COLD START PROBLEM IN RECOMMENDING CLOUD SERVICES: A SURVEY

2002

Abstract We have developed a method for recommending items that combines content and collaborative data under a single probabilistic framework. We benchmark our algorithm against a naïve Bayes classifier on the cold-start problem, where we wish to recommend items that no one in the community has yet rated. We systematically explore three testing methodologies using a publicly available data set, and explain how these methods apply to specific real-world applications.

In the ecommerce services, there is a very important tool that will determine the success to increase number of buying and selling in the marketing target, that is how the user in finding products that are suitable to be purchased. This tool is called recommender system. Recommender system is important tool for establishing an effective communication between users and retailers in ecommerce business. Effective and enjoyable communication to find the product is considered to have a significant impact that increase of marketing achievement. Recommender system established in the mid-90s. Based on technical approach, there are four types of recommender system namely Collaborative, Contents Based, Knowledge Based and Demographic filtering. Collaborative filtering is considered to be more superior than another two methods. It offers obviously advantages in terms of serendipity, novelty and accuracy. Although it has some benefit. However, there is a critical problem in collaborative filtering that called cold start. It is a major problem to which many researchers have paid much more attention to this particular research interest. In response to this particular problem the critical review and analysis on state of the art of the current technology, some possible solutions including approach, method and techniques used have been identified but they need further validation.

Cluster Computing, 2016

The rapid growth of published cloud services in the Internet makes the service selection and recommendation a challenging task for both users and service providers. In cloud environments, software re services collaborate with other complementary services to provide complete solutions to end users. The service selection is performed based on QoS requirements submitted by end users. Software providers alone cannot guarantee users' QoS requirements. These requirements must be end-to-end, representing all collaborating services in a cloud solution. In this paper, we propose a prediction model to compute end-to-end QoS values for vertically composed services which are composed of three types of cloud services: software (SaaS), infrastructure (IaaS) and data (DaaS) services. These values can be used during the service selection and recommendation process. Our model exploits historical QoS values and cloud service and user information to predict unknown end-to-end QoS values of composite services. The experiments demonstrate that our proposed model outperforms other prediction models in terms of the prediction accuracy. We also study the impact of different parameters on the prediction results. In the experiments, we used real cloud services' QoS data collected using our developed QoS monitoring and collecting system.

2010 5th International Symposium on Telecommunications, 2010

Recommender systems have become significant tools in electronic commerce, proposing effectively those items that best meet the preferences of users. A variety of techniques have been proposed for the recommender systems such as, collaborative filtering and content-based filtering. This study proposes a new hybrid recommender system that focuses on improving the performance under the "new user cold-start" condition where existence of users with no ratings or with only a small number of ratings is probable. In this method, the optimistic exponential type of ordered weighted averaging (OWA) operator is applied to fuse the output of five recommender system strategies. Experiments using MovieLens dataset show the superiority of the proposed hybrid approach in the cold-start conditions.

Recommending new items is an important, yet challenging problem due to the lack of preference history for the new items. To handle this problem, the existing system uses the popular core techniques like collaborative filtering, content-based filtering and combinations of these. In this paper, we propose a market-based approach for seeding recommendations for new items in which new items will reach the audience quickest. To support this approach we purposed the algorithm that match the new item specification (features) with the existing item and identify whether these features are available in existing item sets or not. The proposed system identifies the user opinion on new item feature those are available in existing item set and generates the quality report of newly launched item (which is not purchased yet).

Proceedings of the 37th international ACM SIGIR conference on Research & development in information retrieval, 2014

Cold start is one of the most challenging problems in recommender systems. In this paper we tackle the cold-start problem by proposing a context-aware semi-supervised co-training method named C-SEL. Specifically, we use a factorization model to capture finegrained user-item context. Then, in order to build a model that is able to boost the recommendation performance by leveraging the context, we propose a semi-supervised ensemble learning algorithm. The algorithm constructs different (weak) prediction models using examples with different contexts and then employs the cotraining strategy to allow each (weak) prediction model to learn from the other prediction models. The method has several distinguished advantages over the standard recommendation methods for addressing the cold-start problem. First, it defines a fine-grained context that is more accurate for modeling the user-item preference. Second, the method can naturally support supervised learning and semi-supervised learning, which provides a flexible way to incorporate the unlabeled data. The proposed algorithms are evaluated on two real-world datasets. The experimental results show that with our method the recommendation accuracy is significantly improved compared to the standard algorithms and the cold-start problem is largely alleviated.

Journal of emerging technologies and innovative research, 2020

Recommender systems have to deal with cold start problems as new users and new items are always present, where systems are unable to recommend relevant items to the users due to the unavailability of adequate information about them. In literature, many researchers have addressed this problem by collecting missing information, but their approaches differ in the way they collect missing information. This paper tries to propose a concept to solve the cold start problem by combing collaborative filtering, demographic approach, and click steam visit count.

IJCSIS Vol 18 No. 1 January Issue, 2020

Recommender systems for suggesting items of interest to users have become progressively vital in variety of applications where users’ customization is valued. One of the widespread core methods of such systems is collaborative filtering. Data sparsity and cold start problem are the major limitations in Collaborative filtering. These two limitations are linked in a way that due to data sparsity (missing or no ratings) a new item fails to be recommended (cold-start). In this work, we have attempted to contribute in Recommender Systems by proposing a novel matrix factorization method by considering implicit item relationships based on item-similarity. This paper attempts to propose a solution to the cold start problem by combining association rules and clustering technique.

Indonesian Journal of Electrical Engineering and Computer Science

Recommendation systems (RSs) are used to obtain advice regarding decision-making. RSs have the shortcoming that a system cannot draw inferences for users or items regarding which it has not yet gathered sufficient information. This issue is known as the cold start issue. Aiming to alleviate the user’s cold start issue, the proposed recommendation algorithm combined tag data and logistic regression classification to predict the probability of the movies for a new user. First using alternating least square to extract product feature, and then diminish the feature vector by combining principal component analysis with logistic regression to predict the probability of genres of the movies. Finally, combining the most relevant tags based on similarity score with probability and find top N movies with high scores to the user. The proposed model is assessed using the root mean square error (RMSE), the mean absolute error (MAE), recall@N and precision@N and it is applied to 1M, 10M and 20M M...

Applied Sciences, 2021

Recommender systems suggest items of interest to users based on their preferences. These preferences are typically generated from user ratings of the items. If there are no ratings for a certain user or item, it is said that there is a cold start problem, which leads to unreliable recommendations. Existing studies that reviewed and examined cold start in recommender systems have not explained the process of deriving and obtaining the auxiliary information needed for cold start recommendation. This study surveys the existing literature in order to explain the various approaches and techniques employed by researchers and the challenges associated with deriving and obtaining the auxiliary information necessary for cold start recommendation. Results show that auxiliary information for cold start recommendation is obtained by adapting traditional filtering and matrix factorization algorithms typically with machine learning algorithms to build learning prediction models. The understanding...