Improvising the performance of image-based recommendation system using convolution neural networks and deep learning
- PDF / 2,585,123 Bytes
- 14 Pages / 595.276 x 790.866 pts Page_size
- 16 Downloads / 249 Views
(0123456789().,-volV)(0123456789(). ,- volV)
METHODOLOGIES AND APPLICATION
Improvising the performance of image-based recommendation system using convolution neural networks and deep learning A. Razia Sulthana1 • Maulika Gupta2 • Shruthi Subramanian3 • Sakina Mirza4
Springer-Verlag GmbH Germany, part of Springer Nature 2020
Abstract Recommendation systems now hold special significance, for in a world full of choices, order is the need of the hour. Without proper sorting, the gift of choice means nothing. The online retail world is fast-paced and ever-growing. With the exponential waning of attention span, it has become crucial to convert a casual visitor into a buyer within a limited window. Different ways can be used to do this: analysing buying patterns, surveys, user–user relationships, user-item relationships, and so on. This can be done with simple data analysis or with complex algorithms—the data must be harnessed one way or another. Deep learning is a branch of machine learning that has now become synonymous with computer vision, as these deep architectures closely emulate the biological process of vision. In this paper, the primary focus is the incorporation of a recommendation system with the visual features of products. This is done with the help of a deep architecture and a series of ‘‘convolution’’ operations that cause the overlapping of edges and blobs in images. We find that when the dimensionality problem has been dealt with, the features extracted serve as good quality representations of the images. Our empirical study compares the different linear and nonlinear reduction techniques on convolutional neural network features for building a recommendation model entirely based on the images. Keywords Deep learning Convolution neural network Recommendation system Dimensionality reduction Tensor flow
1 Introduction
Communicated by V. Loia. & A. Razia Sulthana [email protected] Maulika Gupta [email protected] Shruthi Subramanian [email protected] Sakina Mirza [email protected] 1
BITS Pilani-Dubai, Dubai, United Arab Emirates
2
Organization for the Prohibition of Chemical Weapons, The Hague, Netherlands
3
Miami Ad School Europe, Berlin, Germany
4
Grenoble Ecole De Management, Berlin, Germany
With the advent of technology and competition in the market, consumers are blessed with a myriad of options to choose from. However, this premature blessing can turn out to be a bane. ‘Information overload’ calls for filtering and organizing these options for consumers; hence—recommendation systems. The image of the product is the first thing that catches one’s eye; thus, it would be intuitive to deem pictorial representation as the gold standard for analysing the ‘content’ of the product. While image representation has been considered to be an issue in the past, convolutional neural network or CNN (a deep learning architecture)—what was once a simple 5-layer network for character recognition (LeCun et al. 1998), has now evolved into a network that has effectively simp
Data Loading...
