Service Recommendation Research Articles

Opening a New Era with Machine Learning in Financial Services? Forecasting Corporate Credit Ratings Based on Annual Financial Statements

Corporate credit ratings provide multiple strategic, financial, and managerial benefits for decision-makers. Therefore, it is essential to have accurate and up-to-date ratings to continuously monitor companies’ financial situations when making financial credit decisions. Machine learning (ML)-based internal models can be used for the assessment of companies’ financial situations using annual statements. Particularly, it is necessary to check whether these ML models achieve better results compared to statistical methods. Due to the multi-class classification problem when forecasting corporate credit ratings, the development, monitoring, and maintenance of ML-based systems are more challenging compared to simple classifications. This problem becomes even more complex due to the required coordination with financial regulators (e.g., OECD, EBA, BaFin, etc.). Furthermore, the ML models must be updated regularly due to the periodic nature of annual statements as a dataset. To address the problem of the limited dataset, multiple sampling strategies and machine learning algorithms can be combined for accurate and up-to-date forecasting of credit ratings. This paper provides various implications for ML-based forecasting of credit ratings and presents an approach for combining sampling strategies and ML techniques. It also provides design recommendations for ML-based services in the finance industry on how to fulfill the existing regulations.

Examining the transition to adulthood in autism spectrum disorder: examining the perspectives of autistic individuals, caregivers and service providers

PurposeThe purpose of this study is to examine how the search for transitional services has been characterized as a challenging experience for autistic youth and their families. Transitional services are reported to be inconsistent and do not address the range of needs that autistic individuals have.Design/methodology/approachIn this study, qualitative interviews were conducted with autistic individuals (n = 31), their parents/caregivers (n = 23) and transition-based service providers (n = 10).FindingsFindings invite capacity building across sectors, including working with both the autistic individual and their caregiver, and ensuring targeted services commensurate with individual needs related to autism and ancillary challenges. Implications and recommendations for service and system advancement are offered.Practical implicationsCurrent services were reportedly insufficient in meeting the needs of autistic individuals as they transitioned into adulthood. Service areas needing to be bolstered include daily life, community engagement and employment. Capacity building and enhanced training are required. Information and communication strategies require advancement.Social implicationsA more responsive system is required, which involves support from many societal sectors (e.g. health, mental health, advanced education, social services, industry, housing and justice) over the lifespan. Policy adjustments and organizational mandates need to be reviewed to better consider the needs of transitioning autistic youth and allocate resources accordingly. Partnerships across stakeholder groups are needed.Originality/valueThis study provides details on a known but not well understood issue of transition to adulthood for autistic adults. This study is unique in providing first-hand data from transitioning autistic adults, with corroborating data from families and service providers.

A Customized Deep Sleep Recommender System Using Hybrid Deep Learning.

This paper proposes a recommendation system based on a hybrid learning approach for a personal deep sleep service, called the Customized Deep Sleep Recommender System (CDSRS). Sleep is one of the most important factors for human life in modern society. Optimal sleep contributes to increasing work efficiency and controlling overall well-being. Therefore, a sleep recommendation service is considered a necessary service for modern individuals. Accurate sleep analysis and data are required to provide such a personalized sleep service. However, given the variations in sleep patterns between individuals, there is currently no international standard for sleep. Additionally, service platforms face a cold start problem when dealing with new users. To address these challenges, this study utilizes K-means clustering analysis to define sleep patterns and employs a hybrid learning algorithm to evaluate recommendations by combining user-based and collaborative filtering methods. It also incorporates feedback top-N classification processing for user profile learning and recommendations. The behavior of the study model is as follows. Using personal information received through mobile devices and data, such as snoring, sleep time, movement, and noise collected through AI motion beds, we recommend sleep and receive user evaluations of recommended sleep. This assessment reconstructs the profile and, finally, makes recommendations using top-N classification. The experimental results were evaluated using two absolute error measurement methods: mean squared error (MSE) and mean absolute percentage error (MAPE). The research results regarding the hybrid learning methods show 13.2% fewer errors than collaborative filtering (CF) and 10.2% fewer errors than content-based filtering (CBF) on an MSE basis. According to the MAPE, the methods are 14.7% more accurate than the CF model and 9.2% better than the CBF model. These results demonstrate that CDSRS systems can provide more accurate recommendations and customized sleep services to users than CF, CBF, and combination models. As a result, CDSRS, a hybrid learning method, can better reflect a user's evaluation than traditional methods and can increase the accuracy of recommendations as the number of users increases.

