Ijraset Journal For Research in Applied Science and Engineering Technology
Authors: Urmila Dhadwad, Siddhi Dhomse, Snehal Desai, Pooja Kohok, Shweta Shah
DOI Link: https://doi.org/10.22214/ijraset.2023.49725
Certificate: View Certificate
Latest improvements in the online shopping system through the machine learning, data mining to improve the handcraft products marketing. One of the main reason to build the solutions for the handcrafts is to develop the products with the use of latest technologies for achieving the success in the handcraft industry. Handcraft are the products which are made by the craft person and it is very unique in market. In the handcraft store we can eliminate the middle man. This paper reviews the various methods and techniques which are used for handcrafts. Firstly, we provide a review on the different strategies used in handcrafts with respect to present world. Then we highlight the different techniques applied to create platform for handcrafts-frameworks, data mining, machine learning and commerce and internet technology. We also give an overview of the results achieved by using this different techniques.
I. INTRODUCTION
After the COVID-19 pandemic, many businesses chose an online option rather than going offline. People are not interested in going to the market to purchase the product. Rather, customer simply choose an online platform to buy the products customers want. The primary goal of a handicraft store is to reach as many customers as possible in order to increase sales and profit for the company. It mainly focuses on artisans in rural areas. But the artisans in rural areas are dependent on middlemen to sell their products. It aims to increase the sale of handloom products, which directly increases the profit of artisans. Various marketing strategies are used to grab more audience attention. Social media platforms such as Instagram, Facebook and LinkedIn are used for marketing purposes. Different machine learning techniques, such as recommendation systems and chatbots are used[13]. A machine learning algorithm such as Naive Bayes is used for building a recommendation system that uses machine learning techniques to predict whether a user will like a given product or not. With the help of a chatbot, users can interact with the system to solve their problems. It is a web-based portal created with dedication in mind and the hard work of individual artisans and craftsmen[11]. Its aims are to use and combine modern technology to provide artisans with a platform to show their skills in crafts to a wider range of audiences. This approach reduces the cost of involving a middleman and also provides an opportunity for a greater profit margin for the sellers who sell the crafts. Sellers can directly register on the portal and show their skills to the world. Handicraft is the industry where users can buy various products handcrafted by skilled artisans and individual manufacturers. The admin has all rights to the data displayed on the portal. Artists register as sellers and send their product info to the admin, who manages the data at the backend. Customers can easily buy the product with a user-friendly interface.
II. RELATED WORKS
A. Different Strategies used in handcrafts with respect to present world
Following are the different main strategies used in handcrafts:
B. Different Techniques Applied to Create Platform for Handcrafts
Following are different techniques applied for creating handcrafts platform:
1. Frameworks
a. Spring MVC Framework
Model View Controller or MVC, is popularly called a software design pattern to develop web applications. The MVC consists of three parts:
MVC is used to separate the implementation logic from the actual implementation part. All the requests received by controller for application which is used to prepare data needed by view part. The view part then uses this data to generate the result [4],[8].
b. Advantages of MVC Architecture
This paper focus on designing of web applications using Spring MVC framework [3]. Spring MVC framework uses the Model-View-Controller pattern for designing web applications faster and easier. It concludes that MVC pattern architecture and technologies like JSP, Servlet and EJB on the platform of J2EE have simplified the development process of web applications.MVC architecture provides the concept of parallel development as it divides the application into three layers, so different developers can work simultaneously on layers to build applications, which reduces time and speed up the development of applications.
c. Spring Framework
The Spring framework is an open-source application framework. It is easy to build java application using spring framework. Spring makes java programming easier, faster and safer. Spring is world’s most popular Java framework which is used to build web application faster. The architecture of spring consists of seven modules -
d. Features of Spring Framework
2. Data Mining
Data mining is the process of extracting and finding out the patterns in large datasets[10]. Data mining is an interdisciplinary subfield of computer science with an overall goal of finding out important information from a dataset and transforming the information into a comprehensible structure for further use. The term “data mining” is misnamed because the goal of data mining is extracting patterns and information from large dataset not extracting data. It is frequently used with large-scale data for information processing for collection, extracting information and analysis of data. The process of data mining is the semi-automatic or automatic analysis of large volume of data and finding out interesting patterns from it.These patterns is kind of summary for input data, and it is used for further analysis, for example this pattern is used for predictive analytics and in different machine learning task to obtain more accurate result. Tasks involve in data mining:
a. Anomaly detection
b. Association rule learning
c. Clustering
d. Classification
e. Regression
f. Summarization
3. Machine Learning
a. Chatbot AIML: When a user wants to purchase something from artisans, he or she requires instructions on how to use the system and other items, much as when shopping in a store. To offer these kinds of services online, we use chatbot that provide service to user. When a user first visits an online store, he or she can ask questions to learn more about the software. A pattern matching algorithm is used by the system to send a customer’s query to the AIML Knowledge Base System (KBS) for an answer. The response is then sent back to the user and then to the system. There are numerous chatbot implementations in various fields [6].In this paper, author have also included multi-language support, which makes this application more interactive with the user. To support multi-lingual capacities, this paper proposes to develop Bangla conversational agent that can chat user with Bangla. AIML supported the Avro keyboard layout, Unicode and ANSI[6]. When chatbots get input data from users, we have to add a translator program. The translator checks the input. If the input contains the English alphabet, the translator will pass it directly to the system; otherwise, it will turn the input into an English phrase and pass it on to the knowledge base system for further processing. However, a translator is not necessary for the response.
