Contemporary Recommendation Systems on Big Data and Their Applications: A Survey

This survey paper conducts a comprehensive analysis of the evolution and contemporary landscape of recommendation systems, which have been extensively incorporated across a myriad of web applications. It delves into the progression of personalized recommendation methodologies tailored for online products or services, organizing the array of recommendation techniques into four main categories: content-based, collaborative filtering, knowledge-based, and hybrid approaches, each designed to cater to specific contexts. The document provides an in-depth review of both the historical underpinnings and the cutting-edge innovations in the domain of recommendation systems, with a special focus on implementations leveraging big data analytics. It further outlines and explores the predominant challenges encountered in the current generation of recommendation systems, including issues related to data sparsity, scalability, and the imperative for diversified recommendation outputs. The survey underscores these challenges as promising directions for subsequent research endeavors within the discipline. Additionally, the paper examines various real-life applications driven by recommendation systems, addressing the hurdles involved in seamlessly integrating these systems into everyday life. Ultimately, the survey underscores how the advancements in recommendation systems, propelled by big data technologies, have the potential to significantly enhance real-world experiences.

keywords:

[label1]organization=Antai College of Economics and Management, Shanghai Jiao Tong University,addressline=1954 Huashan Road, city=Shanghai, postcode=200030, state=Shanghai, country=China

[label2]organization=Department of Electrical and Computer Engineering, University of Miami,addressline=1251 Memorial Drive, city=Coral Gables, postcode=33146, state=FL, country=USA

[label3]organization=Department of Architecture, Cornell University,addressline=129 Sibley Dome, city=Ithaca, postcode=14853, state=NY, country=USA

[label4]organization=Bascom Palmer Eye Institute, University of Miami Miller School of Medicine,addressline=900 NW 17th St, city=Miami, postcode=33136, state=FL, country=USA

[label5]organization=Department of Civil & Architectural Engineering, University of Miami,addressline=1251 Memorial Drive, city=Coral Gables, postcode=33146, state=FL, country=USA

[label6]organization=Department of Architecture, University of Miami,addressline=1223 Theo Dickinson Dr, city=Coral Gables, postcode=33146, state=FL, country=USA

Comprehensive Classification and Analysis of Recommendation Techniques: The paper meticulously categorizes the myriad of recommendation system methodologies into four principal types: content-based, collaborative filtering, knowledge-based, and hybrid approaches. It offers a detailed exploration of how these methodologies have evolved over time and their application in providing personalized recommendations across various online platforms. This classification serves as a foundational framework for understanding the diverse strategies employed in tailoring user experiences and addresses the unique challenges and requirements specific to each approach.

Examination of Challenges and Future Research Directions: Highlighting the current challenges faced by recommendation systems, such as data sparsity, scalability, and the need for diversifying recommendation outputs, the paper not only provides a critical analysis of these issues but also positions them as promising avenues for future research. This focus underscores the dynamic nature of the field and encourages the exploration of innovative solutions to enhance the effectiveness and efficiency of recommendation systems in handling large-scale data and meeting the evolving preferences of users.

Real-World Applications and Impact on Society: The survey extends its analysis beyond theoretical models to examine the practical implementation and impact of recommendation systems in everyday life. It explores their application across various domains including marketing, healthcare, and governance, and discusses how they influence consumer behavior and societal trends. By highlighting the potential of recommendation systems to promote sustainable lifestyles and improve decision-making processes, the paper sheds light on the significant role these technologies play in shaping our digital and real-world experiences.

1 Introduction

In this survey, we scrutinize the escalating popularity and diverse applications of recommendation systems in web applications, a topic extensively explored by Zhou et al. zhou2021combinatorial . These systems, a specialized category of information filtering systems, are designed to predict user preferences for various items. They play a pivotal role in guiding decision-making processes, such as purchasing decisions and music selections, as discussed by Wang et al. wang2020personalized . An exemplary instance of this application is Amazon’s personalized recommendation engine, which tailors each user’s homepage. Major corporations like Amazon, YouTube, and Netflix utilize these systems to enhance user experience and generate substantial revenue, as highlighted by Adomavicius et al. and Omura et al. adomavicius2005toward ; omura2020ad . Figure 1 from Entezari et al. entezari2021tensor illustrates a modern recommendation system. Additionally, these systems are increasingly pertinent in the field of human-computer interaction (HCI), where they improve interaction efficiency through feedback mechanisms, a topic explored in several studies 7962152 .

Recommendation systems are particularly crucial for certain companies, as their efficiency can lead to substantial revenue generation and competitive advantage, as evidenced in the research by Rismanto et al. and Cui et al. rismanto2020research ; cui2020personalized . For example, Netflix’s “Netflix Prize” challenge aimed to develop a recommender system surpassing their existing algorithm, offering a substantial prize to incentivize innovation.

Furthermore, in the domain of big data, recommendation systems are highly prevalent, as detailed by Li et al. li2021research ; li2021sports . These systems predict user interests in purchasing based on extensive data analysis, including purchase history, ratings, and reviews. There are four widely recognized types of recommendation systems, as identified by Numnonda numnonda2018real : content-based, collaborative filtering-based, knowledge-based, and hybrid-based, each with distinct advantages and drawbacks, as Xiao et al. elucidate xiao2018personalized . For example, collaborative filtering-based systems may face issues such as data sparsity and scalability, as Huang et al. mention huang2019multimodal , and cold-start problems, while content-based systems might struggle to diversify user interests, as noted by Zhang et al. zhang2018mcrs and Benouaret et al. benouaret2020comparative .

