Personalized Recommendation System Research Articles

Application of AI technology in personalized recommendation system for financial services

Abstract How to quickly and accurately retrieve the products that users are interested in from a huge amount of financial products has become a business pain point that financial institutions must solve. In this study, an interpretable EPRSA model for personalized financial service recommendations based on self-attention mechanisms is proposed by combining an LSTM model and an LDA topic model with AI technology support. A customized recommendation system for financial services is constructed by introducing the Nginx server into the Flask framework, and the design of the database and personalized recommendation module is interpreted. For the financial service personalized recommendation system proposed in this paper, its recommendation performance and system performance are tested, and the stock financial products are selected as the recommendation objects to explore its recommendation effect. It is found that the DNCG index of personalized recommendation of financial products of the EPRSA model is improved by 40.18%, the average response time of the system when the number of concurrent users is 1,000 is 1.96 s. The average quality of the personalized recommendation of the collection of stocks reaches 0.153. The customized recommendation of financial services using AI technology can select financial products based on the investor’s preference, help investors better understand the product returns, and improve the service quality of the financial industry.

Research on personalized recommendation system for social media marketing content in big data environment

Abstract A personalized recommendation system is an effective and consistent marketing method that caters to consumer demand for goods. It solves the problem of consumer shopping choices on e-commerce websites and is currently a hot spot in the field of network information services. In this paper, from the perspective of the user’s shopping process, we summarize the four factors that can maximally reflect the consumer’s interest and preference, i.e., product browsing, collection, adding to cart, and purchasing behavior. To achieve static user interest weights, we quantify each index factor and set the corresponding rules. Considering the change in user interest, the decaying interest value over time is designed to compensate for the deficiencies of static system recommendations. We use implicit user feedback data to identify content that truly interests users and then construct a personalized recommendation algorithm for social media marketing content using multi-source data. The test results show that UIPR has an MRR value of more than 0.8 and an NDCG value of more than 0.55 in both the MovieLens and Taobao datasets, compared to the baseline model’s best value. This proves that UIPR consistently performs better and makes better recommendations.

Personalized Recommendation System for English Teaching Resources in Colleges and Universities Based on Collaborative Recommendation

Abstract In recent years, with the rapid development of the Internet and education informatization, online teaching has become a popular education mode in the information age, providing learners with very rich teaching resources. In this paper, we construct a personalized system and co-recommendation technology for English teaching resources, and we improve the traditional co-recommendation algorithm and propose hybrid recommendations. The performance of the system is evaluated experimentally to compare the effectiveness of the performance of the four systems. The improved recommendation algorithm is superior to the other three recommendation algorithms in each dataset in the system. The average grade mean of the experimental class assisted by the hybrid recommendation system in teaching English in colleges and universities in the latter two experiments is 27.54, which is higher than that of the comparison class of 25.33, and the T-value is 1.81>1.645. The improved personalized recommender system has good validity and stability in both performance and practical application.

Design of Personalized Recommendation System for Teaching Resources Based on Cloud Edge Computing

With the continuous development of cloud computing and edge computing technologies, the education sector is gradually applying these technologies to enhance the management and utilization efficiency of teaching resources. Therefore, to address the issue of information overload mentioned above, it is necessary to establish a personalized recommendation system based on user needs, preferences, and other information, recommending products, information, and resources that may be of interest to users. This can not only save users search time, but also alleviate the problem of information overload to some extent. On this basis, this article discussed a new content oriented recommendation method: constructing a user interest feature vector resource association matching model, and analyzing it to achieve recommendation of similar resources. The experimental results showed that the MAE (Mean Absolute Error) value of personalized recommendation based on CF (Collaborative Filtering) algorithm was below 0.8, which was smaller than other algorithms, indicating high accuracy of recommendation based on CF algorithm.

