Research on Personalized Book Recommendation Based on Improved Similarity Calculation and Data Filling Collaborative Filtering Algorithm.

The traditional collaborative filtering recommendation algorithm can be divided into the user-based and the item-based two methods, which only uses the information in the rating matrix. Because of the limitation of the information capacity they used, it is difficult to further improve the accuracy of the recommendation, and cold start problem also affects the normal operation of the recommendation system. This paper presented a collaborative filtering recommendation algorithm (UISA) fusing user-based, item-based and social networks data. The algorithm uses the data of the neighbor relations in social networks, calculating the users' friends not reflected in the rating matrix. At the same time, we can calculate the similarity between items by using the data of item text in social networks, mining similar items not reflected in the rating matrix. In this way, it can fundamentally expand available information capacity of the traditional filtering collaboration recommendation algorithms, improve the recommendation accuracy, alleviate cold start problem. Experimental results based on KDD CUP 2012 real data show that compared with the traditional collaborative filtering system, this system has obvious advantages in the recommendation accuracy and ease of cold start.

At present, the traditional collaborative filtering (CF) recommendation algorithm generally has the problems of data sparsity and low accuracy. In order to solving these problems, this paper proposes a multi-feature fusion collaborative filtering recommendation algorithm. Firstly, considering that different users have different preferences for different item attributes, this paper used item attribute scores and user preference information for matrix filling to alleviate the problem of data sparsity. Secondly, considering the influence of multiple features of user activity , the count of common item ratings, and item popularity on the calculation of user similarity, and used these features to improve the calculation of similarity. Finally, the matrix after data filling and the improved similarity calculation formula were used to make personalized recommendations for users. Experimental results prove that compared with traditional algorithms and other improved algorithms, the improved algorithm in this paper alleviates the problem of data sparsity to a certain extent, and at the same time has a certain improvement in accuracy

Personalized recommendation system is an important means for people to get interested information and product quickly. This traditional user-based collaborative filtering algorithm cost too much computation on similarity calculation. In order to solve this problem, a new collaborative filtering recommendation algorithm based on K-Means clustering of user’s attributes is proposed. In this algorithm, the longitude and latitude of users’ are first clustered, and then the similarity of users’ are calculated within each cluster. Finally, parallelization of this proposed algorithm on Spark is implemented. Experiments show that the user attributes-based collaborative filtering has satisfied performance.

The structural similarity and numerical similarity in the similarity calculation of the traditional user-based collaborative filtering recommendation algorithm have their own shortcomings. Structural similarity only uses the structural information of user ratings without considering the numerical information for user similarity, and numerical similarity only uses the ratings to calculate the similarity without considering the structural information, which makes the similarity calculation lacks accuracy. Aiming at this problem, a method that considers both the structural similarity of numerical information and the numerical similarity of structural information is proposed. When improving the numerical similarity, the influence of item quality and item popularity on the numerical similarity is considered. Simultaneously, the commonly used numerical similarity calculation uses the improved structural similarity to optimize. The five-fold cross-validation method is tested on the Movielens100K public data set. Compared with the traditional user-based collaborative filtering recommendation algorithm, the experiment proves that the proposed method effectively improves the recommendation performance.

In the era of the Internet, all people's behaviors on the Internet will be stored in the server in the form of data, which leads to the image level growth of data today. In the context of big data, how to effectively analyze various existing data to obtain the necessary information is an urgent challenge that various industries need to overcome. Recommendation algorithms are one of them, mainly using existing data to recommend information of interest to users. In traditional recommendation algorithms, collaborative filtering recommendation algorithms encounter difficulties such as cold start and data sparsity. In order to better explore data features, deep learning algorithms have begun to be applied. Recurrent neural networks can not only learn input data but also perform self-learning, which can better extract features between data and improve the accuracy of recommendations. However, the information that users are interested in is greatly influenced by time, in order to improve the accuracy of recommendations. This study investigates the recursive neural network recommendation algorithm with added time series, and experiments have shown that this recommendation algorithm can indeed improve the accuracy of recommendations more accurately.