As recommendation system algorithms, neural networks, and big data continue to evolve, their integration into various aspects of our lives is increasingly evident. We are witnessing a surge in applications that leverage big data, recommendation systems, and machine learning to enhance our daily experiences. In the realm of marketing, these technologies enable more personalized recommendations that align with individuals’ personal backgrounds and cultural preferences, whether they are watching movies, shopping online, or traveling. The impact extends to governance, where big data applications are facilitating more efficient and responsive public services. Simultaneously, these innovations are promoting a more sustainable lifestyle and fostering stronger connections in healthcare, demonstrating their potential to improve well-being across various sectors. Moreover, these applications are collecting vast amounts of data across all age groups, from children to seniors, empowering individuals with insights to better understand and analyze their behaviors and preferences sun2024said ; huh2019location . This data-driven approach is revolutionizing how we interact with technology, making it a pivotal element in our journey towards a more informed and connected society.

The structure of this paper is outlined as follows: Section 2 provides a comprehensive exploration of recommendation systems, tracing their evolution from historical foundations to contemporary state-of-the-art methodologies, accompanied by a thorough examination of recent advancements within the sector. Section 3 addresses the specific challenges encountered in recommendation systems that leverage big data, such as data sparsity, scalability issues, and the imperative for diverse recommendations. This section also delves into potential solutions for overcoming these obstacles. Section 4 is dedicated to the application of recommendation systems in real-life contexts, discussing their practical implications and the challenges associated with their integration. Finally, the paper culminates with a comprehensive summary presented in Section 7 .

2 Recommendation Systems

Recommendation systems aim to predict users’ preferences for a certain item and provide personalized services yi2019deep . This section will discuss several commonly used recommender methods, such as content-based method, collaborative filtering-based method, knowledge-based method, and hybrid-based method.

2.1 Content-based Recommendation Systems

The main idea of content-based recommenders is to recommend items based on the similarity between different users or items lops2011content . This algorithm determines and differentiates the main common attributes of a particular user’s favorite items by analyzing the descriptions of those items. Then, these preferences are stored in this user’s profile. The algorithm then recommends items with a higher degree of similarity with the user’s profile. Besides, content-based recommendation systems can capture the specific interests of the user and can recommend rare items that are of little interest to other users. However, since the feature representations of items are designed manually to a certain extent, this method requires a lot of domain knowledge. In addition, content-based recommendation systems can only recommend based on users’ existing interests, so the ability to expand users’ existing interests is limited.

2.2 Collaborative Filtering-based Recommendation Systems

Collaborative Filtering-based (CF) methods are primarily used in big data processing platforms due to their parallelization characteristics elahi2016survey . The basic principle of the recommendation system based on collaborative filtering is shown in Fig. 2 alhijawi2016using . CF recommendation systems use the behavior of a group of users to recommend to other users al2018similarity . There are mainly two types of collaborative filtering techniques, which are user-based and item-based.

User-based CF: In the user-based CF recommendation system, users will receive recommendations of products that similar users like rezaimehr2021survey . Many similarity metrics can calculate the similarity between users or items, such as Constrained Pearson Correlation coefficient (CPC), cosine similarity, adjusted cosine similarity, etc. For example, cosine similarity is a measure of similarity between two vectors. Let x 𝑥 x italic_x and y 𝑦 y italic_y denote two vectors, cosine similarity between x 𝑥 x italic_x and y 𝑦 y italic_y can be represented by

Item-based CF: Item-based CF algorithm predicts user ratings for items based on item similarity. Generally, item-based CF yields better results than user-based CF because user-based CF suffers from sparsity and scalability issues. However, both user-based CF and item-based CF may suffer from cold-start problems zhang2016fast .

3.1 Big Data Processing Flow

Big data comes from many sources, and there are many methods to process it ram2018privacy . However, the primary processing of big data can be divided into four steps wu2013data . Besides, Fig. 4 presents the basic flow of big data processing.

Data Processing and Integration. The collection terminal itself already has a data repository, but it cannot accurately analyze the data. The received information needs to be pre-processed emani2015understandable .

Data Analysis. In this process, these initial data are always deeply analyzed using cloud computing technology lin2019cloud .

3.2 Modern Recommendation Systems based on the Big Data

The shortcomings of traditional recommendation systems mainly focus on insufficient scalability and parallelism cheng2020research . For small-scale recommendation tasks, a single desktop computer is sufficient for data mining goals, and many techniques are designed for this type of problems al2021hybrid .

However, the rating data is usually so large for medium-scale recommendation systems that it is impossible to load all the data into memory at once dev2016recommendation . Common solutions are based on parallel computing or collective mining, sampling and aggregating data from different sources, and using parallel computing programming to perform the mining process chen2018disease . The big data processing framework will rely on cluster computers with high-performance computing platforms wan2021research . At the same time, data mining tasks will be deployed on a large number of computing nodes (i.e., clusters) by running some parallel programming tools asiyakeyword , such as MapReduce kadam2016big ; verma2015big . For example, Fig. 5 is the MapReduce in the Recommendation Systems.

In recent years, various big data platforms have emerged uzun2021big . For example, Hadoop and Spark kadam2016big , both developed by the Apache Software Foundation, are widely used open-source frameworks for big data architectures kadam2016big ; zhang2018service . Each framework contains an extensive ecosystem of open-source technologies that prepare, process, manage and analyze big data sets chaithra2015user . For example, Fig. 6 is the ecosystem of Apache Hadoop ait2019distributed .

Hadoop allows users to manage big data sets by enabling a network of computers (or “nodes”) to solve vast and intricate data problems. It is a highly scalable, cost-effective solution that stores and processes structured, semi-structured and unstructured data.

