommendation accuracy in memory-based method, but also has the scalability as good as model-based method. The user model is constructed based on item combination feature and demographic information, and it focuses on searching for set of neighboring users shared with same interest, which helps to improve system scalability. To enhance recommendation accuracy, each feature in user model is given a different weight when computing the similarity between users. Genetic algorithm is adopted to learn the weight values of features. A comparison experiment was performed on MovieLens data set, and the result shows methodology proposed in this paper performs better than conventional collaborative filtering in recommendation accuracy and scalability.

In view of the sparsity of user-resource interaction data, information asymmetry caused by cold start, and weak personalized resource allocation in the current integration of enterprises with vocational schools and universities, this article adopts the Collaborative Filtering (CF) algorithm to mine the user’s behavior patterns and preferences, establish a more intelligent resource recommendation model, and enhance the relevance and accuracy of resource recommendation. The intelligent resource recommendation system plays a key role in the construction of smart cities, fully optimizing the interaction between educational institutions and enterprises, and providing strong support for promoting the development of smart cities. First, an embedded feature expression for users and resources is established, and the deep embedding learning method is used to extract the association between high-dimensional and nonlinear features. Secondly, based on the traditional CF algorithm, the neural network architecture is combined to achieve accurate matching between users and resources. Finally, through experiments in user cold start and resource cold start scenarios, the performance improvement of the recommendation system is verified and compared with the widely used Matrix Factorization (MF) and Neural Collaborative Filtering (NCF) for analysis. According to the experimental results, the average precision of the proposed method is 0.804, which is 7.34% and 5.51% higher than MF and NCF respectively. The conclusion shows that the CF algorithm helps to enhance the resource recommendation effect and provides a new perspective for enhancing service personalization.

Recently, collaborative filtering algorithm is widely used in recommendation systems. Similarity calculation is an important step of this algorithm. Some of the existing similarity computing methods can not accurately measure the similarity, and the accuracy needs to be improved. In this paper, a new similarity calculation method is proposed, which is called JacRA. In order to verify the effectiveness of our proposed method, we compare several methods based on MovieLens data sets. Experimental results show that our method outperforms the contrast methods in terms of accuracy.

Recommender systems have become indispensable tools in various domains, such as e-commerce, entertainment, and social media, for delivering personalized user experiences. Collaborative Filtering (CF) is an essential technique in RS that leverages user similarity patterns to suggest items which align with individual preferences. This study presents an experimental comparative analysis of collaborative filtering-based recommender system methods including memory-based methods (KNN variants), model-based approaches (SVD, SVD++, co-clustering), and techniques based on neural networks (NCF, DeepFM, LightGCN). We conduct a thorough evaluation of these methods on the MovieLens benchmark datasets (100K, 1M, 25M) utilizing various metrics, such as RMSE, MAE, FCP, NDCG@10, Precision@10, Recall@10, and F1@10 Score, aiming to identify the most effective approaches and understand the advantages and disadvantages of each approach. Additionally, we provide detailed insights into the working mechanisms of each model. Our comprehensive analysis reveals the strengths and limitations of each method, offering critical insights for practitioners in selecting the most suitable recommender system technique based on specific requirements and constraints. The findings indicate that, on large datasets, neural and graph-based models achieve measurable improvements in both rating accuracy and top-k ranking tasks, with ranking gains observed upto 15%. Nonetheless, more straightforward approaches (KNN, SVD) continue to hold their ground in smaller datasets or low-resource environments because of their straightforward implementation and clarity in interpretation. The results highlight the importance of achieving a balance between computational expense, scalability, and model intricacy when choosing collaborative filtering techniques for practical implementations of recommender systems. We offer practical insights to assist professionals in selecting models that are suited to particular application needs and data attributes. This research enhances the understanding of collaborative filtering techniques and offers valuable insights for improving the performance of RS across diverse domains.

Recommendation system has been applied in many fields, such as Human Computer Interaction, Information Retrieval, and so on. Essentially speaking, these are based on data mining. Among the many algorithms used in the recommendation system, collaborative filtering algorithm is one of the most mature and most widely used algorithm. With the coming of big data era, a variety of recommendation algorithm surge, and distributed recommendation algorithm has become a hot research topic. As a sub project of Hadoop , Mahout is also very obvious to support collaborative filtering algorithm. In order to deeply analyze the operation principle and the use effect of Collaborative Filtering Recommendation Algorithm in mahout, we designed a combination model composed of the recommender and the similarity measure. Using the custom data set, we write some Java classes to test collaborative filtering algorithm based on user and the collaborative filtering algorithm based on the item, the experimental results shows that our combination model get a better classification effect .