A Privacy-Preserving Time-Aware Method for Next POI Recommendation

Compared with traditional point-of-interest (POI) recommendation, next POI recommendation is more difficult and requires comprehensive consideration of users’ behavior patterns, spatial–temporal context, and other information. In addition, unreliable service providers may disclose the privacy of users when providing recommendation services. For next POI recommendation, a privacy-preserving time-aware recommendation method (PPTA-RM) is proposed in this paper. The PPTA-RM method is based on centralized differential privacy and combines coarse-grained recommendation with fine-grained recommendation. At the coarse-grained level, the users’ POI category preference is modeled by improved matrix factorization and predicted by singular spectrum analysis (SSA), and gradient perturbation is carried out during the matrix factorization process to protect the POI category preference of users. At the fine-grained level, the users’ POI preference is modeled and predicted by an improved hyperlink-induced topic search (HITS) algorithm, which considers the weighted combination of users’ social attributes and POI geographic distance attributes, and a privacy budget allocation strategy considering the visit count of POIs is designed to add Laplace noise to the check-in data of users. The experimental analysis on two real datasets shows that the proposed method improves F1-Score@10 by 0.4–21.8% under different privacy budgets, which validates that the proposed method holds the next POI recommendation accuracy better while preserving the user’s privacy.

Decisional Needs of People From Minority Ethnic Groups Around Living Donor Kidney Transplantation: A UK Healthcare Professionals' Perspective.

Despite improved patient and clinical outcomes, living donor kidney transplantation is underutilized in the United Kingdom, particularly among minority ethnic groups, compared to deceased donor kidney transplantation. This may in part be due to the way in which kidney services present information about treatment options. With a focus on ethnicity, semi structured interviews captured the views of 19 kidney healthcare professionals from two renal centres in West Yorkshire, about the decisional needs and context within which people with advanced kidney disease make transplant decisions. Data were analysed using thematic analysis. Themes were categorized into three groups: 1) Kidney healthcare professionals: language, cultural awareness, trusted personnel, and staff diversity, 2) Patient information resources: timing and setting of education and suitability of patient-facing information and, 3) People with advanced kidney disease: knowledge, risk perception, and cultural/religious beliefs. To our knowledge, this is the first study in the United Kingdom to investigate in depth, healthcare professionals' views on living donor kidney transplantation decision making. Six recommendations for service improvement/delivery to support decision making around living donor kidney transplantation among minority ethnic groups are described.

A Multi-Channel Text Sentiment Analysis Model Integrating Pre-training Mechanism

The number of tourist attractions reviews, travel notes and other texts has grown exponentially in the Internet age. Effectively mining users’ potential opinions and emotions on tourist attractions, and helping to provide users with better recommendation services, which is of great practical significance. This paper proposes a multi-channel neural network model called Pre-BiLSTM combined with a pre-training mechanism. The model uses a combination of coarse and fine- granularity strategies to extract the features of text information such as reviews and travel notes to improve the performance of text sentiment analysis. First, we construct three channels and use the improved BERT and skip-gram methods with negative sampling to vectorize the word-level and vocabulary-level text, respectively, so as to obtain more abundant textual information. Second, we use the pre-training mechanism of BERT to generate deep bidirectional language representation relationships. Third, the vectors of the three channels are input into the BiLSTM network in parallel to extract global and local features. Finally, the model fuses the text features of the three channels and classifies them using SoftMax classifier. Furthermore, numerical experiments are conducted to demonstrate that Pre-BiLSTM outperforms the baselines by 6.27%, 12.83% and 18.12% in average in terms of accuracy, precision and F1-score.