A Study of Innovative Teaching Methods in Higher Education for Digital Localization

Abstract With the rapid development of the Internet and information technology, the data generated by online learning resources has shown explosive growth. In this paper, a personalized recommendation model is used to transform and innovate digital localized education. Firstly, the model is constructed by combining online learning characteristics to generate personalized learning paths. Then, personalized recommendation algorithms are proposed on this basis, and traditional recommendation algorithms are found to have limitations. Therefore, this paper chooses a personalized recommendation algorithm based on a knowledge graph. After the questionnaire survey of the learners, it was concluded that there were significant differences in the three dimensions of learning motivation, cognitive load, and learning self-control through the comparison of the differences between the pre-and post-tests in the five dimensions, and the self-control of the students was improved. Then, the satisfaction analysis of the recommender system was conducted, and most of the learners were satisfied and very satisfied with the system, and “dissatisfied” and “very dissatisfied” were 0. The personalized recommender system provides effective targeted learning methods and improves learning efficiency in the innovation of digital localization education. The personalized recommendation system offers effective targeted learning methods that enhance learning efficiency in the innovation of digital localized education.

Q-ADER: An Effective Q-Learning for Recommendation With Diminishing Action Space.

Deep reinforcement learning (RL) has been widely applied to personalized recommender systems (PRSs) as they can capture user preferences progressively. Among RL-based techniques, deep Q-network (DQN) stands out as the most popular choice due to its simple update strategy and superior performance. Typically, many recommendation scenarios are accompanied by the diminishing action space setting, where the available action space will gradually decrease to avoid recommending duplicate items. However, existing DQN-based recommender systems inherently grapple with a discrepancy between the fixed full action space inherent in the Q-network and the diminishing available action space during recommendation. This article elucidates how this discrepancy induces an issue termed action diminishing error in the vanilla temporal difference (TD) operator. Due to this discrepancy, standard DQN methods prove impractical for learning accurate value estimates, rendering them ineffective in the context of diminishing action space. To mitigate this issue, we propose the Q-learning-based action diminishing error reduction (Q-ADER) algorithm to modify the value estimate error at each step. In practice, Q-ADER augments the standard TD learning with an error reduction term which is straightforward to implement on top of the existing DQN algorithms. Experiments are conducted on four real-world datasets to verify the effectiveness of our proposed algorithm.

RETRACTION: Personalized Recommendation System Design for Library Resources through Deep Belief Networks

RETRACTION: Personalized Recommendation System Design for Library Resources through Deep Belief Networks

FPGA-Accelerated Data Preprocessing for Personalized Recommendation Systems

FPGA-Accelerated Data Preprocessing for Personalized Recommendation Systems

Research on personalized recommendation of teaching resources based on joint probability matrix decomposition model and CNN improvement algorithm

Abstract This study proposes a teaching resource recommendation method (TRRDLMF) based on deep learning and probabilistic matrix decomposition, aiming to improve teaching resource recommendation’s accuracy and personalization level. The study combines hybrid neural network feature extraction of teaching resources and user feature extraction based on extended noise-reducing self-encoder and extended probabilistic matrix decomposition-based teaching resource recommendation technique. The study validates the model’s effectiveness by conducting empirical analyses on four online learning platform datasets of different sizes. The recommendation system can effectively track learners’ knowledge mastery status and learning preferences, and provide corresponding teaching resources. Test question similarity and difficulty analysis results show that the model can accurately capture the correlation between test questions and provide complementary data in education. The personalized recommendation analysis reveals the learners’ knowledge preference states that change with learning, demonstrating the model’s ability to give explanations at the level of learners’ knowledge preferences. The analysis of the impact of data size on recommendation results shows that the recommender system can achieve up to 73.12% accuracy and 97.89% recall for different TOP-K recommendation lists, with the best F-value at TOP-6. The personalized recommendation system for teaching resources based on the joint probability matrix decomposition model and CNN improvement algorithm proposed by the research demonstrates significant effects in improving the accuracy and personalization level of teaching resources recommendation, which helps learners to acquire suitable learning resources more efficiently, and has high practical value and promotion potential.

