Search Results (172)

Cloud computing has increasingly adopted multi-tenant infrastructures to enhance cost efficiency and resource utilization by enabling the shared use of computational resources. However, this shared model introduces several security and privacy concerns, including unauthorized access, data redundancy, and susceptibility to malicious activities. In such environments, the effectiveness of cloud-based recommendation systems largely depends on the trustworthiness of participating nodes. Traditional collaborative filtering techniques often suffer from limitations such as data sparsity and the cold-start problem, which significantly degrade rating prediction accuracy. To address these challenges, this study proposes a Trusted Graph-Based Collaborative Filtering Recommender System (TGBCF). The model integrates graph-based trust relationships with collaborative filtering to construct a trust-aware user network capable of generating reliable service recommendations. Each node’s reliability is quantitatively assessed using a trust metric, thereby improving both the accuracy and robustness of the recommendation process. Simulation results show that TGBCF achieves a rating prediction accuracy of 93%, outperforming the baseline collaborative filtering approach (82%). Moreover, the model reduces the influence of malicious nodes by 40–60%, demonstrating its applicability in dynamic and security-sensitive cloud service environments. Full article

The cold-start problem remains a critical challenge in personalized advertising, where users with limited or no interaction history often receive suboptimal recommendations. This study introduces a novel, three-stage framework that systematically integrates transformer architectures and large language models (LLMs) to improve recommendation accuracy, transparency, and user experience throughout the entire advertising pipeline. The proposed approach begins with transformer-enhanced feature extraction, leveraging self-attention and learned positional encodings to capture deep semantic relationships among users, ads, and context. It then employs an ensemble integration strategy combining enhanced state-of-the-art models with optimized aggregation for robust prediction. Finally, an LLM-driven enhancement module performs semantic reranking, personalized message refinement, and natural language explanation generation while also addressing cold-start scenarios through pre-trained knowledge. The LLM component further supports diversification, fairness-aware ranking, and sentiment sensitivity in order to ensure more relevant, diverse, and ethically grounded recommendations. Extensive experiments on DigiX and Avazu datasets demonstrate notable gains in click-through rate prediction (CTR), while an in-depth real user evaluation showcases improvements in perceived ad relevance, message quality, transparency, and trust. This work advances the state-of-the-art by combining CTR models with interpretability and contextual reasoning. The strengths of the proposed method, such as its innovative integration of components, empirical validation, multifaceted LLM application, and ethical alignment highlight its potential as a robust, future-ready solution for personalized advertising. Full article

Achieving optimal agricultural yields and promoting sustainable farming relies on accurate crop recommendations. However, the applicability of many current systems is limited by their considerable computational requirements and dependence on comprehensive datasets, especially in resource-limited contexts. This paper presents HOLISTIQ RS, a novel crop recommendation system explicitly designed for operation on low-specification hardware and in data-scarce regions. HOLISTIQ RS combines collaborative filtering with a Markov model to predict appropriate crop choices, drawing upon user profiles, regional agricultural data, and past crop performance. Results indicate that HOLISTIQ RS provides a significant increase in recommendation accuracy, achieving a MAP@5 of 0.31 and nDCG@5 of 0.41, outperforming standard collaborative filtering methods (the KNN achieved MAP@5 of 0.28 and nDCG@5 of 0.38, and the ANN achieved MAP@5 of 0.25 and nDCG@5 of 0.35). Significantly, the system also demonstrates enhanced recommendation diversity, achieving an Item Variety (IV@5) of 23%, which is absent in deterministic baselines. Significantly, the system is engineered for reduced energy consumption and can be deployed on low-cost hardware. This provides a feasible and adaptable method for encouraging informed decision-making and promoting sustainable agricultural practices in areas where resources are constrained, with an emphasis on lower energy usage. Full article