Spark is a data processing engine for big data sets. Like Hadoop, Spark splits up large tasks across different nodes. However, it tends to perform faster than Hadoop, and it uses random access memory (RAM) to cache and process data instead of a file system. This enables Spark to handle use cases that Hadoop cannot. The following are some benefits of the Spark framework:

It is a unified engine that supports SQL queries, streaming data, machine learning (ML), and graph processing.

It can be 100x faster than Hadoop for smaller workloads via in-memory processing, disk data storage, etc.

Furthermore, Spark is fully compatible with the Hadoop eco-system and works smoothly with Hadoop Distributed File System (HDFS), Apache Hive, and others. Thus, when the data size is too big for Spark to handle in-memory, Hadoop can help overcome that hurdle via its HDFS functionality. Fig. 7 is a visual example of how Spark and Hadoop can work together. Fig. 8 is the the architecture of the modern recommendation system based on Spark.

4 Recommendation System Application

Recommendation systems have become ubiquitous across diverse sectors such as search engines, digital media platforms, and e-commerce sites on the internet [1][2]. The progression of information technology has led to their significant evolution, embracing increasingly complex models. The emergence of big data has been a catalyst for the refinement of recommendation systems, empowering them to offer more precise and holistic recommendations. Currently, the incorporation of big data into contemporary recommendation systems plays a crucial role in streamlining operations in e-commerce and e-governance, as well as in fostering sustainable living practices [3][4][5]. This integration signifies a leap forward in leveraging technology to enhance decision-making processes and user experiences across various digital platforms.

4.1 Recommendation System in E-Commerce

Recommendation systems have evolved from specialized tools utilized by a select few e-commerce platforms to vital commercial assets that significantly transform the e-commerce landscape [6]. Major online platforms and applications, such as Amazon and TikTok, now harness the power of big data to refine their recommendation algorithms for users [7][8]. Ansari et al. previously highlighted the need for advancements in data collection and analytics to expand the operational advantages in the marketing sector, prompted by the advent of new applications for information agents [9]. With the advancement of big data, the application of information agents has shifted towards providing accurate and tailored recommendations to customers on online markets and platforms through innovative models like topic modeling and sentiment analysis [10][11]. Therefore, in an era dominated by big data, it’s evident that recommender systems have become widely integrated into various aspects of e-commerce operations. This extensive adoption emphasizes the pivotal role these systems play in improving user experience, personalizing customer interactions, and boosting the overall efficiency of e-commerce platforms.

4.2 Recommendation System in E-Governance

E-governance stands as a fundamental challenge in the realm of smart city initiatives, integrating information technology and big data in the public sector to elevate the delivery of services and information. This approach not only aims to enhance government transparency, accountability, and trustworthiness but also to engage citizens in the governance process [12]. In the digital era, particularly highlighted by the rise of epidemics, the demand for e-governance in society is on the rise. This underscores the necessity for governments to establish adept online information systems to meet the goals of effective e-governance [13]. Businesses, including pharmaceutical companies, are also recognizing the need for digital governance. For instance, they can implement recommendation systems, built on blockchain and machine learning technologies, to streamline drug shipment monitoring [14]. Additionally, these systems have applications in demand-side management, like energy management, where they utilize big data analytics to identify residential users’ preferences for energy-efficient appliances [15]. Thus, the deployment of recommendation systems, bolstered by big data technologies, plays a crucial role in improving the digital governance framework, optimizing business processes, and facilitating efficient energy management in the digital age.

4.3 Recommendation System in Sustainable Lifestyle

In the context of an academic discourse exploring the impact of recommendation systems on fostering a sustainable lifestyle, the digital transformation catalyzed by the Internet revolution has significantly facilitated the transition towards e-commerce and a lifestyle centered around digital interactions, concurrently with a heightened emphasis on sustainability across environment, societal, and governance sectors xia2023dynamic . This shift has intensified the demand for environmentally friendly practices in daily activities, such as online shopping, dietary habits, and transportation, prompting both organizations and individuals to prefer products and services with reduced environmental footprints. Addressing the nexus of technological innovation, consumer behavior, and environmental responsibility, recent studies advocate the integration of green marketing strategies with online retail platforms through the deployment of sophisticated recommendation systems felfernig2023recommender . These systems are instrumental in refining the digital shopping journey, aiming to promote sustainable living by prioritizing options with lower environmental impacts, thus facilitating a shift towards sustainability among both providers and consumers. The work of Lee et al lee2011recommender . and Zhang et al zhanga2022towards . highlights the critical capacity of recommendation systems to advocate for environmentally sustainable choices, representing a crucial advancement in embedding eco-sustainability within the digital commerce ecosystem.

Furthermore, green building emerges as a significant aspect that profoundly influences our connection to sustainable living xu2021sustainable . With the advancement of recommendation systems, big data, and the Internet of Things (IoT), several challenges associated with green building can be addressed through the integration of recommendation systems and machine learning technologies. These technologies hold the potential to enhance various facets of green building, including:

Implementing Building Information Modeling (BIM) and Life Cycle Assessment (LCA) for sustainable construction, veselka2020recommendations ; cheng2023data

Such integrations not only underscore the potential of technological innovations in promoting energy efficiency and supporting sustainable building practices but also mark a significant stride towards leveraging recommendation systems in the pursuit of a greener lifestyle.

4.4 Recommendation System in Healthcare

The healthcare industry is experiencing a paradigm shift with the incorporation of cutting-edge technologies, and recommendation systems have emerged as a pivotal component in this transformative landscape. Leveraging machine learning algorithms and data analytics, recommendation systems in healthcare offer a versatile range of applications, from improving clinical decision-making to enhancing patient engagement. This subsection explores the diverse facets of recommendation systems in healthcare and their impact on various stakeholders within the ecosystem.

