Ecommerce Website with Recommendation System Including Chatbot and Reverse Image Search

Abstract

Abstract: In Today’s generation, it has become a need to get clear vision, prioritize and effortlessly to provide appropriate information to decrease the problem of information overload, which has created a major problem for many users using internet. Recommender systems is capable to solve this major problem by using searching technique through a huge volume of dynamically generated useful data to provide users with personalized content and services depending on their interest. Recommendation system plays an important role in the internet world and is used in many applications. Recommendation systems are of three types: 1) collaborative filtering 2) content based and 3) hybrid based approach. With the advancement of machine learning for decades, there are still numerous problems insolvable, such as image recognition and location detection, image classification, image generation, speech recognition, natural language processing and so on. In this emerging field of deep learning, the research on topic like image classification has always been the topmost traditional research to be evolved. Simultaneously, Image recognition technology is also beneficial to gradually respond in better way to the development of international indicators, and betterment the development and progress in various fields. Hence, image processing technology which is based on machine learning has always been widely used in feature image segmentation, classification and recognition, and is an important topic in various fields. It allows you to find similar products in your store in a very easy way. Let the customer find the product based on the photo. What\'s more, you no longer have to manually match similar products, it will be done automatically by AI algorithm. The main purpose of this project is to use the concept of a machine learning algorithm to build a Recommendation and Reverse Image Search and recognition with the help of convolutional neural networks (CNN).

Introduction

I. INTRODUCTION

A recommendation system is an vast class of web applications that involves predicting the user responses to the options. Recommender systems are uncomplicated algorithms which provide the most accurate and exact relevant items to the user by filtering out needful or useful information from of a huge volume of data. Recommendation engines has ability to discover various  data patterns in the data set ,which would be useful for filtering .

This can be done by learning customerchoices and interests and provides the accurate results that best co-relates to customers needs and interests.

It allows you to find similar products in your store. The customer will find the product by uploading its image. They will no longer have to manually match similar products, it will be done automatically by AI algorithm.

II. MOTIVATION

Modern e-commerce is about much more than just offering products online We aim to build a virtual shopping assistant using image recognition technologies to improve the overall online shopping experience for the users. The application has two main components image recognition service and a product recommendation system. Each component is an important part of this application.  

   III. AIM AND OBJECTIVES OF THE WORK

A. Project Aims

Our aim is to build a virtual shopping assistant using image recognition technologies to improve the overall online shopping experience for the users. The proposed application has two main components image recognition service and a product recommendation system. Each component is an important part of this application.

B. Project Objectives

Recommender systems in ecommerce website has the ability to predict whether a particular user would prefer an item or not based on the user's profile history. These systems make use of information-filtering-techniques which helps to analyse given information and provide the user with more accurate/relevant products. So the main objective of recommender systems is to provide recommendations based on recorded information on the users' preferences.

It allows you to find similar products in your store in an easy way. Let the customer find the product based on the photo. Because of this, we no need to manually match similar products, it will be done automatically by AI algorithm.   

IV. SYSTEM REQUIREMENT

A. Hardware Requirements   

1. Software Application Processor: Intel ® Core TM i7- 10510U. 
2. Hard Disk: 20 GB and above. 
3. RAM: 4 GB. 

    B. Software Requirements   

1. Operating system: Windows 7 and   above 
2. Language: PYTHON
3. Framework: Flask

 V. SYSTEM ARCHITECTURE

VI. ARCHITECTURE SUMMARY

 There are two modules in our project Recommendation System and Reverse Image Search.

A. Recommendation System

In first module Recommendation System i.e. product-details including category, name, color, type, brand, image, etc is stored in the database. Depending upon the inputs from the customer i.e. customer clicks on any product/view the product, the model will be able to compute the similarity and predict the similar products based on some parameters and then the model will display the recommended products .

 B. Reverse Image Search

In this module, customer will upload product image through the system. The model will be able to extract features from input image, compare features of input image with features of images in database and then sort results by relevancy and display the results to the user.   

Conclusion

The proposed application will have two main components, i.e Recommendation System and Reverse Image Search service. Each of these components is an important part of this application. However, image recognition service is the core functionality of the application which enables users to extract meaningful information from the images which are hard to describe in words, for example, categories, brand name, colour features of a product. In future we will try to enhance the accuracy of all two functionalities to make the user interface more reliable

References

[1] Shakila Shaikh; Sheetal Rathi; Prachi Janrao , “Recommendation system in E-commerce websites: A Graph Based Approach” IEEE - 2017 IEEE 7th International Advance Computing Conference [2] Mohsen Jamali, Martin Ester , ”A Matrix Factorization Technique with Trust Propagation for Recommendation in Social Networks” ACM [3] Neha Sharma, Vibhor Jain, Anju Mishra “An Analysis Of Convolutional Neural Networks For Image Classification” IEEE [4] Deepika Jaiswal, Soman Kp, Sowmya Vishvanathan “Image Classification Using Convolutional Neural Networks” ACM.

Copyright

Copyright © 2022 Preeti Badave, Bhakti Bhomaj, Bhargavi Bindu, Riddhi Shivarkar, Prof Nikhil Dhavase . This is an open access article distributed under the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.