Predicting mobile users' next location using the semantically enriched geo-embedding model and the multilayer attention mechanism

Predicting the next location of human mobility and its semantic information can support recommendations for location-based services and trajectory mining, such as human mobility pattern recognition and sequential anomaly detection. Previous studies have ignored the implicit correlation between location and spatiotemporal information thereby limiting the model performance in terms of location prediction accuracy. In this study, we propose a GEMA-BiLSTM (Geographical Embedding and Multilayer Attention -Bidirectional Long Short-Term Memory) model to predict the next-location in users' mobility. The model combines location and spatiotemporal information to extract the semantics of human mobility. The results show that the model can accurately predict the next location with a high accuracy of 87.63%. Compared with BiLSTM-CNN, LSTM, CNN, and Markov, the location prediction accuracy of the model improved by 2.28%, 9.72%, 11.53%, and 17.64%, respectively. In addition, the model has the highest semantic prediction accuracy (75.35%). Compared with the BiLSTM-CNN model, the our method improves the semantic prediction accuracy for residential and industrial function areas by 4.79% and 5.37%, respectively. The accuracy of location prediction for different time periods indicates that the next location of human activity during morning rush and evening rush hours is the most difficult to predict, which corresponds to the increase in human travel demand. Moreover, weekday human activity patterns indicate that the commercial area is still very active at night, which may be linked to nighttime economic policies. This study could improve the accuracy of recommendations for location-based service applications.

VACCINE HESITANCY - FROM PARENTAL DISTRUST TO COVID-19 CONSPIRACIES.

Worldwide studies continuously confirm that vaccination is a safe and effective method of combating various infectious diseases and a key component of global public health programs. However, the vaccination status of a population is often lower than needed to achieve collective immunity. A key reason that affects lower vaccination coverage is vaccine hesitancy, identified as one of the ten greatest threats to global public health. So far, vaccine hesitancy has been most investigated in the context of parental refusal of children vaccination. The emergence of the COVID-19 pandemic and the development of its vaccines put vaccine hesitancy further in the focus of investigators as well as healthcare workers and policy makers. We have witnessed its immediate effects on public health and mortality rates as well as even more extreme ways of vaccine refusal than previously documented. The aim of this review article is to summarize relevant scientific understandings of vaccine hesitancy, including its psychological determinants, insights from parental refusal of child vaccination, medical distrust, and conspiracy theories related to the COVID-19 pandemic, as well as recommendations for public health services for combating vaccine hesitancy.

Joint Strategic Needs Assessments in London, the LGBTQ+ population and the latter’s health, care and wellbeing needs

PurposeJoint Strategic Needs Assessments (JSNAs) are intended to help create evidence-based priorities for public health commissioning at local government level in the UK. They are supposed to consider the needs of people with protected characteristics, and this study aims to look at how the JSNAs for London are serving the city’s lesbian, gay, bisexual, transgender and queer (LGBTQ+) population.Design/methodology/approachJSNAs are documentary data and are in the public domain. Each of the 31 JSNAs for London was individually assessed against a series of questions designed to test their inclusion of the local LGBTQ+ population.FindingsFewer than one in five of London’s JSNAs: had a dedicated LGBTQ+ section; cited bespoke research into, or engagement with, the local LGBTQ+ population; made recommendations for specialist services for people from this community; or considered intersectionality in the context of this population.Originality/valueThis study demonstrates that many of London’s JSNAs contain little information on the city’s local LGBTQ+ population and only minimal assessment of its health, care and wellbeing needs. Recommendations include conducting further research on this population at the local level, using available guidance and engaging best practice.

Multi-Feature Video Recommendation Based on Hypergraph Convolution for Mobile Edge Environment

With the massive growth of edge devices, how to provide users with video recommendation services in a mobile edge environment has become a research hotspot. Most traditional video recommendation methods regard the relationship between user and neighbor to be linear and ignore higher-order connectivity among users, which results in poor recommendation performance. Besides, these methods use a single feature to represent user preferences, which cannot effectively alleviate the data sparsity problem. To improve the performance of video recommendation, this article proposes a multi-feature video recommendation method based on hypergraph convolution (MVRHC). Hypergraph convolution is adopted to compute user neighborhood-level features for modeling high-order correlations among users. Final features are obtained by fusing multi-party features through attention mechanism. And video recommendation is then implemented based on the obtained features. Experimental results on two real-world datasets demonstrate that MVRHC has better performance compared with baseline methods.