Data sparsity remains to be a critical concern for recommendation systems since it results in low accuracy and poor recommendation quality. To address this problem, collaborative filtering techniques based on user similarity have been applied but existing implementations have not been shown to sufficiently address the problem of data sparsity. Thus, this paper presents an enhanced memory-based collaborative filtering algorithm utilizing a new similarity measure that identifies co-rated items and computes user similarity to overcome the data sparsity problem and improve the recommendation quality which can be adopted for various applications. Results of the study show that the use of the new similarity measure has improved the determination of user similarity than when using the traditional Cosine, Euclidean Distance, and Pearson Correlation similarity metrics.

CF (Collaborative filtering) algorithm has the widest and most successful applications in personalized recommendations. However, due to its over-reliance on the users' historical data, it is difficult to avoid data sparseness and cold start issues. The data sparseness and cold start may cause poor recommendation accuracy of the collaborative filtering algorithm. A hybrid optimal collaborative filtering algorithm based on users' characteristics and trust is proposed in this paper. In the process of users' similarity calculation, the age and gender of users' characteristics are introduced to make the determination of nearest neighbor more accurate. Besides, in order to improve the recommendation accuracy of the traditional CF recommendation algorithm, the trust relationship is introduced into the prediction score by measuring the users' trust, and this improvement will be used in the recommendation of new items in order to improve the recommendation accuracy of the traditional CF recommendation algorithm. The experimental results of Movie lens data set show that the improved recommendation accuracy of the recommendation system can be achieved by the proposed algorithm. Also, the problems of cold start and sparse data can be solved effectively.

In view of a series of problems in college book recommendation, such as cold start of users, high proportion of popular recommendations and low recommendation accuracy, this paper improves these problems based on the problems of the existing collaborative filtering algorithm and combined with the characteristics of college book borrowing. An improved University book recommendation algorithm is proposed, in which the time attenuation factor is added when generating the user evaluation matrix, and the influence of gender and professional factors on the user feature similarity is considered. The algorithm solves the problem of insufficient score of collaborative filtering algorithm. Experiments show that this algorithm is better than the traditional collaborative filtering recommendation algorithm and can meet the actual needs.

Collaborative filtering recommendation is a popular recommendation algorithm in electronic commerce, but the disadvantage of cold start still exists in the reason of new coming users and items. CBR (case-based reasoning) is used to get source case in history according to the notation of target case, and the source case plays a guiding role in solving the problem of the target case. It is a useful algorithm to evaluate the solution of target case, and explain the abnormal phenomenon of target case. In this paper we applied case-based reason with forgetting mechanism to solve the cold start problem in collaborative filtering, to deduce the score of items which is not scored by user, and then to recommend items with TOP-N collaborative filtering. Experimental results show that the proposed collaborative filtering combining case-based reasoning could significantly ease cold start problem.

Currently collaborative filtering is widely used in e-commerce, digital libraries and other areas of personalized recommendation service system. Nearest-neighbor algorithm is the earliest proposed and the main collaborative filtering recommendation algorithm, but the data sparsity and cold-start problems seriously affect the recommendation quality. To solve these problems, A collaborative filtering recommendation algorithm based on users' social relationships is proposed. 0n the basis of traditional filtering recommendation technology, it combines with the interested objects of user's social relationship and takes the advantage of the tags to projects marked by users and their interested objects to improve the methods of recommendation. The experimental results of MAE ((Mean Absolute Error)) verify that this method can get better quality of recommendation.