In the recommendation system (RS) literature, a distinction exists between studies dedicated to fully operational (known users/items) and cold-start (new users/items) RSs. The warm-up phase—the transition between the two—is not widely researched, despite evidence that attrition rates are the highest for users and content providers during such periods. RS formulations, particularly deep learning models, do not easily allow for a warm-up phase. Herein, we propose two independent and complementary models to increase RS performance during the warm-up phase. The models apply to any cold-start RS expressible as a function of all user features, item features, and existing users’ preferences for existing items. We demonstrate substantial improvements: Accuracy-oriented metrics improved by up to 14% compared with not handling warm-up explicitly. Non-accuracy-oriented metrics, including serendipity and fairness, improved by up to 12% compared with not handling warm-up explicitly. The improvements were independent of the cold-start RS algorithm. Additionally, this paper introduces a method of examining the performance metrics of an RS during the warm-up phase as a function of the number of user–item interactions. We discuss problems such as data leakage and temporal consistencies of training/testing—often neglected during the offline evaluation of RSs. Full article

To address the limitations of existing knowledge graph-based recommendation algorithms, including insufficient utilization of semantic information and inadequate modeling of user behavior motivations, we propose SKGRec, a novel recommendation model that integrates knowledge graph and semantic features. The model constructs a semantic interaction graph (USIG) of user behaviors and employs a self-attention mechanism and a ranked optimization loss function to mine user interactions in fine-grained semantic associations. A relationship-aware aggregation module is designed to dynamically integrate higher-order relational features in the knowledge graph through the attention scoring function. In addition, a multi-hop relational path inference mechanism is introduced to capture long-distance dependencies to improve the depth of user interest modeling. Experiments on the Amazon-Book and Last-FM datasets show that SKGRec significantly outperforms several state-of-the-art recommendation algorithms on the Recall@20 and NDCG@20 metrics. Comparison experiments validate the effectiveness of semantic analysis of user behavior and multi-hop path inference, while cold-start experiments further confirm the robustness of the model in sparse-data scenarios. This study provides a new optimization approach for knowledge graph and semantic-driven recommendation systems, enabling more accurate capture of user preferences and alleviating the problem of noise interference. Full article

Serverless computing has gained significant attention in recent years. However, the cold start problem remains a major challenge, not only because of the substantial latency it introduces to function execution time, but also because frequent cold starts lead to poor resource utilization, especially during workload fluctuations. To address these issues, we propose a multi-level scheduling solution: the Hybrid Model. This model is designed to reduce the frequency of cold starts while maximizing container utilization. At the global level (across invokers), the Hybrid Model employs a skewness-aware scheduling strategy to select the most appropriate invoker for each request. Within each invoker, we introduce a greedy buffer-aware scheduling method that leverages the available slack (remaining buffer) of warm containers to aggressively encourage their reuse. Both the global and the local schedule are tightly integrated with a prediction component- The Hybrid Predictor- that combines Auto-Regressive Integrated Moving Average ARIMA (linear trends) and Random Forest (non-linear residuals + environment-aware features) for 5-min workload forecasts. The Hybrid Model is implemented on Apache OpenWhisk and evaluated using Azure-like traces and real FaaS applications. The evaluations show that the Hybrid Model achieves up to 34% SLA violation reductions compared to three state-of-the-art approaches and maintains the container utilization to be more than 80%. Full article

Delivering compelling presentations is a critical skill across academic, professional, and public domains—yet many presenters struggle with structuring content, maintaining visual consistency, and engaging their audience effectively. Existing tools offer isolated support for design or delivery but fail to promote long-term skill development. This paper presents a novel intelligent application, the Presentation Advisor application, powered by a personalized recommendation engine that goes beyond fixing slide content and visualization, enabling users to build presentation competence. The recommendation engine leverages a model based on hybrid multi-tower neural network architecture enhanced with temporal encoding, problem sequence modeling, and utility-based scoring to deliver adaptive context-aware feedback. Unlike current tools, the presented system analyzes user-submitted presentations to detect common issues and delivers curated educational content tailored to user preferences, presentation types, and audiences. The system also incorporates strategic cold-start mitigation, ensuring high-quality recommendations even for new users or unseen content. Comprehensive experimental evaluations demonstrate that the suggested model significantly outperforms content-based filtering, collaborative filtering, autoencoders, and reinforcement learning approaches across both accuracy and personalization metrics. By combining cutting-edge recommendation techniques with a pedagogical framework, the Presentation Advisor application enables users not only to improve individual presentations but to become consistently better presenters over time. Full article

