Tripti Mahara

Merging user and item based collaborative filtering to alleviate data sparsity

Memory based algorithms, generally referred as similarity based Collaborative Filtering (CF) algorithm, is one of the most widely accepted approaches to provide service recommendations. It provides personalized and automated suggestions to customers to select variety of products. Memory based algorithms mainly have two kinds of algorithms: User-based and Item-based algorithms. The User-based CF algorithm recommends items by finding similar users. Contrary to User-based CF, an Item-based CF algorithm recommends items by finding similar items. The core of memory based CF technologies is to calculate similarity among users or items. However, due to inherent sparsity, a large number of entries (ratings) in user-item rating matrix are missing. This results in only few available ratings to make prediction for the unknown ratings. This results in poor prediction quality of the CF algorithm. In this paper a hybrid approach is presented that combines user-based CF and item-based CF. It also leverage the biclustering technique to reduce the dimensionality. The biclustering helps to cluster all users/items into several groups. These clusters are then used to measure users/items similarities based on their respective parent groups. To obtain individual prediction, it adopts the user-based and item-based CF schemes based on the computed similarity respectively. Finally it combines the resultant predictions of each model to make final predictions. Interestingly, experiments demonstrated that the proposed approach outperforms the traditional user-based, item-based and some state of the art recommendation approaches in terms of accuracy of prediction and quality of recommendations.

Nearest biclusters collaborative filtering framework with fusion

Abstract Collaborative filtering is one of the widely used recommendation technique. It provides automated and personalized suggestions to consumers for selecting variety of products by examining their preferences. However, sparsity is one of the major weaknesses of this prosperous approach. This problem inherently occurs in the system due to ever increasing number of users and items. This affects the performance of a recommender system as the accuracy of prediction decreases. Thus, there is a need for a technique that can perform efficiently under sparse environment and this work proposes one such technique. The memory based CF techniques can be user-based or item based. In both cases, the user-item rating matrix can provide only partial information to predict unknown ratings. This is due to the sparsity inherent to rating data. Hence, we propose to fuse the item-based CF and user-based CF. Subsequently, Neighborhood formation is a crucial step in Collaborative filtering technique. Therefore, this paper adopts the biclustering approach for neighborhood formation. This approach, allows a degree of overlap between biclusters (i.e. a user or item is included in more than one clusters). Therefore, a new similarity measure is proposed that obtains a bicluster that has strong partial similarity with an active users’ preferences. Experimental results demonstrate that proposed approach generates better accuracy of rate prediction compared to the tradition item-based, user-based and some state of the art approaches.

An exploratory study to investigate value chain of Saharanpur wooden carving handicraft cluster

Wooden carved handicraft is one of the popular and well known handicrafts of India. SRE is one of the dominant clusters along with Jodhpur and Mysore that are known for their wooden carvings. It is a labor intensive sector and the skills are usually passed from one generation to another. The wooden carving sector is undergoing considerable changes because of ever growing global competition, economic developments and technological advancements. This paper investigates value chain of wooden carving handicraft cluster of Saharanpur and presents various issues and challenges faced by this cluster. The study was accomplished by field visits, interviews with stakeholders and observations. On the basis of this study suitable recommendations and suggestions for cluster and its units have been proposed to overcome growth barriers.

Preliminary Study of E-commerce Adoption in Indian Handicraft SME: A Case Study

Small and medium enterprises (SME) play a vital role in Indian economy. It is crucial for a SME to innovate if it wants to thrive in the competitive environment. Adopting e-commerce as a sales channel is one of the ways to increase customer base for an organization. This paper investigates the reasons why small and medium size enterprises employed in handicraft sector move from traditional commerce to e-commerce through case study based approach. The research methodology involved interviews with owner and employee/s. The findings were assessed using technology-organization and environment (TOE) framework. The results reveal that the owner had a crucial and important role in e-commerce adoption by a SME. It is the willingness of the owner to innovate that opens the new sales channel for a SME. The importance of good infrastructure becomes a driver for e-commerce adoption.

Interactions and Participation on Social Commerce Websites: Exploratory Study

An increasing number of organizations are adopting social commerce (SC) to engage and occupy customers in product development, sales and support activities. Therefore, it is imperative for retailers and marketers to know customers’ adoption behaviour towards SC websites and the benefits they gain through voluntary contribution of information on these websites. The study attempts to identify customer participation through development of a conceptual framework based on the uses and gratification (UG) approach. The importance of non-altruistic motives, that is, benefits shape member’s participation on SC websites, is confirmed by results. According to the results, two interaction characteristics, that is, human interactivity and member identity are essential for building trust in SC website. Findings of the study also conclude that interaction characteristics strongly affect three benefits, that is, personal integrative, social integrative and hedonic. Hence, it is implied that benefits gained by members on SC website interactions shape their participation intentions. Therefore, SC websites must be designed keeping in view both usage and benefits by members.

Fuzzy logic based similarity measure for multimedia contents recommendation

Collaborative filtering is one of the mainstream approaches to provide recommendations in various online environments such as Ecommerce. Although this is a popular method for service recommendation, it still suffers from sparsity issue where only a small number of rating records are available for some new items or users in the system. Consequently, the accuracy of rate prediction is often compromised. Unlike the conventional collaborative filtering methods that directly compute the similarity between users, this paper presents a fuzzy logic based approach to refine the similarity obtained using traditional approaches like Pearson correlation, Cosine, Adjusted Cosine etc. Experiments were conducted on the two popular benchmark datasets and it shows that the proposed method obtains better prediction accuracy as compare to other traditional similarity measures.

An Empirical Study of Consumers Intention to Purchase Wooden Handicraft Items Online: Using Extended Technology Acceptance Model:

Handicraft is one of the many productive sectors for developing countries. It contributes significantly towards economic growth. This study seeks to investigate consumers’ perception towards purchase of wooden handicraft items through e-commerce platform. The proposed extended technology acceptance model investigates the role of website quality, service and product perception on consumers purchase intention towards wooden handicraft items online. Trust acts as a mediator to study its effect on consumer intention. The effect of website quality, service and product perception was analyzed for the technology acceptance model constructs, namely perceived ease of use and perceived usefulness. A total of 234 respondents were surveyed and data was analyzed using structural equation modelling technique. Service perception and product perception determine perceived usefulness whereas perceived ease of use is determined by website quality and service perception. The results show that trust has positive role in determining consumers’ purchase intention. Website quality, service and product perception determine trust, and they build consumers’ confidence in online shopping. Both seller and website should have effective strategies to build consumers’ trust. The research suggests that sellers can significantly surge consumers’ trust by improvising product and service perception, whereas the website can ensure consumers’ trust by increasing the quality of website and service perception.

LeaderRank based k -means clustering initialization method for collaborative filtering

Abstract Collaborative filtering based Recommender System is one of the most common technique used for personalized product ranking. It aids the consumer in decision-making process. It helps to choose a product according to the consumers preference from a large pool of choices.Despite its success, collaborative filtering suffers from the sparsity problem which limits the quality of recommendations. In this paper, we investigate the application of clustering collaborative framework. A unique centroid selection approach for k-means clustering algorithm is proposed that aims to improve clustering quality. The results on three benchmark datasets depict the improvement in the quality of recommendations made.