Student support services: Perceptions and recommendations for the next generation.

Student support services/student affairs are central to the student academic experience and success at US and Canadian dental schools. This manuscript evaluates student and administrator perceptions of support services and offers recommendations for best practices in student services in predoctoral dental education to help institutions improve the student experience. A survey of administrators and dental students found perceptions of student support services vary between these groups. Seventeen student services administrators and 263 students started the survey, and 12 administrators and 156 students completed the full survey. Survey comments indicated access to student support services is a concern. Results of the student survey, in conjunction with current literature, were utilized to develop recommendations for dental student support services. Recommendations for student support services in dental schools include accessibility of student services, and ensuring students have access to support in the domains of wellness, academic support, and peer support as well as implementation of humanistic practices. Wellness supports should include behavioral health services, physical health services, and access to mindfulness interventions. Academic support services should include study skills, time management training, and academic supports such as tutoring. Structured peer support programs should also be implemented. Dental schools should also be mindful of the changing support needs of incoming dental students.

Research on Hybrid Recommendation Model for Personalized Recommendation Scenarios

One of the five types of Internet information service recommendation technologies is the personalized recommendation algorithm, and knowledge graphs are frequently used in these algorithms. RippleNet is a personalized recommendation model based on knowledge graphs, but it is susceptible to localization issues in user portrait updating. In this study, we propose NRH (Node2vec-side and RippleNet Hybrid Model), a hybrid recommendation model based on RippleNet that uses Node2vec-side for item portrait modeling and explores potential association relationships of items; the user portrait is split into two parts, namely, a static history portrait and a dynamic preference portrait; the NRH model adopts a hybrid recommendation approach based on collaborative filtering and a knowledge graph to obtain the user’s preferences on three publicly accessible datasets; and comparison experiments with the mainstream model are lastly carried out. The AUC and ACC increased, respectively, by 0.9% to 29.5% and 1.6% to 31.4% in the MovieLens-1M dataset, by 1.5% to 17.1% and 4.4% to 18.7% in the Book-Crossing dataset, and by 0.8% to 27.9% and 2.9% to 24.1% in the Last.FM dataset. The RippleNet model was used for comparison experiments comparing suggestion diversity. According to the experimental findings, the NRH model performs better in accuracy and variety than the popular customized knowledge graph recommendation algorithms now in use.

Enhancing Collaborative Filtering-Based Recommender System Using Sentiment Analysis

Recommendation systems (RSs) are widely used in e-commerce to improve conversion rates by aligning product offerings with customer preferences and interests. While traditional RSs rely solely on numerical ratings to generate recommendations, these ratings alone may not be sufficient to offer personalized and accurate suggestions. To overcome this limitation, additional sources of information, such as reviews, can be utilized. However, analyzing and understanding the information contained within reviews, which are often unstructured data, is a challenging task. To address this issue, sentiment analysis (SA) has attracted considerable attention as a tool to better comprehend a user’s opinions, emotions, and attitudes. In this study, we propose a novel RS that leverages ensemble learning by integrating sentiment analysis of textual data with collaborative filtering techniques to provide users with more precise and individualized recommendations. Our system was developed in three main steps. Firstly, we used unsupervised “GloVe” vectorization for better classification performance and built a sentiment model based on Bidirectional Long Short-Term Memory (Bi-LSTM). Secondly, we developed a recommendation model based on collaborative filtering techniques. Lastly, we integrated our sentiment analysis model into the RS. Our proposed model of SA achieved an accuracy score of 93%, which is superior to other models. The results of our study indicate that our approach enhances the accuracy of the recommendation system. Overall, our proposed system offers customers a more reliable and personalized recommendation service in e-commerce.

