Traditional recommender systems primarily rely on overall ratings, which may fail to capture the fine-grained nuances of user preferences. Multi-Criteria Recommender Systems (MCRS) address this limitation by incorporating user feedback across multiple aspects of the items to provide more accurate and personalized suggestions. While the integration of advanced deep learning techniques has significantly improved MCRS performance, the research landscape remains fragmented, lacking a unified theoretical framework that connects modern neural network architectures with classical Multi-Criteria Decision-Making (MCDM) theories. To address this gap, this paper presents a conceptually driven narrative review that introduces a novel architectural taxonomy for MCRS. We systematically classify existing methodologies into two paradigms: Multi-Stage architectures and Single-Stage architectures. Multi-Stage MCRS explicitly integrates MCDM principles, such as multi-attribute utility functions or Pareto dominance, by decomposing the recommendation pipeline into multi-criteria rating prediction and preference aggregation. Conversely, Single-Stage MCRS employs holistic, end-to-end modeling paradigms, such as neighborhood-based methods, deep tensor factorization, or multiview graph neural networks, in order to capture complex and non-linear dimensional interactions simultaneously. Moreover, this review examines the transition from relying on explicit criteria elicitation to mining implicit preferences from user-generated reviews, a shift that significantly broadens the real-world applicability of MCRS. We also discuss ongoing challenges in the field, such as data sparsity, integration with contextual situations, and model explainability. By bridging classical decision science with modern deep learning, this review provides a clear roadmap and theoretical insights for future MCRS research.

Financial risk models provide critical quantitative insights, yet translating complex risk data into actionable narratives remains a challenge. While LLMs offer powerful text generation capabilities, they struggle with numerical reasoning and are prone to hallucinations which is a critical flaw in financial compliance environment. This paper proposes TSRMTGen, a framework that transforms risk model data into accurate, coherent narratives. Our approach integrates expert knowledge through “Hint” injection and utilizes a two-step generation process to ensure factual consistency. We demonstrate the effectiveness of TSRMTGen through a rigorous 3-layer human-in-the-loop evaluation, achieving a 0

In this paper, we introduce a unique task, the assessment of the mutual fund parent companies, in our financial company, where the anomaly events associated with parent companies need to be identified and sent to financial experts to access the impact on related mutual funds. We propose a hybrid framework of anomaly detection to combine data-driven detection and experts-engaged tuning to enhance the identification process. Our experiments have demonstrated its effectiveness through the feedback from financial experts, utilizing a tracking record spanning from May 2022 to June 2023.

Financial investments are increasingly encouraged to incorporate environmental, social, and governance (ESG) considerations. For instance, in the context of mutual fund investments, once an investor determines a specific risk preference (e.g., conservative, moderate, or aggressive), ESG-optimized portfolios can be recommended to facilitate investment in ESG-positive mutual funds, such as those associated with lower pollution levels and improved ecosystem health. However, promoting ESG integration presents challenges, particularly in ensuring transparency within investment recommendations, which is crucial for fostering investor confidence and adoption. To address this issue, this paper proposes an interactive visualization system that allows users to navigate multi-objective optimized portfolios, compare their strengths and weaknesses, and understand the impact of ESG considerations on portfolio composition. The system aims to enhance user understanding and support informed investment decision-making. The effectiveness of this platform is validated through a user study, wherein financial experts provided positive feedback regarding its ability to improve decision-making processes. Additionally, by leveraging large language models (LLMs), the system offers on-demand explanations of financial terminology through text highlighting and a chat-based interface, further enhancing transparency and user engagement.

Recommender systems (RSs) are designed to help users navigate through large amounts of information by providing personalized suggestions tailored to their preferences. Multi-criteria recommender systems (MCRSs) extend this concept by utilizing users' ratings on multiple aspects of items (i.e., multi-criteria ratings) to predict their overall preferences. Currently, there are several open-source libraries released for RSs. However, none of these existing libraries can handle multi-criteria recommendations due to the special challenges in MCRSs. In this paper, we introduce a Multi-Criteria Recommendation Kit (MCRecKit) which is a Python-based open-source library for multi-criteria recommendations. MCRecKit fills the gap by providing flexible tools and algorithms specifically designed to address the complexity of MCRSs. The library offers a variety of methods for processing, modeling, and evaluating multi-criteria data, enabling researchers and developers to experiment with novel approaches.

Multi-criteria recommender systems can improve the quality of recommendations by considering user preferences on multiple criteria. One promising approach proposed recently is multi-criteria ranking, which uses Pareto ranking to assign a ranking score based on the dominance relationship between predicted ratings across criteria. However, applying Pareto ranking to all criteria may result in non-differentiable ranking scores. To alleviate this issue, we proposed a hybrid multi-criteria ranking method by using subsorting. More specifically, we utilize one ranking method as the major sorting approach, while we apply another preference ordering method as subsorting. Our experimental results on the OpenTable and Yahoo!Movies data present the advantages of this hybrid ranking approach. In addition, the experiments also reveal more insights about the sustainability of the multi-criteria ranking for top-N item recommendations.