In online environments, a vast amount of data is explored daily on the internet, such as news, movies, audios, and books. The interest of the target user is the greatest demand for recommender systems, and getting suitable information is a challenge. To develop a recommender system, collaborative filtering (CF) approach considers users who have similar ratings. Therefore, can compute the similarity of users when there are enough rated by users to items. A significant challenge of the collaborative filtering approach is cold start problem, which is how to make a recommendation for users who have few ratings than others. This work proposes a collaborative filtering model based on applying fuzzy c-means clustering on user's truthfulness information. A new fuzzy user-based similarity measure formula is suggested which combines user's rating with fuzzy truthfulness information using a combination coefficient. The experimental results using Movie Lens data set have shown an improvement in recommendation under sparsity and cold start condition.

Personalized recommendation systems can help people find interesting things and are widely used in developing the Internet. Many recommendation systems employ collaborative filtering technology, which has proven one of the most successful techniques in recommender systems in recent years. Collaborative filtering is a method of making predictions about the interests of a user by collecting preferences or taste information from many users. However, this technique suffers poor quality when the number of missing preferences or taste information in the user database increases. To resolve the problems in collaborative filtering, traditional approach presents collaborative filtering using cluster-based data smoothing. However, this approach didn't use data smoothing in the entire the user database, and most of the clustering method is user clustering, in addition, they use clustering including missing value. Therefore, this paper presents a novel approach that incorporates hybrid-clustering technology after introducing a smooth-based method in the entire database. First, we introduce rating smoothing for the entire database based on collaborative-filtering algorithms that uses similarities among users are called item-based collaborative filtering to resolve the sparsity issue. The proposed approach utilizes clustering collaborative filtering that combines both user clustering and item clustering to produce the recommendations. Finally, we evaluate the experiment results in point of the precision.

Recommender system (RS) is a unique type of information clarification system that anticipates the user's evaluation of items from a large pool based on the expectations of a single stakeholder. The proposed system is highly useful for getting expected meaning suggestions and guidance for choosing the proper product using artificial intelligence and IoT (Internet of Things) such as chatbot. The current proposed technique makes it easier for stakeholders to make context-based decisions that are optimal rather than reactive, such as which product to buy, news classification based on high filtering views, highly recommended wanted music to choose, and desired product to choose. Recommendation systems are a critical tool for obtaining verified information and making accurate decisions. As a result, operational efficiency would skyrocket, and the risk to the company that uses a recommender system would plummet. This proposed solution can be used in a variety of applications such as commercial hotels OYO and other hotels, hospitals (GYAN), public administrative applications banks HDFC, and ICICI to address potential questions on the spot using intelligence computing as a recommendation system. The existing RS is considering a few factors such as buying records, classification or clustering items, and user's geographic location. Collaborative filtering algorithms (CFAs) are much more common approaches for cooperating to mesh the respective documents they retrieved from the historical data. CFAs are distinguished in plenty of features that are uncommon from other algorithms. In this existing system classification, precision and efficiency and error rate are statistical measurements that need to be enhanced according to the current need to fit for global requirements. The proposed work deals with enhancing accuracy levels of text reviews with the recommender system while interacting by the numerous users for their domains. The authors implemented the recommender system using a user-based CF method and presented the significance of collaborative filtering on the movie domain with a recommender system. This whole experiment has been implanted using the RapidMiner Java-based tool. Results have been compared with existing algorithms to differentiate the efficiency of the current proposed approach.

Recommendation systems have been investigated and implemented in many aspects. Particularly, in case of collaborative filtering system, more important issue is how to manipulate the personalized recommendation results for better user understandability and satisfaction. Collaborative filtering system predicts items of interest for users based on predictive relationship discovered between the item and others. In this paper, the categorization for grouping associative items mining, for the purpose of improving accuracy and performance in the item-based collaborative filtering, is proposed. It is possible that, if the associative item is required to be simultaneously regrouped in all other groups in which they occur, the proposed method regrouped the associative items into the relevant group. In addition, the proposed method can result in improved predictive performance under the sparse data and cold-start circumstance that starts from small items in the collaborative filtering. And this method can increase the prediction accuracy and the scalability because of removing the noise generated by ratings on items of dissimilar content or interest. The approach is empirically evaluated for comparison with k-means, average link, and robust, using the MovieLens dataset. This method was found to significantly outperform the previous method.