Research on recurrent neural network recommendation algorithm based on time series

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 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.

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.

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.

Recommendation algorithms in social networks have attracted much attention in recent years. Collaborative filtering recommendation algorithm is one of the most commonly used recommendation algorithms. Traditional user-based collaborative filtering recommendation algorithm recommends based on the user-item rating matrix, but the large amounts of data may cause low efficiency. In this paper, we propose an improved collaborative filtering recommendation algorithm based on community detection. Firstly, the user-item rating matrix is mapped into the user similarity network. Furthermore, a novel discrete particle swarm optimization algorithm is applied to find communities in the user similarity network, and finally Top-N items are recommend to the recommended user according to the communities. The experiments on a real dataset validate the effectiveness of the proposed algorithm for improving the precision, coverage and efficiency of recommendation.

Personalized courses recommendation technology is one of the hotspots in online education field. A good recommendation algorithm can stimulate learners' enthusiasm and give full play to different learners' learning personality. At present, the popular collaborative filtering algorithm ignores the semantic relationship between recommendation items, resulting in unsatisfactory recommendation results. In this paper, an algorithm combining knowledge graph and collaborative filtering is proposed. Firstly, the knowledge graph representation learning method is used to embed the semantic information of the items into a low-dimensional semantic space; then, the semantic similarity between the recommended items is calculated, and then, this item semantic information is fused into the collaborative filtering recommendation algorithm. This algorithm increases the performance of recommendation at the semantic level. The results show that the proposed algorithm can effectively recommend courses for learners and has higher values on precision, recall, and F1 than the traditional recommendation algorithm.

Aiming at the fact that the traditional collaborative filtering recommendation algorithm is insufficient in the number of users’ implicit feedback, and the user interest preference model is too rough, a collaborative filtering recommendation algorithm with the importance of tags is proposed. Type and frequency of use of the label reflect user preferences and preferences, in order to establish a new user preferences model for better mining and use implicit user feedback data will affect the degree of the label on the user to quantify, to establish a new method for similarity computation. The experimental results show that the proposed algorithm has obvious advantages, improves the recommendation accuracy and alleviates the cold start problem.

Aiming at the problem that the traditional Collaborative Filtering algorithm has low recommendation accuracy, in the paper, we propose a collaborative filtering recommendation algorithm based on the global trust degree integrating the direct trust information in the social networks.We first transform the local trust relationships to the global trust relationship by the rules in the trust network, and get the trust rank of all users in the trust networks; Then we use the global trust value to instead of the similarity information value as the weights of a predicted formula in the traditional collaborative recommendation algorithm, and integrate the weights to the matrix factorization-based recommendation model.

With the continuous development of mobile communications and Internet technologies, the marketing model of the communications industry has shifted from calling-based to social APP-based personalized recommendations. In order to improve the accuracy of recommendation, this paper proposes a recommendation algorithm for social analysis. Empirical data was firstly used to construct a “user-APP” two-layer communication network model, and then the traditional collaborative filtering recommendation technology was integrated to reconstruct similar users and similar APP network model. The bipartite graph weight distribution method was taken to recommend targets in the obtained network model. The experimental simulation shows that, in view of the characteristics of the two-layer communication network, compared with the traditional recommendation algorithm, the algorithm effectively improves the accuracy of the score prediction.

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.

In the recommendation system, compared with the explicit feedback, implicit feedback has the characteristics of large quantity, easier tracking and easier access. Even in many practical application scenarios of the recommendation system, there is only implicit feedback without explicit feedback Based on implicit feedback to recommend there has been a problem, that is usually implicit feedback provides only reflect the noise signal of user preferences, because although the observed interactions at least reflect the user’s interest in the item, but not observed the interaction may be missing data, and is not necessarily negative samples, so it’s natural lack of negative feedback In this work, this paper improves the neural colla-borative filtering algorithm (NCF) by extracting the popularity characteristics as the basis for extracting negative samples from implicit feedback data. To a certain extent, it solves the problem that negative sampling introduces a lot of noise in previous work. At the same time, we found that the gradient vanishing in the training process when using the traditional loss function Binary Cross Entropy (BCE). In order to solve this problem, a new loss function, BCE-Max, was proposed in this paper. Based on the above improvements, we proposed a neural collaborative filtering recommendation algorithm (PNCF) based on popularity characteristics. By comparing the performance of PNCF, NCF, traditional collaborative filtering and some matrix factorization recommendation algorithms in the evaluation indexes such as HR@10, NDCG@10 and avg_popularity@10, we find that PNCF has certain advantages over these recommendation algorithms. Meanwhile, We found that compared with NCF, the experimental results of PNCF improved by about 1.2% and 2% onHR@10 and NDCG@10 respectively, and even improved by about 2% on HR@1 and NDCG@I.

Personalized recommendation of film and television culture is an important content to meet people’s daily cultural needs and social information. Promoting the personalized recommendation of film and television culture is conducive to promoting the more efficient use of network resources. However, in recent years, the film and television culture industry has developed rapidly, and the production of film and television culture has also increased year by year. How to quickly and accurately find the user’s favorite film and television culture in the massive film and television cultural data has become an urgent problem to be solved. Aiming at the shortcomings of the film and television culture recommendation system, this paper proposes a new personalized recommendation algorithm for film and television culture based on an intelligent classification algorithm. Based on the preliminary screening results of the traditional collaborative filtering recommendation algorithm, the user data and video data are used as input and the video score as output, which is further filtered by a convolutional neural network. Finally, selecting the film and television culture recommendation set that is most suitable for the current user can also make up for the cold start problem of collaborative filtering at the beginning of the system operation. The simulation experiment is carried out. The experimental results show that the personalized recommendation algorithm based on an intelligent classification algorithm improves the scoring accuracy by 0.15, which indicates that the designed film and television culture recommendation system has a good application effect.

In E-commerce recommendation system,Information overload on Internet has brought a tough problem,which is how to precisely position users' interest and provide users with accurate product recommendation.To solve this problem,in this paper,a product characteristic extraction algorithm was developed and a user preference model was constructed by deeply mining large-scale of user reviews in E-commerce community,to improve accuracy of traditional collaborative filtering recommendation algorithm with coordination of historic user rating information;moreover,data sparsity problem was alleviated with similarity propagation technique.Experiment results show that,in condition of sparse data,algorithm in this paper can still fit product preference of users very well,and has significantly improvement in accuracy compared with traditional collaborative filtering algorithm.

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.

(Purpose/Significance). This paper aims at the problems of inaccurate recommendation effect caused by data sparseness and cold start in the traditional collaborative filtering-based book personalized recommendation algorithm. So this paper proposes a collaborative filtering recommendation algorithm which improves the similarity solution method and the filling method of missing data. (Method/Process). By considering the influence of the user's common rating book collection on the similarity calculation, the average rating value of all books is used as the threshold, and the user's common rating weight is introduced into the user's similarity calculation. As for data filling, according to the user's average rating, the basic attributes such as the age and gender of users are coded, and then Euclidean distance is initially calculated, making hierarchical clustering on users. What's more, Shope-one algorithm is used to calculate the filling value of the former m similar users，and add the weight value of the degree simultaneously to get the final filling value, so as to improve the data filling method. (Result/Conclusion). Experiments were carried out with the data set of Book-Crossing Data set through Python. The experimental results show that the improved collaborative filtering algorithm has a significantly improvement in the accuracy and quality of book recommendation.