The process of financial portfolio optimization involves choosing the most suitable mix of assets to meet a particular investment goal. Conventional portfolio optimization primarily focuses on maximizing returns and minimizing risks while overlooking the importance of social responsibility or sustainability in financial investments. In this paper, we present a Python-based multi-objective portfolio optimization library for sustainable investments (MOPO-LSI). MOPO-LSI is able to take Environmental, Social and Governance (ESG) factors into consideration in financial portfolio, where investors’ assets can be well allocated to mutual funds towards the ESG optimization along with their financial goals in the investment. MOPO-LSI is easy to be configured and used, and it is capable of production solutions in two scenarios – when client preferences are known or unknown. The developers can also easily customize the library to adapt it to their own financial objectives.

Multi-criteria decision making (MCDM) is a popular branch of decision making, where the decision makers need to make a choice based on a number of decision criteria. This process is applicable in various domains of our daily life. For example, a person who is booking a hotel may need to take into account several factors such as location, safety, budget, and room cleanliness. Similarly, a consumer who is placing an order online may consider factors such as budget, quality, functionality, and delivery time. Recommender systems have become a popular solution to assist users in decision making, and these systems can also be developed with multiple criteria and user preferences in mind. This tutorial provides a comprehensive review of MCDM schemes and the development of multi-criteria recommender systems (MCRS). It explores various MCDM solutions and discusses how the current development of MCRS can be linked to these MCDM theories and solutions. The tutorial also highlights the gap between MCDM and the practice of MCRS, which could inspire future development of MCRS.

Multi-criteria recommender systems are capable of enhancing recommendation quality by taking into account user preferences across multiple criteria. A promising approach that has recently emerged is multi-criteria ranking, which employs Pareto ranking to determine a ranking score based on the dominance relation of predicted multi-criteria ratings. While this technique can be integrated with existing MCRS models, the issue of dimensionality remains a challenge. To tackle similar problems, other preference ordering methods have been proposed in the field of multi-objective optimization. This study presents a comparative analysis of preference ordering methods for multicriteria ranking, along with insights obtained from experiments conducted on four real-world datasets.

Financial portfolio optimization is a process of selecting the optimal combination of assets to achieve a specific investment objective. Traditional portfolio optimization may only maximize returns and minimize risks, and ignore social responsibility or sustainability in financial investments. In this paper, we release MOPO-LSI which is a multi-objective portfolio optimization library for sustainable investments. More specifically, MOPO-LSI additionally considers Environmental, Social and Governance (ESG) factors as objectives to be optimized in financial portfolio, where investors' assets can be well allocated to mutual funds towards the improvements in sustainable development and practices. No matter client preferences on ESG factors are unknown or not, MOPO-LSI provides solutions to portfolio optimization in these scenarios. Moreover, MOPO-LSI is easy to be configured and used, and users can also extend its definition of multi-objective problems and adapt the solutions to customized requirements or applications.

Multi-criteria recommender systems can improve the quality of recommendations by considering user preferences on multiple criteria. One promising approach proposed recently is multi-criteria ranking, which uses Pareto ranking to assign a ranking score based on the dominance relationship between predicted ratings across criteria. However, applying Pareto ranking to all criteria may result in non-differentiable ranking scores. To alleviate this issue, we conducted a study on three relaxed Pareto ranking methods for multi-criteria ranking. We evaluated these methods on three real-world datasets and found that the k-dominance ranking approach, which is one of the relaxed Pareto ranking methods, was able to further enhance the ranking performance.

Recommender systems have been widely applied to several domains and applications to assist decision making by recommending items tailored to user preferences. One of the popular recommendation algorithms is the model-based approach which optimizes a specific objective to improve the recommendation performance. These traditional recommendation models usually deal with a single objective, such as minimizing the prediction errors or maximizing the ranking quality of the recommendations. In recent years, there is an emerging demand for multi-objective recommender systems in which multiple objectives are considered and the recommendations can be optimized by the multi-objective optimization. For example, a recommendation model may be built by optimizing multiple metrics, such as accuracy, novelty and diversity of the recommendations. The multi-objective optimization methodologies have been well developed and applied to the area of recommender systems. In this article, we provide a comprehensive literature review of the multi-objective recommender systems. Particularly, we identify the circumstances in which a multi-objective recommender system could be useful, summarize the methodologies and evaluation approaches in these systems, point out existing challenges or weaknesses, finally provide the guidelines and suggestions for the development of multi-objective recommender systems.

The FinRec workshop series offers a central forum for the study and discussion of the domain-specific aspects, challenges, and opportunities of RecSys and other related technologies in the financial services domain. Six years after the second edition of the workshop, the recent advances in the area of personalization and recommendation in financial services fostered the need for a new workshop aiming at bringing together researchers and practitioners working in financial services-related areas. Accordingly, the third edition of the event aims to: (1) understand and discuss open research challenges, (2) provide an overview of existing technologies using recommender systems in the financial services domain, and (3) provide an interactive platform for information exchange between industry and academia.

The development of recommender systems usually deal with single-objective optimizations, such as minimizing prediction errors or maximizing the ranking quality. There is an emerging demand in multi-objective recommendations in which the recommendation list can be generated by optimizing multiple objectives. For example, researchers may balance different evaluation metrics (e.g., accuracy, novelty, diversity) in their models, or consider different objectives in a multi-task recommender. This tutorial provides an overview of the multi-objective optimization and its applications in the area of recommender systems. More specifically, we summarize the multi-objective optimization methods, identify the circumstances in which a multi-objective recommender system could be useful, and point out the challenges in multi-objective recommendations.

A second-order dynamics, tracking-differentiator, is given to generate smooth approximation of the incoming measurement and its derivative, which can be used as the desired trajectory for the control system.