Clinical Decision Support . One of the primary applications of recommendation systems in healthcare is in clinical decision support. These systems analyze electronic health records (EHRs), medical literature, and patient data to assist healthcare professionals in making informed decisions about diagnostics, treatment plans, and interventions. By providing relevant and evidence-based information, recommendation systems contribute to more accurate and personalized patient care, potentially reducing diagnostic errors and improving overall healthcare outcomes bates2003impact ; shojania2009effects .

Patient-Centered Care . In the era of patient-centered care, recommendation systems play a crucial role in tailoring healthcare services to individual patient needs. These systems analyze patient preferences, demographics, and health histories to generate personalized recommendations for treatment options, preventive measures, and lifestyle modifications. By fostering patient engagement and empowerment, recommendation systems contribute to a more collaborative and effective healthcare relationship between providers and patients coulter2007effectiveness ; street2009communication .

Resource Optimization . Recommendation systems help optimize healthcare resources by streamlining processes and improving operational efficiency. For instance, in hospital management, these systems can suggest optimal bed allocation, appointment scheduling, and resource utilization based on historical data and real-time information. By minimizing bottlenecks and enhancing resource allocation, recommendation systems contribute to cost-effectiveness and improved service delivery li2017survey ; brailsford2009comprehensive .

Telehealth and Remote Monitoring . With the rise of telehealth and remote monitoring, recommendation systems support healthcare providers in delivering virtual care. These systems analyze patient-generated health data from wearable devices, monitoring tools, and telehealth platforms to provide timely recommendations for interventions, medication adjustments, or lifestyle modifications. This real-time support contributes to proactive healthcare management, particularly for patients with chronic conditions fatehi2018clinician ; dorsey2016state .

Collaborative Healthcare Networks . Recommendation systems facilitate collaboration and knowledge sharing among healthcare professionals through the creation of collaborative networks. By analyzing expertise, research interests, and clinical experiences, these systems connect healthcare professionals for consultations, research collaborations, and second opinions. This fosters a culture of continuous learning and knowledge dissemination within the healthcare community alshammary2019collaborative ; choi2018systematic .

As recommendation systems continue to evolve, their integration into healthcare processes holds immense potential for improving patient outcomes, enhancing operational efficiency, and advancing the overall quality of healthcare services. However, challenges such as data interoperability, privacy concerns, and algorithmic transparency must be addressed to ensure the responsible and ethical deployment of recommendation systems in the complex healthcare landscape. Ongoing research, interdisciplinary collaboration, and stakeholder engagement are crucial for harnessing the full benefits of recommendation systems in healthcare.

5 Datasets for Recommendation Systems

Datasets play a pivotal role in the development, evaluation, and benchmarking of recommendation systems. The choice of dataset depends on factors such as the application domain, the type of recommendation task, and the specific research objectives. In this section, we provide a summary of some commonly used datasets in recommendation systems research:

5.1 MovieLens

The MovieLens dataset is one of the most widely used datasets for collaborative filtering-based recommendation systems. It contains movie ratings provided by users, along with movie metadata such as titles, genres, and release years. MovieLens datasets are available in various sizes, ranging from small-scale datasets suitable for initial experimentation to large-scale datasets for comprehensive evaluations.

5.2 Amazon Reviews

Amazon provides extensive datasets comprising user reviews and ratings for a wide range of products available on its platform, including books, electronics, clothing, and more. These datasets offer rich information about user preferences, product attributes, and user-item interactions, making them valuable resources for research in recommendation systems, sentiment analysis, and e-commerce analytics.

5.3 Netflix Prize Dataset

The Netflix Prize dataset is a large-scale dataset of movie ratings collected from Netflix users. It was released as part of the Netflix Prize competition, a renowned competition aimed at improving the performance of recommendation algorithms. The dataset contains millions of ratings provided by users over several years, along with additional contextual information such as user demographics and temporal dynamics.

5.4 Last.fm Dataset

The Last.fm dataset comprises music listening histories of users on the Last.fm platform, including details about artists, albums, and user preferences. It offers insights into user behavior and preferences in the context of music consumption, making it valuable for research in music recommendation systems, personalized playlists, and music discovery applications.

5.5 Yelp Dataset

The Yelp dataset consists of user reviews and ratings for businesses across various categories, including restaurants, hotels, and local services. It provides rich information about user opinions, business attributes, and geographic locations, enabling research in recommendation systems, sentiment analysis, and location-based services.

5.6 Other Datasets

In addition to the datasets mentioned above, several other datasets are available for recommendation systems research, covering diverse domains such as news articles, social media interactions, academic papers, and online retail transactions. These datasets offer valuable opportunities for exploring different recommendation scenarios, addressing various challenges, and advancing the state-of-the-art in recommendation technology.

In summary, the availability of diverse datasets facilitates the development and evaluation of recommendation systems across different application domains. Researchers can leverage these datasets to build robust, scalable, and personalized recommendation algorithms, ultimately enhancing user experiences and driving innovation in the field of recommendation systems.

6 Open Questions and Future Research Directions

Despite the significant advancements made in recommendation systems on big data, several open questions persist, and numerous avenues for future research beckon. This section delves into some of these intriguing areas, presenting potential directions for researchers to explore further.

6.1 Interpretable Recommender Systems

Research could focus on developing recommendation models that not only provide accurate predictions but also offer transparent explanations for their recommendations. Techniques such as model-agnostic explanation methods, rule-based systems, or attention mechanisms can be explored to enhance interpretability.

