Factorizing Historical User Actions for Next-Day Purchase Prediction

It is common practice for many large e-commerce operators to analyze daily logged transaction data to predict customer purchase behavior, which may potentially lead to more effective recommendations and increased sales. Traditional recommendation techniques based on collaborative filtering, although having gained success in video and music recommendation, are not sufficient to fully leverage the diverse information contained in the implicit user behavior on e-commerce platforms. In this article, we analyze user action records in the Alibaba Mobile Recommendation dataset from the Alibaba Tianchi Data Lab, as well as the Retailrocket recommender system dataset from the Retail Rocket website. To estimate the probability that a user will purchase a certain item tomorrow, we propose a new model called Time-decayed Multifaceted Factorizing Personalized Markov Chains (Time-decayed Multifaceted-FPMC), taking into account multiple types of user historical actions not only limited to past purchases but also including various behaviors such as clicks, collects and add-to-carts. Our model also considers the time-decay effect of the influence of past actions. To learn the parameters in the proposed model, we further propose a unified framework named Bayesian Sparse Factorization Machines. It generalizes the theory of traditional Factorization Machines to a more flexible learning structure and trains the Time-decayed Multifaceted-FPMC with the Markov Chain Monte Carlo method. Extensive evaluations based on multiple real-world datasets demonstrate that our proposed approaches significantly outperform various existing purchase recommendation algorithms.

An Improved Recommender System Solution to Mitigate the Over-Specialization Problem Using Genetic Algorithms

Nowadays, recommendation systems offer a method of facilitating the user’s desire. It is useful for recommending items from a variety of areas such as in the e-commerce, medical, education, tourism, and industry domains. The e-commerce area represents the most active research we found, which assists users in locating the things they want. A recommender system can also provide users with helpful knowledge about things that could be of interest. Sometimes, the user gets bored with recommendations which are similar to their profiles, which leads to the over-specialization problem. Over-specialization is caused by limited content data, under which content-based recommendation algorithms suggest goods directly related to the customer profile rather than new things. In this study, we are particularly interested in recommending surprising, new, and unexpected items that may likely be enjoyed by users and will mitigate this limited content. In order to recommend novel and serendipitous items along with familiar items, we need to introduce additional hacks and note of randomness, which can be achieved using genetic algorithms that brings diversity to recommendations being made. This paper describes a Revolutionary Recommender System using a Genetic Algorithm called RRSGA which improves the fitness functions for recommending optimal results. The proposed approach employs a genetic algorithm to address the over-specialization issue of content-based filtering. The proposed method aims to incorporate genetic algorithms that bring variety to recommendations and efficiently adjust and suggest unpredictable and innovative things to the user. Experiments objectively demonstrate that our technology can recommend additional products that every consumer is likely to appreciate. The results of RRSGA have been compared against recommendation results from the content-based filtering approach. The results indicate the effectiveness of RRSGA and its capacity to make more accurate predictions than alternative approaches.

Intelligent Recommendation Algorithm of Multimedia English Distance Education Resources Based on User Model

Based on the understanding and comparison of various main recommendation algorithms, this paper focuses on the collaborative filtering algorithm and proposes a collaborative filtering recommendation algorithm with improved user model. Firstly, the algorithm considers the score difference caused by different user scoring habits when expressing preferences and adopts the decoupling normalization method to normalize the user scoring data; secondly, considering the forgetting shift of user interest with time, the forgetting function is used to simulate the forgetting law of score, and the weight of time forgetting is introduced into user score to improve the accuracy of recommendation; finally, the similarity calculation is improved when calculating the nearest neighbor set. Based on the Pearson similarity calculation, the effective weight factor is introduced to obtain a more accurate and reliable nearest neighbor set. The algorithm establishes an offline user model, which makes the algorithm have better recommendation efficiency. Two groups of experiments were designed based on the mean absolute error (MAE). One group of experiments tested the parameters in the algorithm, and the other group of experiments compared the proposed algorithm with other algorithms. The experimental results show that the proposed method has better performance in recommendation accuracy and recommendation efficiency.

Deep Learning for Recommender Systems: A Netflix Case Study

Deep learning has profoundly impacted many areas of machine learning. However, it took a while for its impact to be felt in the field of recommender systems. In this article, we outline some of the challenges encountered and lessons learned in using deep learning for recommender systems at Netflix. We first provide an overview of the various recommendation tasks on the Netflix service. We found that different model architectures excel at different tasks. Even though many deep-learning models can be understood as extensions of existing (simple) recommendation algorithms, we initially did not observe significant improvements in performance over well-tuned non-deep-learning approaches. Only when we added numerous features of heterogeneous types to the input data, deep-learning models did start to shine in our setting. We also observed that deep-learning methods can exacerbate the problem of offline–online metric (mis-)alignment. After addressing these challenges, deep learning has ultimately resulted in large improvements to our recommendations as measured by both offline and online metrics. On the practical side, integrating deep-learning toolboxes in our system has made it faster and easier to implement and experiment with both deep-learning and non-deep-learning approaches for various recommendation tasks. We conclude this article by summarizing our take-aways that may generalize to other applications beyond Netflix.

Personalized Product Recommendation and User Satisfaction

A recommendation system is a significant part of artificial intelligence (AI) to help users' access information at any time and from anywhere. Online product recommender systems are widely used to recommend products based on consumers' preferences. The traditional recommendation algorithms of recommendation engines do not meet the needs of users in the AI environment when exposed to large amounts of data resulting in a low recommendation efficiency. To address this, a personalized recommendation system was introduced. These personalized recommendation systems (PRS) are an important component for ecommerce players in the Indian e-commerce aspects. Since personalized recommendations are becoming increasingly popular, this study examines information processing theory with respect to personalized recommendations and their impact on user satisfaction. Further, relationships between the variables were examined by conducting regression analysis and found a positive correlation exists between personalized product recommendation and user satisfaction.