A Knowledge Graph Embedding Based Service Recommendation Method for Service-Based System Development

Web API is an efficient way for Service-based Software (SBS) development, and mashup is a key technology which merges several web services to deal with the increasing complexity of software requirements and expedite the service-based system development. The efficient service recommendation method is vital for the software development. However, the existing methods often suffer from data sparsity or cold start issues, which should lead to bad effects. Currently, this paper starts with SBS development, and proposes a service recommendation method based on knowledge graph embedding and collaborative filtering (CF) technology. In our model, we first construct a refined knowledge graph using SBS-service co-invocation record and SBS and service related information to mine the potential semantics relationship between SBS and service. Then, we learn the SBS and service entities in the knowledge graph. These heterogeneous entities (SBS and service, etc.) are embedded into the low-dimensional space through the representation learning algorithms of Word2vec and TransR, and the distances between SBS and service vectors are calculated. The input of recommendation model is SBS requirement (target SBS), the similarities functional SBS set is extracted from knowledge graph, which can relieve the cold start problem. Meanwhile, the recommendation model uses CF to recommend service to target SBS. Finally, this paper verifies the effectiveness of method on the real-word dataset. Compared with the several state-of-the-art methods, our method has the best service hit rate and ranking quality.

Positive and Negative Experiences With Supportive Services and Programming: Gaps and Recommendations From Youth Experiencing Homelessness

Services for youth experiencing homelessness (YEH) are designed with limited input from the youth themselves. This study explored the experiences and recommendations for services aimed at mitigating the negative effects of homelessness among youth. A total of 45 interviews were conducted with YEH (ages 15 to 24, M = 21.5 years) who experienced at least one night of homelessness. Transcripts were coded by using a modified constructivist grounded theory approach. YEH reported myriad challenges to navigating disjointed programming and misguided policies. Recommendations from YEH for policy and programmatic change include peacekeeping and diffusion training for program staff, trauma-informed approaches, and conflict resolution among agency staff; and integrate creative outlets and transitional services into existing programs. Programming supporting YEH must extend beyond meeting only basic needs to creating opportunities for safety, autonomy, and growth. Programs targeting youth homelessness need input from YEH in their design and implementation.

Interpretable web service recommendation based on disentangled representation learning

Most existing Web service recommendation models based on machine learning do not fully consider the high-order features interaction between users and services and with poor interpretability. In this paper, an Interpretable Web Service Recommendation model based on Disentangled Representation Learning (WSR-DRL) is proposed. First of all, to make full use of the service description information to improve the accuracy of Web service recommendation, the features representation of service name is obtained by using BERT model, and the local and global features representation of service description information is further obtained by combining 2-D CNN and Bi-LSTM. Then the disentangled convolution neural network is used to generate the high-order interaction features between users and services, and the neighborhood routing algorithm is used to mine the latent factors in these features. That improves the accuracy of Web service recommendation and make it interpretable. Finally, in order to verify the effectiveness of the model, several groups of experiments are carried out on real data sets. The experimental results show that compared with latest models such as DMF, DeepFM, DKN, GCMC, NDCG model and WSR-MGAT model, the WSR-DRL model proposed in this paper shows better performance on Precision@10, Recall@10, F1@10 and NDCG@10 evaluation metrics.

Gated Multi-task Learning for QoS-aware Service Recommendation

In the ever-increasing diversity of cloud environment, the recommendation of web service-related applications based on service quality is a basic tasks that both service providers and web developers are very interested in. A key challenge is how to get personalized and accurate QoS values of web services from the multi-source information of users/services. In addition, complex contexts and multi-tasking attributes also make the collaborative services quality prediction difficult to meet. Inspired by the progress of multi-task deep learning, this paper proposes a new framework of service quality prediction called multi-task gated expert network (MGEN), which is based on gating mechanism and multi-task learning. The MGEN consists of three parts: expert-based context-source feature extraction, gated interaction learning and information fusion. First, multiple expert networks are used to capture the latent representation in raw data of web services, including both implicit features in the QoS matrix and explicit features of service descriptions. In the process, several independent experts extract features from different dimensions. Second, output embedding of different expert networks is transmitted to each task layer through different weights, learning both global and local high-order feature interactions. Third, the interactive information of different tasks is fused by embedding splicing, and then fed back to the prediction module for final service recommendation. Results of the comparative experiment demonstrate that the proposed MGEN significantly outperforms the state-of-the-art models of service recommendation, where both the implicit and explicit information of various multi-source features and interaction sequences are effectively extracted. In addition, the gating mechanism performs well in the QoS prediction by independently modeling each task.

