Page 1 of 8

European Journal of Business &

Social Sciences

Available at https://ejbss.org/

ISSN: 2235-767X

Volume 07 Issue 03

March 2019

Available online: https://ejbss.org/ P a g e | 266

A Novel Method for Connecting E-Commerce to Social

Media using Micro blogging Information

Ch.Venkateswarlu#1 Guvvala Sravanthi#2

#1 Assistant Professor, Dept of CSE, Visvodaya Engineering College,

Kavali,India

#2Studnet, Dept of Master of Computer Application (MCA), PBR

Visvodaya Institute Of Technology And Science, Kavali,India

ABSTRACT:

In last few years, the bounds between ecommerce and social networking have

turn out to be increasingly blurred. it is possible to access many Ecommerce websites

by using users social network accounts like facebook, twitter etc. Users of social

networks can able to post their newly purchased products in the micro blogs, and can

give links to the Ecommerce web pages from where they are purchased. In this paper

we have a tendency to propose a unique answer for cross-site cold-start product

recommendation that aims to advocate product from ecommerce websites to users at

social networking sites in “coldstart” things, a haul that has seldom been explored

before. A serious challenge is the way to leverage data extracted from social

networking sites for cross-site cold-start product recommendation. This paper

proposes, by using neural networks extract user features or user embeddings and

product feature or product embedding’s from the data collected from Ecommerce

websites. Then by using gradient boosting tree method on the social networking sites,

collect user features and combine this with the user embeddings. Then by using

matrix factorization method use these user embedding’s for the cold start product

recommendation. Keywords:- e-commerce, product recommender, product

demographic, microblogs, recurrent neural networks

1.INTRODUCTION

In recent years, the boundaries between e-commerce and social networking

have become increasingly blurred. E-commerce websites such as eBay features many

of the characteristics of social networks, including real-time status updates and

interactions between its buyers and sellers. Some e-commerce websites also support

the mechanism of social login, which allows new users to sign in with their existing

login information from social networking services such as Facebook, Twitter or

Google+. To address this challenge, we propose to utilize the linked users across

convivial networking sites and e-commerce websites (users who have gregarious

networking accounts and have made purchases on e-commerce websites) as a bridge

to map users’ gregarious networking features to latent features for product

recommendation. In concrete, we propose learning both users’ and products’ feature

Page 2 of 8

European Journal of Business &

Social Sciences

Available at https://ejbss.org/

ISSN: 2235-767X

Volume 07 Issue 03

March 2019

Available online: https://ejbss.org/ P a g e | 267

representations (called utilizer embeddings and product embeddings, respectively)

from data amassed from ecommerce websites utilizing recurrent neural networks and

then apply a modified gradient boosting trees method to transform users’ gregarious

networking features into utilizer embeddings. We then develop a feature predicated

matrix factorization approach which can leverage the learnt utilizer embeddings for

cold-start product recommendation. We built our dataset from the most immensely

colossal Chinese micro blogging accommodation SINA WEIBO2 and the most

astronomically immense Chinese B2C e-commerce website, containing a total of

20,638 linked users. The experimental results on the dataset have shown the

feasibility and the efficacy of our proposed framework. Our major contributions are

summarized below:

• We formulate a novel quandary of recommending products from an e-commerce

website to convivial networking users in “cold-start” situations. To the best of our

erudition, it has been infrequently studied afore.

• We propose to apply the recurrent neural networks for learning correlated feature

representations for both users and products from data amassed from an e-commerce

website.

• We propose a modified gradient boosting trees method to transform users’ micro

blogging attributes to latent feature representation which can be facilely incorporated

for product recommendation.

• We propose and instantiate a feature-predicated matrix factorization approach by

incorporating utilizer and product features for cold-start product recommendation.

2.PROPOSED SYSTEM

E-commerce websites such as e-Bay has many of the traits of social

networks, including real-time updates and interaction between buyers and sellers by

using their micro blogs. Some e-commerce websites also support the mechanism of

social login, which allows users to login with their existing login information from

social networking. There is no such system that has adopted the use of micro- blogging and other demographic information for cold start situation where a

customer to e-commerce site is offered suggestion of the products. Here we are

focused on the details of the micro-blogging information, demographic information,

location information, etc for the product recommendation. In this paper, we face the

problem of recommending products to users who do not have any historical purchase

records, i.e., in “cold-start” situations. We called the solution to this problem as

“cross site cold-start product recommendation”. We propose to use the coupled users

across social networking sites and e-commerce websites (users of the social

networking accounts and have done purchases on e-commerce websites) as a bridge

to map users’ social networking features to latent features for product

Page 3 of 8

European Journal of Business &

Social Sciences

Available at https://ejbss.org/

ISSN: 2235-767X

Volume 07 Issue 03

March 2019

Available online: https://ejbss.org/ P a g e | 268

recommendation. In specific, we have a tendency to propose learning each users’ and

products’ feature representations (called user embeddings and product embeddings,

respectively) from the information collected from the ecommerce websites by using

neural networks then apply a modified gradient boosting trees method to transform

users’ social networking features into user embeddings. Then by applying a feature

based matrix factoring approach which might utilize the learnt user embeddings for

cold-start product recommendation.

We propose to use the coupled users across social networking sites and e- commerce websites (users United Nations agency have social networking accounts

and have created purchases on e-commerce websites) as a bridge to map users’ social

networking options to latent options for product recommendation. In specific, we

have a tendency to propose learning each users’ and products’ feature representations

(called user embeddings and product embeddings, respectively) from knowledge

collected from ecommerce websites exploitation continual neural networks then apply

a changed gradient boosting trees methodology to rework users’ social networking

options into user embeddings. We have a tendency to then develop a feature based

matrix factoring approach which might leverage the learnt user embeddings for cold- start product recommendation. It target text attribute, network attribute and temporal

attribute.

Fig1.System Architecture