scispace - formally typeset
Proceedings ArticleDOI: 10.1109/ICDIPC.2015.7323046

Adaptive Commodity Suggestion System — Match-BOT

01 Oct 2015-pp 306-311
Abstract: Potential customers of E-commerce garment businesses purchase clothes based on their personal choice as well as contemporary perception about fashion trends which is highly sublime in nature. This, coupled with the influential influx of cinema, social media and the Internet has led to rapid change in dressing preferences. E-commerce sites have a huge inventory categorized based on different attributes like colour, fabric, fit, product type and vendor. Hence, it is a tedious task for the user to find products coherent with the latest trend and appropriate according to their personal taste and global trends. The recommendation engines of these websites gives recommendations based only on a linear similarity of products, not comprehensively taking into account latest trends in fashion backed by fashion specialists, user preference or wardrobe collections. We propose an Adaptive Commodity Suggestion System called ”Match-BOT” which takes into account the trends obtained through insights provided by Google Trends, individual preferences, and similarity between user preferences. The user preferences are extracted by analyzing user purchase patterns and thus obtaining categorised product attribute preferences in the form of weights. This is an application of Content Based Learning The global trend obtained from Google Trends is then overlapped with the user preference and a user specific suggestion list is generated. The similarity between two user is calculated using Collaborative Filtering and then taken into account by including cross-user suggestions based on the degree of correlation. The output of this process would be in the form of list of suggestions of products which have been customized to society's understanding of fashion and predilections of the user and constantly updated to reflect dynamic global trends. This would result in an unparalleled browsing experience for the user and an efficient sales and successive inventory management systems.

...read more

Topics: Collaborative filtering (50%)
References
  More

Open accessProceedings ArticleDOI: 10.1145/371920.372071
01 Apr 2001-
Abstract: Recommender systems apply knowledge discovery techniques to the problem of making personalized recommendations for information, products or services during a live interaction. These systems, especially the k-nearest neighbor collaborative ltering based ones, are achieving widespread success on the Web. The tremendous growth in the amount of available information and the number of visitors to Web sites in recent years poses some key challenges for recommender systems. These are: producing high quality recommendations, performing many recommendations per second for millions of users and items and achieving high coverage in the face of data sparsity. In traditional collaborative ltering systems the amount of work increases with the number of participants in the system. New recommender system technologies are needed that can quickly produce high quality recommendations, even for very large-scale problems. To address these issues we have explored item-based collaborative ltering techniques. Item-based techniques rst analyze the user-item matrix to identify relationships between di erent items, and then use these relationships to indirectly compute recommendations for users. In this paper we analyze di erent item-based recommendation generation algorithms. We look into di erent techniques for computing item-item similarities (e.g., item-item correlation vs. cosine similarities between item vectors) and di erent techniques for obtaining recommendations from them (e.g., weighted sum vs. regression model). Finally, we experimentally evaluate our results and compare them to the basic k-nearest neighbor approach. Our experiments suggest that item-based algorithms provide dramatically better performance than user-based algorithms, while at the same time providing better quality than the best available userbased algorithms.

...read more

Topics: Collaborative filtering (62%), Recommender system (61%), Slope One (59%) ...read more

7,756 Citations


Journal ArticleDOI: 10.1023/A:1009804230409
Abstract: i>Recommender systems are being used by an ever-increasing number of E-commerce sites to help consumers find products to purchase. What started as a novelty has turned into a serious business tool. Recommender systems use product knowledge—either hand-coded knowledge provided by experts or “mined” knowledge learned from the behavior of consumers—to guide consumers through the often-overwhelming task of locating products they will like. In this article we present an explanation of how recommender systems are related to some traditional database analysis techniques. We examine how recommender systems help E-commerce sites increase sales and analyze the recommender systems at six market-leading sites. Based on these examples, we create a taxonomy of recommender systems, including the inputs required from the consumers, the additional knowledge required from the database, the ways the recommendations are presented to consumers, the technologies used to create the recommendations, and the level of personalization of the recommendations. We identify five commonly used E-commerce recommender application models, describe several open research problems in the field of recommender systems, and examine privacy implications of recommender systems technology.

...read more

Topics: Recommender system (62%), Personalization (59%)

1,602 Citations


Open accessPosted Content
Raymond J. Mooney1, Loriene Roy1Institutions (1)
Abstract: Recommender systems improve access to relevant products and information by making personalized suggestions based on previous examples of a user's likes and dislikes. Most existing recommender systems use social filtering methods that base recommendations on other users' preferences. By contrast, content-based methods use information about an item itself to make suggestions. This approach has the advantage of being able to recommended previously unrated items to users with unique interests and to provide explanations for its recommendations. We describe a content-based book recommending system that utilizes information extraction and a machine-learning algorithm for text categorization. Initial experimental results demonstrate that this approach can produce accurate recommendations.

...read more

1,268 Citations


Open accessProceedings ArticleDOI: 10.1145/336597.336662
Raymond J. Mooney1, Loriene Roy1Institutions (1)
01 Jun 2000-
Abstract: Recommender systems improve access to relevant products and information by making personalized suggestions based on previous examples of a user's likes and dislikes. Most existing recommender systems use collaborative filtering methods that base recommendations on other users' preferences. By contrast,content-based methods use information about an item itself to make suggestions.This approach has the advantage of being able to recommend previously unrated items to users with unique interests and to provide explanations for its recommendations. We describe a content-based book recommending system that utilizes information extraction and a machine-learning algorithm for text categorization. Initial experimental results demonstrate that this approach can produce accurate recommendations.

...read more

Topics: Recommender system (61%), Collaborative filtering (59%), Information filtering system (55%) ...read more

1,246 Citations


Book ChapterDOI: 10.1007/978-3-642-00296-0_5
01 Jan 2009-
Topics: Interclass correlation (75%), Fisher transformation (72%), Correlation ratio (70%) ...read more

910 Citations


Network Information