A Web Service Clustering Method with Semantic Enhancement Based on RGPS and BTM

<p>In order to overcome the data sparsity problem in service description text and to improve the web service clustering quality, we propose a web service clustering method with semantic enhancement based on RGPS (Role-Goal-Process-Service) Framework and Bi-term Topic Model (BTM). First, we extend service description text’s feature according to RGPS meta-model framework. Also, we generate the service latent feature by BTM. Then, we employ K-means on the generated features. The results of experiments on service registry PWeb show that this method can get better clustering performance in purity and entropy. It is proved that this method has great efficiency compared with the baseline methods K-means, Agglomerative and LDA (Latent Dirichlet Allocation). This paper enhances the service clustering performance and creates foundation work for service organization and recommendation. </p> <p> </p>

Eco-CSAS: A Safe and Eco-Friendly Speed Advisory System for Autonomous Vehicle Platoon Using Consortium Blockchain

Future worldwide 6G research will drive the evolution of emerging intelligent control technologies, such as intelligent speed advisory systems (ISA), to a more advanced generation. As a special type of ISA, consensus-based speed advisory systems (CSAS) can be widely used to recommend a consensus speed for a vehicle platoon, enabling minimizing energy consumption or emissions over a planned route. Recently, speed recommendation services that protect data privacy (i.e., how to obtain an optimal speed in a privacy-preserving way) have drawn tremendous attention. However, current approaches could still encounter service trust issues with central servers and the malicious behavior of vehicles. Furthermore, existing research lacks considering road safety constraints (i.e., safe distance between adjacent vehicles and road speed limits) that are essential for the practical deployment of CSAS. To address the above issues, this paper proposes Eco-CSAS, a safe and eco-friendly consensus speed advisory system using blockchain. We formulate an optimization problem subject to the minimum following distance and maximum road speed limit to minimize the energy consumption of the automatic vehicle platoon. In addition, we introduce a consortium blockchain and cryptographic primitives to ensure service trust and data privacy. We implement the system on the Hyperledger platform, and experimental results show that the system can achieve speed recommendations in a trustworthy and privacy-preserving manner while ensuring a secure platoon.

Effect of patient-related factors on hospitalization service satisfaction and recommendation intention of medical institutions in Korea

ObjectiveThis study examined the factors that influence the 'Overall Satisfaction' and 'Intention to Recommend' of medical institutions used using the Korea Medical Service Experience Survey (2019–2021).Data sourcesThis study used the data of Medical Service Experience Survey in Korea. The data collected for data analysis were from 2019 to 2021 (Medical service period: 2018.07.01. ~ 2021.06.30).Study designThe 2019 Medical Service Experience Survey was conducted from July 8 to September 20, 2019, and a total of 12,507 people (Medical service period: 2018.07.01. ~ 2019.06.30) were collected. The 2020 survey was conducted from July 13 to October 9, 2020, and a total of 12,133 people (Medical service period: 2019.07.01 ~ 2020.06.30.) were collected. The 2021 survey was conducted from July 19 to September 17, 2021), and a total of 13,547 people were collected (Medical service period: 2020.07.01. ~ 2021.06.30). Overall satisfaction and recommendation intentions for medical institutions consist of a Likert 5-point scale. At this time, the Top-box rating model used in the United States was applied.Data collections/extraction methodsIn this study, only those who used inpatient services (15 years of age or older) were included because they spent a long time in a medical institution and had an intensive experience, and a total of 1,105 subjects were included in the analysis.Principal findingsSelf-rated health and the type of bed influenced overall satisfaction with medical institutions. In addition, the type of economic activity, living area, self-rated health, the type of bed, and the type of nursing service affected the intention to recommend. And it was confirmed that overall satisfaction with medical institutions and intention to recommend them were higher in the 2021 survey than in 2019.ConclusionsThese results suggest that government policy on resources and systems is important. Through the case of Korea, it was found that the policy of reducing multi-person beds and expansion of integrated nursing service had a significant impact on patients' experience of using medical institutions and improving the quality of care.