6.2 Fairness and Bias

Future research might concentrate on devising fairness-aware recommendation algorithms that mitigate bias and ensure equitable treatment across diverse user groups. This could involve developing fairness metrics, fairness-aware loss functions, or debiasing techniques tailored for recommendation systems.

6.3 Context-Aware Recommendations

Advanced research may explore leveraging deep learning architectures, such as recurrent neural networks (RNNs) or transformers, to effectively capture and utilize contextual information in recommendation models. Additionally, techniques like multi-modal learning could be investigated to incorporate various types of context, such as textual, visual, or temporal cues.

6.4 Cold-Start Problem

Novel research directions could involve exploring transfer learning approaches, where knowledge learned from related domains or auxiliary data sources is transferred to alleviate the cold-start problem. Hybrid recommendation techniques combining collaborative filtering, content-based methods, and knowledge graphs could also be investigated to handle cold-start scenarios more effectively.

6.5 Long-Tail Recommendations

Research efforts could focus on developing specialized algorithms for long-tail recommendations, such as mixture models, probabilistic graphical models, or ensemble methods tailored to capture rare item preferences. Techniques like active learning or diversity-promoting algorithms could also be explored to enhance the coverage of long-tail items in recommendations.

6.6 Dynamic and Adaptive Recommendations

Future research might investigate reinforcement learning frameworks for recommendation systems, where agents learn optimal recommendation policies through interaction with users and feedback. Additionally, online learning algorithms capable of continuously updating recommendation models in response to evolving user preferences and feedback could be explored.

6.7 Privacy-Preserving Recommendations

Research could explore techniques such as federated learning, where recommendation models are trained across decentralized data sources without sharing raw user data. Differential privacy mechanisms could also be integrated into recommendation algorithms to ensure individual user privacy while maintaining recommendation utility.

6.8 Multi-Stakeholder Recommendations

Advanced research may focus on developing multi-objective optimization frameworks for recommendation systems, considering the diverse interests of users, providers, and advertisers simultaneously. Game-theoretic approaches could be employed to model interactions among stakeholders and design recommendation strategies that optimize collective utility while addressing conflicting objectives.

In conclusion, the field of recommendation systems on big data is ripe with opportunities for future exploration and innovation. By addressing these open questions and pursuing novel research directions, researchers can propel the field forward, advancing the state-of-the-art in recommendation technology and unlocking new possibilities for personalized user experiences in diverse application domains.

7 Summary

This survey paper offers an exhaustive overview of recommendation systems, a technological innovation that has seen widespread adoption in various web-based applications in recent years. The primary objective of modern recommendation systems is to furnish users with personalized suggestions for online products or services, employing a range of techniques including content-based, collaborative filtering, knowledge-based, and hybrid approaches to cater to diverse requirements across different scenarios.

The manuscript delves into a comprehensive historical review and a critical examination of the state-of-the-art methodologies in recommendation systems, with a special emphasis on the pioneering developments brought about by the advent of big data analytics. Additionally, this paper scrutinizes the prevalent challenges encountered in contemporary recommendation systems, such as data sparsity, scalability issues, and the need for diversity in recommendations, proposing these hurdles as fertile grounds for future research endeavors.

Simultaneously, this survey extends its analysis to the application of recommendation systems within various life-related domains, including marketing, governance, medical, health, and the promotion of sustainable lifestyles. This exploration aims to provide a foundational understanding of how recommendation systems intersect with everyday life, highlighting their significance in shaping user experiences and influencing societal trends. Through this holistic review, the paper endeavors to present a nuanced perspective on the evolution of recommendation systems and their growing impact on digital consumer culture and beyond.