News Recommendation System Based on User Interest and Deep Network

In order to provide the personalized news recommendation for users more efficiently, the personalized recommendation system combined with deep network was investigated. Based on the deep network, a news recommendation system for users was designed. By means of neural network and aggregating users’ interest characteristics, users’ personalized needs for news recommendation was met. In order to solve the problem of inaccurate construction of users’ interest preference characteristics, a personalized news method based on users’ search records and interest preference was proposed. By constructing exogenous user interest preferences from user search records, the final recommendation list was generated by using the fusion method of the two preferences. Because the traditional recommendation algorithm ignored time series of the users’ browsing behaviors, an improved circulation model of neural network algorithm was proposed. The parallel convolution neural network based on attention was used to aggregate characteristics of users’ interest and the recursive neural network based on attention mechanism was used to explore hidden time series characteristics. At the same time, it was tested on real news data sets and the results showed that this method had a good recommendation effect.

Analysis and Design of a Personalized Recommendation System Based on a Dynamic User Interest Model

Analysis and Design of a Personalized Recommendation System Based on a Dynamic User Interest Model

Personalized learning paths recommendation system with collaborative filtering and content-based approaches

Recommender systems have undergone a transformative evolution, reshaping user interactions across diverse domains. Notably, the emphasis on personalized learning paths has grown significantly in education. This research paper delves into the performance evaluation of User-based Collaborative Filtering and Content-based recommendation techniques to develop innovative recommender systems explicitly tailored to Information Systems students. By integrating the primary dataset collection rooted within the Knowledge - Skill - Attitude framework for students in the Faculty of Information Systems at the University of Economics and Law, this study assesses how effectively these two separate models develop personalized recommendation systems. Furthermore, the empirical evaluation of two distinct models, the Collaborative Filtering and Content-Based approach, across key metrics such as Precision, Recall, and F1-Score, provides a comprehensive view of their effectiveness in generating a Recommendation System for the University of Economics and Law. Findings reveal that the Collaborative Filtering approach excels in Precision, achieving a perfect score. At the same time, the Content-based technique demonstrates superior recall capabilities, suggesting its potential to cater to diverse educational needs. This paper also highlights the transformative role of recommendation systems in higher education, particularly in enhancing student engagement through personalized learning experiences and aligning curricula with industry requirements. Recognizing the limitations inherent in deploying either model independently, future research should propose a hybrid approach that combines the strengths of both Collaborative Filtering and Content-based methods, aiming to mitigate the existing drawbacks of the distinct model. The findings provide actionable insights for students, universities, and businesses to enhance educational content and career development tools and pave the way for future research on hybrid recommendation methodologies, which promise a more tailored and efficient learning experience for learners.

A Study on Personalized Digital Marketing Content Creation Based on Consumer Psychoanalysis

Abstract At present, personalized recommendation technology is widely used in digital marketing. In this paper, on the basis of the existing personalized recommendation algorithm based on commodity characteristics, from the perspective of consumer psychology, we propose a multiple attitude recommendation algorithm under the apparent awareness of the customer. In this recommendation algorithm, the user’s recent and historical interest weights are added, and personalized digital marketing content recommendations are made based on consumer psychology. The MT algorithm designed in this paper has a higher recommendation accuracy when compared to other recommendation algorithms. A questionnaire survey is conducted to examine the influence of marketing content on consumers’ purchase intentions on shopping websites using the personalized recommendation system designed in this paper. The correlation analysis results indicate that the variables and the willingness to buy have a positive correlation at a significance level of 0.01. The final regression equation: willingness to buy = 0.065+0.126*information orchestration+0.113*pop-up ads+0.109*social channel recommendation+0.158*web system recommendation+0.152*user trust, which indicates that the variable of web system recommendation has the greatest effect on willingness to buy.

Personalized Recommendations of Online English Teaching Resources for Higher Vocational Education

Abstract Facing the intricate challenges of English instruction in higher vocational colleges, this research innovatively employs online resources to elevate educational quality and learner efficiency. It critiques the ineffectiveness of “one-size-fits-all” educational models and proposes a cutting-edge personalized recommendation system. This system adeptly curates learning materials to align with individual students’ learning patterns and competencies. By pioneering the TDINA and CUPMF models, and synergizing them with convolutional neural network (CNN) technology, our study dives deep into the educational content, ensuring precise resource recommendations. The system’s prowess was demonstrated through the successful recommendation of 815 resources, identifying strengths in electronic wall charts and courseware, alongside areas for enhancement in microclass scripts and recordings. A specialized experiment in personalized exercise recommendations further underscored the system’s efficacy, accurately tailoring the exercise level and difficulty to students’ learning capacities. Significantly, the CUPMF model emerged as a robust tool in refining the accuracy of these personalized recommendations, heralding a new era of bespoke educational experiences for students.