A large number of bug reports are submitted by users and developers in bug-tracking system every day. It is time-consuming for software maintainers to assign bug reports to appropriate developers for fixing manually. Many bug-triaging methods have been developed to automate this process. However, most previous studies mainly focused on analyzing textual content and failed to make full use of the structured information embedded in the bug-tracking system. In fact, this structured information, which plays an important role in bug triaging, reflects the process of bug tracking and the historical activities. To further improve the performance of automatic bug triaging, in this study, we propose a new representation learning model, PTITransE, for knowledge bases, which extends TransE via enhancing the embeddings with textual entity descriptions and is more suitable for bug triaging. Moreover, we make the first attempt to apply knowledge base and link prediction techniques to bug triaging. For each new bug report, the proposed framework can recommend top-k developers for fixing the bug report by using the learned embeddings of entities and relations. Evaluation is performed on three real-world projects, and the results indicate that our method outperforms baseline bug triaging approaches and can alleviate the cold-start problem in bug triaging. Full article

Hyperparameter Optimization (HPO) is an important and challenging problem in machine learning. Traditional HPO methods require substantial evaluations to search for superior configurations. Recent Large Language Model (LLM)-based approaches leverage domain knowledge and few-shot learning proficiency to discover promising configurations with minimal human effort. However, the repetition issues causes LLMs to generate configurations similar to context examples, which may confine the optimization process to local regions. Moreover, since LLMs rely on the examples they generate for a few-shot learning, a self-reinforcing loop is formed, hindering LLMs from escaping local optima. In this work, we propose EvoContext, which aims to intentionally generate configurations that differ significantly from examples via external interventions and actively breaks the self-reinforcing effect for a more efficient approximation of the global optimum. Our EvoContext method involves two phases: (i) initial example generation through cold or warm starting and (ii) iterative optimization that integrates genetic operations for updating examples to enhance global exploration capabilities. Additionally, it employs LLMs in-context learning to generate configurations based on competitive examples for local refinement. Experiments on several real-world datasets show that EvoContext outperforms traditional and other LLM-driven approaches on HPO. Full article

Trust management provides an alternative solution for securing open, dynamic, and distributed multi-agent systems, where conventional cryptographic methods prove to be impractical. However, existing trust models face challenges such as agent mobility, which causes agents to lose accumulated trust when moving across networks; changing behaviors, where previously reliable agents may degrade over time; and the cold start problem, which hinders the evaluation of newly introduced agents due to a lack of prior data. To address these issues, we introduced a biologically inspired trust model in which trustees assess their own capabilities and store trust data locally. This design improves mobility support, reduces communication overhead, resists disinformation, and preserves privacy. Despite these advantages, prior evaluations revealed the limitations of our model in adapting to provider population changes and continuous performance fluctuations. This study proposes a novel algorithm, incorporating a self-classification mechanism for providers to detect performance drops that are potentially harmful for service consumers. The simulation results demonstrate that the new algorithm outperforms its original version and FIRE, a well-known trust and reputation model, particularly in handling dynamic trustee behavior. While FIRE remains competitive under extreme environmental changes, the proposed algorithm demonstrates greater adaptability across various conditions. In contrast to existing trust modeling research, this study conducts a comprehensive evaluation of our model using widely recognized trust model criteria, assessing its resilience against common trust-related attacks while identifying strengths, weaknesses, and potential countermeasures. Finally, several key directions for future research are proposed. Full article

Forecasting demand for newly introduced products presents substantial challenges within high-mix, low-volume manufacturing contexts, primarily due to cold-start conditions and unpredictable order behavior. This research proposes the Dynamic Dual-Phase Forecasting Framework (DDPFF) that amalgamates machine learning-based classification, similarity-driven analogous forecasting, ARMA-based residual compensation, and statistical process control for adaptive model refinement. The framework underwent evaluation through five real-world case studies conducted by a Taiwanese semiconductor tray manufacturer, encompassing a variety of scenarios characterized by high volatility, seasonality, and structural drift. The results indicate that DDPFF consistently outperformed conventional ARIMA and analogous forecasting methodologies, yielding an average reduction of 35.7% in mean absolute error and a 41.8% enhancement in residual stability across all examined cases. In one representative instance, the forecast error decreased by 44.9% compared to established benchmarks. These findings underscore the framework’s resilience in cold-start situations and its capacity to adapt to evolving demand patterns, providing a viable solution for data-scarce and dynamic manufacturing environments. Full article