Everyday there are masses of information generated and the existence of a large amount of information makes it hardly to mining the wanted information. Personalized recommendation is the process to alleviative the problem. Collaborative filtering is one of the most popular technologies in the personal recommendation system. As the user rating matrix becoming extremely sparsity, traditional collaborative filtering recommendation algorithm calculates similarity between items using the rating data, and it does not consider the semantic relationship between different items, thus recommendation quality is very poor. To solve this problem, the paper combines the item semantic similarity and the item rating similarity, which takes into account the influence of item semantic and user rating to enhance the item-based collaborative filtering. The personalized collaborative filtering recommendation algorithm combining the item semantic similarity and item rating similarity can mitigate the sparsity problem in the electronic commerce recommender systems.

Chinese traditional culture contains the wisdom and experience of the concept of governing the country, and contains the moral principles taught by the ancients. Carrying forward and developing the excellent traditional Chinese culture is of great significance for enhancing cultural self-confidence. The purpose of this paper is to study digital cultural communication based on recommendation algorithms. Combined with the particularity of the existence of digital culture, the recommendation technology is studied, aiming at the problems existing in collaborative filtering recommendation technology, an improvement method is proposed, and a recommendation algorithm for digital cultural resources is proposed. Combined with the digital cultural resource recommendation algorithm, a digital cultural resource recommendation engine is designed and implemented. Through the realization of the algorithm, using the data in the “Digital Cultural Resource Database” of the scientific research achievement of the Key Laboratory of Cultural Informatization, the digital cultural resource recommendation algorithm is compared with the traditional collaborative filtering recommendation algorithm, and the MAE mean absolute deviation is used as the main According to the experimental data, the MAE values of the improved collaborative filtering digital culture recommendation algorithm are all lower than 0.15 points, and the conclusion is drawn that the improved recommendation algorithm has higher recommendation quality.

This paper proposes a collaborative filtering recommendation algorithm based on user characteristics and time weight which focuses on the data sparseness and cold start problems of collaborative filtering algorithms. First, digitize user's characteristics in the dataset and calculate the similarity degree of the user's feature, then weight the similarity calculation formula with the integration time function to obtain the comprehensive similarity so that a more accurate prediction score is obtained. The comparison experiments showed that the algorithm can reduce the sparseness of the data set effectively when the data is extremely sparse, and to some extent, it alleviates the cold start problem and improves the prediction accuracy of the recommendation algorithm.

Traditional collaborative filtering recommendation algorithm has some problems, such as sparse data and cold start, and the purchase of insurance products is easily affected by the characteristics of the insured. Therefore, a hybrid recommendation algorithm based on time weighted optimization is proposed, which combines knowledge graph and collaborative filtering recommendation. Knowledge graph extracts the attributes of users and objects as features, constructs triples for training, and shares potential features by cross compression units, which can fully excavate the potential relationship between different information, and can also extend the user preferences by using multiple relationships to ensure the diversity of recommendations; the timeliness of recommendation is guaranteed by time weighting, and the timeliness of recommendation is further considered The influence of age on the purchase preference of the insured better adapts to the characteristics of insurance products. Through the empirical analysis on the insurance product data set, the experimental data show that the algorithm is better in each evaluation index compared with the existing algorithm.

In recent years, application of recommendation algorithm in real life such as Amazon, Taobao is getting universal, but it is not perfect yet. A few problems need to be solved such as sparse data and low recommended accuracy. Collaborative filtering is a mature algorithm in the recommended systems, but there are still some problems. In this paper, a novel collaborative filtering recommendation algorithm based on user correlation and evolutionary clustering is presented. Firstly, score matrix is pre-processed with normalization and dimension reduction, to obtain denser score data. Based on these processed data, clustering principle is generated and dynamic evolutionary clustering is implemented. Secondly, the search for the nearest neighbors with highest similar interest is considered. A measurement about the relationship between users is proposed, called user correlation, which applies the satisfaction of users and the potential information. In each user group, user correlation is applied to choose the nearest neighbors to predict ratings. The proposed method is evaluated using the Movielens dataset. Diversity experimental results demonstrate that the proposed method has outstanding performance in predicted accuracy and recommended precision.