References

• (1) F. Zhou, B. Luo, T. Hu, Z. Chen, Y. Wen, A combinatorial recommendation system framework based on deep reinforcement learning, in: 2021 IEEE International Conference on Big Data (Big Data), IEEE, 2021, pp. 5733–5740.
• (2) H. Wang, N. Lou, Z. Chao, A personalized movie recommendation system based on lstm-cnn, in: 2020 2nd International Conference on Machine Learning, Big Data and Business Intelligence (MLBDBI), IEEE, 2020, pp. 485–490.
• (3) G. Adomavicius, A. Tuzhilin, Toward the next generation of recommender systems: A survey of the state-of-the-art and possible extensions, IEEE transactions on knowledge and data engineering 17 (6) (2005) 734–749.
• (4) T. Omura, K. Suzuki, P. Siriaraya, M. Mittal, Y. Kawai, S. Nakajima, Ad recommendation utilizing user behavior in the physical space to represent their latent interest, in: 2020 IEEE International Conference on Big Data (Big Data), IEEE, 2020, pp. 3143–3146.
• (5) N. Entezari, E. E. Papalexakis, H. Wang, S. Rao, S. K. Prasad, Tensor-based complementary product recommendation, in: 2021 IEEE International Conference on Big Data (Big Data), IEEE, 2021, pp. 409–415.
• (6) F. Ali, D. Kwak, P. Khan, S. H. A. Ei-Sappagh, S. M. R. Islam, D. Park, K.-S. Kwak, Merged ontology and svm-based information extraction and recommendation system for social robots, IEEE Access 5 (2017) 12364–12379. doi:10.1109/ACCESS.2017.2718038 .
• (7) R. Rismanto, A. R. Syulistyo, B. P. C. Agusta, Research supervisor recommendation system based on topic conformity., International Journal of Modern Education & Computer Science 12 (1) (2020).
• (8) Z. Cui, X. Xu, X. Fei, X. Cai, Y. Cao, W. Zhang, J. Chen, Personalized recommendation system based on collaborative filtering for iot scenarios, IEEE Transactions on Services Computing 13 (4) (2020) 685–695.
• (9) B. Li, A. Maalla, M. Liang, Research on recommendation algorithm based on e-commerce user behavior sequence, in: 2021 IEEE 2nd International Conference on Information Technology, Big Data and Artificial Intelligence (ICIBA), Vol. 2, IEEE, 2021, pp. 914–918.
• (10) X. Li, F. Sun, Sports training recommendation method under the background of data analysis, in: 2021 International Conference on High Performance Big Data and Intelligent Systems (HPBD&IS), IEEE, 2021, pp. 12–16.
• (11) T. Numnonda, A real-time recommendation engine using lambda architecture, Artificial Life and Robotics 23 (2) (2018) 249–254.
• (12) J. Xiao, M. Wang, B. Jiang, J. Li, A personalized recommendation system with combinational algorithm for online learning, Journal of Ambient Intelligence and Humanized Computing 9 (3) (2018) 667–677.
• (13) Z. Huang, X. Xu, J. Ni, H. Zhu, C. Wang, Multimodal representation learning for recommendation in internet of things, IEEE Internet of Things Journal 6 (6) (2019) 10675–10685.
• (14) H. Zhang, T. Huang, Z. Lv, S. Liu, Z. Zhou, Mcrs: A course recommendation system for moocs, Multimedia Tools and Applications 77 (6) (2018) 7051–7069.
• (15) I. Benouaret, S. Amer-Yahia, A comparative evaluation of top-n recommendation algorithms: Case study with total customers, in: 2020 IEEE International Conference on Big Data (Big Data), IEEE, 2020, pp. 4499–4508.
• (16) A. Sun, J. J. Londono, B. Elbaum, L. Estrada, R. J. Lazo, L. Vitale, H. G. Villasanti, R. Fusaroli, L. K. Perry, D. S. Messinger, Who said what? an automated approach to analyzing speech in preschool classrooms, arXiv preprint arXiv:2401.07342 (2024).
• (17) J.-H. Huh, T.-J. Kim, A location-based mobile health care facility search system for senior citizens, The Journal of Supercomputing 75 (2019) 1831–1848.
• (18) B. Yi, X. Shen, H. Liu, Z. Zhang, W. Zhang, S. Liu, N. Xiong, Deep matrix factorization with implicit feedback embedding for recommendation system, IEEE Transactions on Industrial Informatics 15 (8) (2019) 4591–4601.
• (19) P. Lops, M. d. Gemmis, G. Semeraro, Content-based recommender systems: State of the art and trends, Recommender systems handbook (2011) 73–105.
• (20) M. Elahi, F. Ricci, N. Rubens, A survey of active learning in collaborative filtering recommender systems, Computer Science Review 20 (2016) 29–50.
• (21) B. Alhijawi, Y. Kilani, Using genetic algorithms for measuring the similarity values between users in collaborative filtering recommender systems, in: 2016 IEEE/ACIS 15th International Conference on Computer and Information Science (ICIS), IEEE, 2016, pp. 1–6.
• (22) L. Al Hassanieh, C. Abou Jaoudeh, J. B. Abdo, J. Demerjian, Similarity measures for collaborative filtering recommender systems, in: 2018 IEEE Middle East and North Africa Communications Conference (MENACOMM), IEEE, 2018, pp. 1–5.
• (23) F. Rezaimehr, C. Dadkhah, A survey of attack detection approaches in collaborative filtering recommender systems, Artificial Intelligence Review 54 (3) (2021) 2011–2066.
• (24) F. Zhang, T. Gong, V. E. Lee, G. Zhao, C. Rong, G. Qu, Fast algorithms to evaluate collaborative filtering recommender systems, Knowledge-Based Systems 96 (2016) 96–103.
• (25) C. Musto, G. Semeraro, M. d. Gemmis, P. Lops, Learning word embeddings from wikipedia for content-based recommender systems, in: European conference on information retrieval, Springer, 2016, pp. 729–734.
• (26) M. Volkovs, G. W. Yu, T. Poutanen, Content-based neighbor models for cold start in recommender systems, in: Proceedings of the Recommender Systems Challenge 2017, 2017, pp. 1–6.
• (27) D. Mittal, S. Shandilya, D. Khirwar, A. Bhise, Smart billing using content-based recommender systems based on fingerprint, in: ICT Analysis and Applications, Springer, 2020, pp. 85–93.