Hybrid Recommendation Scheme Based on Deep Learning

Big data has been developed for nearly a decade, and the information data on the network is exploding. Facing the complex and massive data, it is difficult for people to get the demanded information quickly, and the recommendation algorithm with its characteristics becomes one of the important methods to solve the massive data overload problem at this stage. In particular, the rise of the e-commerce industry has promoted the development of recommendation algorithms. Traditional, single recommendation algorithms often have problems such as cold start, data sparsity, and long-tail items. The hybrid recommendation algorithms at this stage can effectively avoid some of the drawbacks caused by a single algorithm. To address the current problems, this paper makes up for the shortcomings of a single collaborative model by proposing a hybrid recommendation algorithm based on deep learning IA-CN. The algorithm first uses an integrated strategy to fuse user-based and item-based collaborative filtering algorithms to generalize and classify the output results. Then deeper and more abstract nonlinear interactions between users and items are captured by improved deep learning techniques. Finally, we designed experiments to validate the algorithm. The experiments are compared with the benchmark algorithm on (Amazon item rating dataset), and the results show that the IA-CN algorithm proposed in this paper has better performance in rating prediction on the test dataset.

Algorithmic Opportunity Structures and the Dynamics of Online Activism: Far-Right Mobilization on Facebook

This paper introduces the concept of algorithmic opportunity structures to explore how the efficacy of online activism is contingent on the interaction between algorithms, activists, and audiences. In particular, I examine how far-right actors have gamed ranking and recommendation algorithms by producing content designed to generate high engagement rates. This tactic attracts algorithmic amplification, increasing their visibility and reach on social media. I consider the case of Britain First, a far-right, anti-Muslim movement that used Facebook to rapidly build the largest audience of any political organization in the United Kingdom. I use digital trace data, time series analysis, and topic modeling to study Britain First’s activity, recruitment, and support on Facebook. I identify dynamic equilibria indicative of algorithmically-mediated feedback loops, highlighting how variation in these processes is largely a function of user engagement. The content of the group’s posts and exogenous events, including elections and terrorist attacks, are also associated with short-term fluctuations in online mobilization. The results suggest that Britain First’s success is attributable to its exploitation of Facebook’s algorithms, demonstrating how technological assemblages designed and controlled by corporations can structure political competition and moderate opportunities for activism.

Link recommendation algorithms and dynamics of polarization in online social networks

The level of antagonism between political groups has risen in the past years. Supporters of a given party increasingly dislike members of the opposing group and avoid intergroup interactions, leading to homophilic social networks. While new connections offline are driven largely by human decisions, new connections on online social platforms are intermediated by link recommendation algorithms, e.g., “People you may know” or “Whom to follow” suggestions. The long-term impacts of link recommendation in polarization are unclear, particularly as exposure to opposing viewpoints has a dual effect: Connections with out-group members can lead to opinion convergence and prevent group polarization or further separate opinions. Here, we provide a complex adaptive–systems perspective on the effects of link recommendation algorithms. While several models justify polarization through rewiring based on opinion similarity, here we explain it through rewiring grounded in structural similarity—defined as similarity based on network properties. We observe that preferentially establishing links with structurally similar nodes (i.e., sharing many neighbors) results in network topologies that are amenable to opinion polarization. Hence, polarization occurs not because of a desire to shield oneself from disagreeable attitudes but, instead, due to the creation of inadvertent echo chambers. When networks are composed of nodes that react differently to out-group contacts, either converging or polarizing, we find that connecting structurally dissimilar nodes moderates opinions. Overall, our study sheds light on the impacts of social-network algorithms and unveils avenues to steer dynamics of radicalization and polarization in online social networks.

Micromedia News Dissemination Impact Assessment Integrated with Personalized Recommendation Algorithm

The development of the Internet has completely changed the way of recommending and disseminating news content. Traditional media forms of news dissemination effectiveness evaluation methods are no longer fully suitable for the evolving needs of new media news dissemination. Therefore, it is necessary to innovate methods for evaluating the effects of new media news dissemination. This article mainly combines personalized recommendation algorithms to evaluate the effectiveness of news dissemination. Currently, popular personalized recommendation algorithms include content-based recommendation algorithms, collaborative filtering recommendation algorithms, knowledge-based recommendation algorithms, and associated recommendation algorithms. These recommendation algorithms are effective. This promotes the dissemination of news, which also recommends news content that is more relevant to user preferences for most users. In addition, the quality of news content is further evaluated through the news rating system, thereby effectively improving the quality of news content.

NCGAN:A neural adversarial collaborative filtering for recommender system

The major challenge of recommendation system (RS) based on implict feedback is to accurately model users’ preferences from their historical feedback. Nowadays, researchers has tried to apply adversarial technique in RS, which had presented successful results in various domains. To a certain extent, the use of adversarial technique improves the modeling of users’ preferences. Nonetheless, there are still many problems to be solved, such as insufficient representation and low-level interaction. In this paper, we propose a recommendation algorithm NCGAN which combines neural collaborative filtering and generative adversarial network (GAN). We use the neural networks to extract users’ non-linear characteristics. At the same time, we integrate the GAN framework to guide the recommendation model training. Among them, the generator aims to make user recommendations and the discriminator is equivalent to a measurement tool which could measure the distance between the generated distribution and users’ ground distribution. Through comparison with other existing recommendation algorithms, our algorithm show better experimental performance in all indicators.