Research on Personalized Recommendation System of E-Commerce Based on Big Data

Research on Personalized Recommendation System of E-Commerce Based on Big Data

BiVAE를 활용한 MBTI 기반 OTT 서비스 개인화 추천 시스템

The OTT platform, which provides various media contents in the modern society, seeks to improve the user experience by utilizing a personalized recommendation system. However, current recommendation systems are having difficulty in making accurate recommendations because they do not fully understand user's tendencies. This study proposes the use of a personalized recommendation algorithm using BiVAE (bilateral variational autoencoder) to solve this problem, and considers group-specific applications through MBTI. BiVAE is a probabilistic generation model that compresses and generates data considering of bidirectional information flow, providing richer expression and reconstruction capabilities by encoding and decoding in both directions. As a result of applying four types of data to the model, when applying BiVAE for each group using MBTI, the accuracy of OTT genre recommendation was shown to be superior to that of other methods. In addition, when considering MBTI, a personal recommendation using BiVAE showed higher accuracy compared to the existing recommendation system. This result means that the personalized recommendation system considering the user's personal characteristics and personality is important.

Detection of Traditional Costumes: A Computer Vision Approach

Traditional attire has assumed a pivotal role within the contemporary fashion industry. The objective of this study is to construct a computer vision model tailored to the recognition of traditional costumes originating from five distinct countries, namely India, Korea, Japan, Tanzania, and Vietnam. Leveraging a dataset comprising 1,608 images, we proceeded to train the cutting-edge computer vision model YOLOv8. The model yielded an impressive overall mean average precision (MAP) of 96%. Notably, the Indian sari exhibited a remarkable MAP of 99%, the Tanzanian kitenge 98%, the Japanese kimono 92%, the Korean hanbok 89%, and the Vietnamese ao dai 83%. Furthermore, the model demonstrated a commendable overall box precision score of 94.7% and a recall rate of 84.3%. Within the realm of the fashion industry, this model possesses considerable utility for trend projection and the facilitation of personalized recommendation systems.

Retracted: A Personalized Recommendation System for English Teaching Resources Based on Multi-K Nearest Neighbor Regression Algorithm

Retracted: A Personalized Recommendation System for English Teaching Resources Based on Multi-<i>K</i> Nearest Neighbor Regression Algorithm

Retracted: Design of Personalized Recommendation System for Swimming Teaching Based on Deep Learning

Retracted: Design of Personalized Recommendation System for Swimming Teaching Based on Deep Learning

Research on Kindergarten Drama Education Activity System with Traditional Culture as Carrier under Big Data Platform

Abstract Drama education activities carried out by traditional culture comply with, guide and stimulate children’s dramatic nature so that each child can find a suitable place for himself in drama education activities and promote the growth of children with individuality. This paper builds a flipped classroom teaching model for kindergarten drama education activities based on the microblogging public platform. Teachers in the flipped classroom of drama education activities need to collect traditional cultural drama resources before class, and the basic framework of a personalized drama resource recommendation system is proposed on the WeChat public platform. The optimization of drama resource recommendation results is carried out using the preference score of drama resources using the collaborative filtering recommendation algorithm of multi-featured users. The performance test is conducted for the personalized drama resource recommendation system constructed in this paper to provide drama resources for the development of kindergarten drama education activities in the flipped classroom. The results show that when the preference recommendation of multi-featured users’ drama resources has a certain number of users, its accuracy is about 4.5% higher than that of the traditional method, the F-score value is about 0.05 higher than that of the traditional recommendation method, and the real-time updating delay of the personalized recommendation system fluctuates between 1.18s~1.65s. The personalized recommendation system can help teachers to obtain the update and download of traditional culture drama resources in time, make a good guarantee of drama teaching resources for kindergartens to carry out drama education activities with traditional culture as the carrier, and cultivate young children’s awareness of the protection of traditional culture.