• (28) Y. Pérez-Almaguer, R. Yera, A. A. Alzahrani, L. Martínez, Content-based group recommender systems: A general taxonomy and further improvements, Expert Systems with Applications 184 (2021) 115444.
• (29) F. Zhang, V. E. Lee, R. Jin, S. Garg, K.-K. R. Choo, M. Maasberg, L. Dong, C. Cheng, Privacy-aware smart city: A case study in collaborative filtering recommender systems, Journal of Parallel and Distributed Computing 127 (2019) 145–159.
• (30) J. Bobadilla, S. Alonso, A. Hernando, Deep learning architecture for collaborative filtering recommender systems, Applied Sciences 10 (7) (2020) 2441.
• (31) J. Bobadilla, F. Ortega, A. Gutiérrez, S. Alonso, Classification-based deep neural network architecture for collaborative filtering recommender systems., International Journal of Interactive Multimedia & Artificial Intelligence 6 (1) (2020).
• (32) M. Dong, X. Zeng, L. Koehl, J. Zhang, An interactive knowledge-based recommender system for fashion product design in the big data environment, Information Sciences 540 (2020) 469–488.
• (33) A. Gazdar, L. Hidri, A new similarity measure for collaborative filtering based recommender systems, Knowledge-Based Systems 188 (2020) 105058.
• (34) P. M. Alamdari, N. J. Navimipour, M. Hosseinzadeh, A. A. Safaei, A. Darwesh, A systematic study on the recommender systems in the e-commerce, IEEE Access 8 (2020) 115694–115716.
• (35) F. Cena, L. Console, F. Vernero, Logical foundations of knowledge-based recommender systems: A unifying spectrum of alternatives, Information Sciences 546 (2021) 60–73.
• (36) B. Hrnjica, D. Music, S. Softic, Model-based recommender systems, Trends in Cloud-based IoT (2020) 125–146.
• (37) J. Shokeen, C. Rana, A study on features of social recommender systems, Artificial Intelligence Review 53 (2) (2020) 965–988.
• (38) A. Zagranovskaia, D. Mitura, Designing hybrid recommender systems, in: IV International Scientific and Practical Conference, 2021, pp. 1–5.
• (39) A. J. Ibrahim, P. Zira, N. Abdulganiyyi, Hybrid recommender for research papers and articles, International Journal of Intelligent Information Systems 10 (2) (2021) 9.
• (40) S. Shishehchi, S. Y. Banihashem, N. A. M. Zin, S. A. M. Noah, K. Malaysia, Ontological approach in knowledge based recommender system to develop the quality of e-learning system, Australian Journal of Basic and Applied Sciences 6 (2) (2012) 115–123.
• (41) C. C. Aggarwal, Knowledge-based recommender systems, in: Recommender systems, Springer, 2016, pp. 167–197.
• (42) R. Cabezas, J. G. Ruizº, M. Leyva, A knowledge-based recommendation framework using svn, Neutrosophic Sets and Systems 16 (2017) 24.
• (43) J. K. Tarus, Z. Niu, G. Mustafa, Knowledge-based recommendation: a review of ontology-based recommender systems for e-learning, Artificial intelligence review 50 (1) (2018) 21–48.
• (44) M. T. Ribeiro, A. Lacerda, A. Veloso, N. Ziviani, Pareto-efficient hybridization for multi-objective recommender systems, in: Proceedings of the sixth ACM conference on Recommender systems, 2012, pp. 19–26.
• (45) M. Hassan, M. Hamada, Enhancing learning objects recommendation using multi-criteria recommender systems, in: 2016 IEEE International Conference on Teaching, Assessment, and Learning for Engineering (TALE), IEEE, 2016, pp. 62–64.
• (46) Y. Zhang, X. Liu, W. Liu, C. Zhu, Hybrid recommender system using semi-supervised clustering based on gaussian mixture model, in: 2016 international conference on cyberworlds (CW), IEEE, 2016, pp. 155–158.
• (47) G. George, A. M. Lal, Review of ontology-based recommender systems in e-learning, Computers & Education 142 (2019) 103642.
• (48) J. D. West, I. Wesley-Smith, C. T. Bergstrom, A recommendation system based on hierarchical clustering of an article-level citation network, IEEE Transactions on Big Data 2 (2) (2016) 113–123.
• (49) X. He, X. Ke, Research summary of recommendation system based on knowledge graph, in: The 2021 3rd International Conference on Big Data Engineering, 2021, pp. 104–109.
• (50) H. Chen, A dqn-based recommender system for item-list recommendation, in: 2021 IEEE International Conference on Big Data (Big Data), IEEE, 2021, pp. 5699–5702.
• (51) S. D. Kadam, D. Motwani, S. A. Vaidya, Big data analytics-recommendation system with hadoop framework, in: 2016 International Conference on Inventive Computation Technologies (ICICT), Vol. 3, IEEE, 2016, pp. 1–5.
• (52) D. P. Acharjya, K. Ahmed, A survey on big data analytics: challenges, open research issues and tools, International Journal of Advanced Computer Science and Applications 7 (2) (2016) 511–518.
• (53) X. Zhou, W. Liang, I. Kevin, K. Wang, R. Huang, Q. Jin, Academic influence aware and multidimensional network analysis for research collaboration navigation based on scholarly big data, IEEE Transactions on Emerging Topics in Computing 9 (1) (2018) 246–257.
• (54) P. Ram Mohan Rao, S. Murali Krishna, A. Siva Kumar, Privacy preservation techniques in big data analytics: a survey, Journal of Big Data 5 (1) (2018) 1–12.
• (55) X. Wu, X. Zhu, G.-Q. Wu, W. Ding, Data mining with big data, IEEE transactions on knowledge and data engineering 26 (1) (2013) 97–107.
• (56) C. K. Emani, N. Cullot, C. Nicolle, Understandable big data: a survey, Computer science review 17 (2015) 70–81.
• (57) H.-Y. Lin, S.-Y. Yang, A cloud-based energy data mining information agent system based on big data analysis technology, Microelectronics Reliability 97 (2019) 66–78.
• (58) Y. Cheng, X. Bu, Research on key technologies of personalized education resource recommendation system based on big data environment, in: Journal of Physics: Conference Series, Vol. 1437, IOP Publishing, 2020, p. 012024.