Recommendation systems (RSs) play a vital role in e-commerce and content platforms, yet balancing efficiency and recommendation quality remains challenging. Traditional deep models are computationally expensive, while heuristic methods like particle swarm optimization struggle with discrete optimization. To address these limitations, this paper proposes elite-evolution-based discrete particle swarm optimization (EEDPSO), a novel framework specifically designed to optimize high-dimensional combinatorial recommendation tasks. EEDPSO restructures the velocity and position update mechanisms to operate effectively in discrete spaces, integrating neighborhood search, elite evolution strategies, and roulette-wheel selection to balance exploration and exploitation. Experiments on the MovieLens and Amazon datasets show that EEDPSO outperforms five metaheuristic algorithms (GA, DE, SA, SCA, and PSO) in both recommendation quality and computational efficiency. For datasets below the million-level scale, EEDPSO also demonstrates superior performance compared to deep learning models like FairGo. The results establish EEDPSO as a robust optimization strategy for recommendation systems that effectively handles the cold-start problem. Full article

The cold-start problem remains a significant challenge in recommendation systems, particularly in scenarios involving new users or items with insufficient historical interaction data, which severely limits the effectiveness of personalised recommendations. Despite extensive research efforts dedicated to addressing this issue, existing meta-learning approaches, while promising, often rely on the assumption that prior knowledge can be globally shared across all users. This assumption overlooks the inherent inefficiency of information sharing due to diverse user interests, frequently resulting in suboptimal solutions and constrained model performance. To address this limitation, we propose an enhanced meta-learning framework that leverages graph community detection algorithms to cluster users, enabling the extraction of unique prior knowledge within each cluster. This knowledge is then shared efficiently among users with similar interests within the same cluster. Through comparative experiments on cold-start recommendation tasks, our proposed model demonstrates superior performance over traditional methods, validating its effectiveness in improving cold-start recommendation accuracy. Furthermore, this study highlights potential application scenarios and future research directions for advancing cold-start solutions in recommendation systems. Full article

With the flourishing of social media platforms, data in social networks, especially user-generated content, are growing rapidly, which makes it hard for users to select relevant content from the overloaded data. Recommender systems are thus developed to filter user-relevant content for better user experiences and also the commercial needs of social platform providers. Graph neural networks have been widely applied in recommender systems for better recommendation based on past interactions between users and corresponding items due to the graph structure of social data. Users might also be influenced by their social connections, which is the focus of social recommendation. Most works on recommendation systems try to obtain better representations of user embeddings and item embeddings. Compared with recommendation systems only focusing on interaction graphs, social recommendation has an additional task of combining user embedding from the social graph and interaction graph. This paper proposes a new method called SocialJGCF to address these problems, which applies Jacobi-Polynomial-Based Graph Collaborative Filtering (JGCF) to the propagation of the interaction graph and social graph, and a graph fusion is used to combine the user embeddings from the interaction graph and social graph. Experiments are conducted on two real-world datasets, epinions and LastFM. The result shows that SocialJGCF has great potential in social recommendation, especially for cold-start problems. Full article

Given the daily influx of scientific publications, researchers often face challenges in identifying relevant content amid the vast volume of available information, typically resorting to conventional methods like keyword searches or manual browsing. Utilizing a dataset comprising 1895 users and 3122 articles from the CI&T Deskdrop collection, as well as 7947 users and 25,975 articles from CiteULike-t, we examine the effectiveness of collaborative filtering and content-based and hybrid recommendation approaches in scientific literature recommendations. These methods automatically generate article suggestions by analyzing user preferences and historical behavior. Our findings, evaluated based on accuracy (Precision@K), ranking quality (NDCG@K), and novelty, reveal that the hybrid approach significantly outperforms other methods, tackling some challenges such as cold starts and sparsity problems. This research offers theoretical insights into recommendation model effectiveness and practical implications for developing tools that enhance content discovery and researcher productivity. Full article