• (59) K. Al Fararni, F. Nafis, B. Aghoutane, A. Yahyaouy, J. Riffi, A. Sabri, Hybrid recommender system for tourism based on big data and ai: A conceptual framework, Big Data Mining and Analytics 4 (1) (2021) 47–55.
• (60) A. V. Dev, A. Mohan, Recommendation system for big data applications based on set similarity of user preferences, in: 2016 International Conference on Next Generation Intelligent Systems (ICNGIS), IEEE, 2016, pp. 1–6.
• (61) J. Chen, K. Li, H. Rong, K. Bilal, N. Yang, K. Li, A disease diagnosis and treatment recommendation system based on big data mining and cloud computing, Information Sciences 435 (2018) 124–149.
• (62) Z. Wan, Research on e-commerce recommendation system based on big data technology, in: Journal of Physics: Conference Series, Vol. 1883, IOP Publishing, 2021, p. 012159.
• (63) B. Asiya Banu, S. Banu, Keyword based movie recommendation service using mapreduce.
• (64) J. P. Verma, B. Patel, A. Patel, Big data analysis: recommendation system with hadoop framework, in: 2015 IEEE International Conference on Computational Intelligence & Communication Technology, IEEE, 2015, pp. 92–97.
• (65) M. Uzun-Per, A. B. Can, A. V. Gürel, M. S. Aktaş, Big data testing framework for recommendation systems in e-science and e-commerce domains, in: 2021 IEEE International Conference on Big Data (Big Data), IEEE, 2021, pp. 2353–2361.
• (66) Y.-w. Zhang, Y.-y. Zhou, F.-t. Wang, Z. Sun, Q. He, Service recommendation based on quotient space granularity analysis and covering algorithm on spark, Knowledge-Based Systems 147 (2018) 25–35.
• (67) G. Chaithra, et al., User preferences based recommendation system for services using mapreduce approach (2015).
• (68) B. Ait Hammou, A. Ait Lahcen, S. Mouline, A distributed group recommendation system based on extreme gradient boosting and big data technologies, Applied Intelligence 49 (12) (2019) 4128–4149.
• (69) Z. Xia, A. Sun, X. Cai, S. Zeng, Dynamic analysis of corporate esg reports: A model of evolutionary trends, arXiv preprint arXiv:2309.07001 (2023).
• (70) A. Felfernig, M. Wundara, T. N. T. Tran, S. Polat-Erdeniz, S. Lubos, M. El Mansi, D. Garber, V.-M. Le, Recommender systems for sustainability: overview and research issues, Frontiers in big Data 6 (2023).
• (71) Y.-L. Lee, F.-H. Huang, Recommender system architecture for adaptive green marketing, Expert Systems with Applications 38 (8) (2011) 9696–9703.
• (72) Y. Zhanga, Z. Zenga, G. Taob, Z. Shena, Towards sustainable living via green recommendation systems, International Journal of Information Technology 28 (1) (2022).
• (73) J. Xu, Sustainable technology & social ecology with architectural design (2021).
• (74) Y. Himeur, A. Alsalemi, A. Al-Kababji, F. Bensaali, A. Amira, C. Sardianos, G. Dimitrakopoulos, I. Varlamis, A survey of recommender systems for energy efficiency in buildings: Principles, challenges and prospects, Information Fusion 72 (2021) 1–21.
• (75) M. T. Siddique, P. Koukaras, D. Ioannidis, C. Tjortjis, Smartbuild recsys: A recommendation system based on the smart readiness indicator for energy efficiency in buildings, Algorithms 16 (10) (2023) 482.
• (76) B. J. Gogoi, Green building features and factors affecting the consumer choice for green building recommendation, International Journal of Civil Engineering & Technology 9 (6) (2018) 127–136.
• (77) J. Veselka, M. Nehasilová, K. Dvořáková, P. Ryklová, M. Volf, J. Ružička, A. Lupíšek, Recommendations for developing a bim for the purpose of lca in green building certifications, Sustainability 12 (15) (2020) 6151.
• (78) M. Cheng, H. Gao, Data-driven life-cycle risk assessment of bridge networks using bayesian network, in: Life-Cycle of Structures and Infrastructure Systems, CRC Press, 2023, pp. 1953–1960.
• (79) J. Domingo Gil, Recommender system for sustainable alternatives of building materials: sustainability-focused decision making in the construction industry (2023).
• (80) D. W. Bates, J. M. Teich, J. Lee, D. Seger, G. J. Kuperman, N. Ma’Luf, D. Boyle, L. Leape, The impact of computerized physician order entry on medication error prevention, Journal of the American Medical Informatics Association 10 (4) (2003) 321–327.
• (81) K. G. Shojania, A. Jennings, A. Mayhew, C. R. Ramsay, M. P. Eccles, J. M. Grimshaw, The effects of on-screen, point of care computer reminders on processes and outcomes of care, Cochrane Database of Systematic Reviews (3) (2009).
• (82) A. Coulter, J. Ellins, Effectiveness of strategies for informing, educating, and involving patients, BMJ 335 (7609) (2007) 24–27.
• (83) R. L. Street Jr, G. Makoul, N. K. Arora, R. M. Epstein, How does communication heal? pathways linking clinician–patient communication to health outcomes, Patient Education and Counseling 74 (3) (2009) 295–301.
• (84) X. Li, H. Wang, A survey on resource allocation in cloud computing: Issues and solutions, Journal of Network and Computer Applications 80 (2017) 90–106.
• (85) S. C. Brailsford, J. Vissers, H. Buxton, A comprehensive review of patient simulation in nursing education, Simulation & Gaming 40 (4) (2009) 529–565.
• (86) F. Fatehi, R. Wootton, A clinician’s guide to the use of artificial intelligence in telemedicine–a focus on triage services, Studies in Health Technology and Informatics 252 (2018) 46–51.
• (87) E. R. Dorsey, E. J. Topol, State of telehealth, New England Journal of Medicine 375 (2) (2016) 154–161.
• (88) D. H. Al-Shammary, A. A. Rahman, O. A. Moti, Collaborative learning in healthcare: A systematic review, Journal of Medical Systems 43 (9) (2019) 279.
• (89) W. S. Choi, M. J. Rho, A systematic review of research trends and future directions in gamification, in: Extended Abstracts of the 2018 CHI Conference on Human Factors in Computing Systems, ACM, 2018, p. LBW511.