b. Naive Bayesian Algorithm: The Naive Bayes classifier is used to measure the probability that customers will buy a product or not[11]. Data were collected from various past resources and then analysed using naive Bayes classifiers. An identification classifier would analyse the product review to determine the aggregate opinions about each of them.
c. Sentiment Analysis: Sentiment analysis is the most commonly used technique for analysing text-based data and identifying sentiment content. Suggestions, feedback, tweets, and comments all create a large amount of text data. Sentiment analysis involves the use of artificial intelligence (AI) to collect text data from a variety of sources, identify opinions, and classify the findings into a positive, neutral, or negative response to a product or service. This paper used CNN and GRU networks to extract the main sentimental and contextual features of the reviews, and an attention mechanism is used to weight them [12]. By using a model to analyse user reviews, we can help merchants on e-commerce platforms obtain user feedback in time to improve service quality.
4. Commerce and Internet Technology
In this paper, author analyse the deep learning-based C2B cross-border EC business models[1]. First, a few of the business model components are chosen for research work after being analysed. According to the experimental findings, the important variables rise as user value rises, but the overall pattern stays the same. The number of active users grows as user value rises, making the rise in active users more noticeable.
C. Results Published in Previous Studies
III. PROPOSED METHODOLOGY
This paper concludes how the different techniques can be useful for the e-shop application. The naive Bayes algorithm is useful in e-shop application, further naive Bayes algorithm is proposed in this paper for the better sentimental analysis in review classification, to classify the reviews according to customer review positive, negative and neutral. The naive bayes algorithm can also be helpful in the recommendation engine to recommend the product. As naive bayes algorithm is simple to implement and it gives the more accuracy.
IV. ARCHITECTURE DIAGRAM
This paper proposes Spring Boot, a layered architecture in which each layer communicate with each other[4].
This paper concludes that how e-commerce now become an important factor for many organizations in daily running of their business. Then different factors that contribute to the success of the E-commerce industry are mentioned like consistency in website design, planning, marketing strategies and product quality should be same as display on portal. This paper focus on how to use different techniques, framework and machine learning algorithms to build e-shop application and also how e-shop is important for customers.
[1] Q. Wu, J. Ma and Z. Wu,” Consumer-Driven E-Commerce: A Study on C2B Applications,” 2020 International Conference on E-Commerce and Internet Technology (ECIT), Zhangjiajie, China, 2020, pp. 50-53, doi: 10.1109/ECIT50008.2020.00019. [2] Rationale of Handicraft on Women Employment in Rural Area: A case study on Jari workers (Ananya Chakrabot y Mar 2013) [3] A. Singh, P. Chawla, K. Singh and A. K. Singh,” Formulating an MVC Framework for Web Development in JAVA,” 2018 2nd International Conference on Trends in Electronics and Informatics (ICOEI), Tirunelveli, India, 2018, pp. 926-929, doi: 10.1109/ICOEI.2018 [4] Chunsheng Zhao, Mai Jiang and Zhiyong He,” The design of E-commerce system architecture based on Struts2, Spring and Hibernate,” The 2nd International Conference on Information Science and Engineering, Hangzhou, 2010, pp. 3251-3254, doi: 10.1109/ICIS [5] Ghosal, Indrajit Prasad, Bikram. (2020). Inspiring Digitalization of Handicraft Market: An empirical approach. 15. 199-209. 10.23862/kiit-parikalpana/2019/v15/i1-2/190186. [6] Satu, Md Akhund, Tajim Md. Niamat Ullah Yousuf, Mohammad. (2017). Online Shopping Management System with Customer Multi-Language Supported Query handling AIML Chatbot. 10.13140/RG.2 [7] Zhang, Jianxi Zhang, Changfeng Yu, Huaizhi. (2018). Research on e-commerce intelligent service based on Data Mining. MATEC Web of Conferences. 173. 03012. 10.1051/matecconf/201817303012. [8] MVC Architecture: A Detailed Insight to the Modern Web Applications Development (Abdul Majeed1 and Ibtisam Rauf September 26, 2018) [9] D. Zhang, Z. Wei and Y. Yang,” Research on Lightweight MVC Framework Based on Spring MVC and Mybatis,” 2013 Sixth International Symposium on Computational Intelligence and Design, Hangzhou, China, 2013, pp. 350-353, doi: 10.1109/ISCID.2013.94. [10] R. A. E. -D. Ahmeda, M. E. Shehaba, S. Morsya and N. Mekawiea,” Performance Study of Classification Algorithms for Consumer Online Shopping Attitudes and Behavior Using Data Mining,” 2015 Fifth International Conference on Communication Systems and Network Technologies, Gwalior, India, 2015, pp. 1344-1349, doi: 10.1109/CSNT.2015.50. [11] Zhao, Wenyuan. (2020). Classification of Customer Reviews on E-commerce Platforms Based on Naive Bayesian Algorithm and Support Vector Machine. Journal of Physics: Conference Series. 1678. 012081. 10.1088/1742-6596/1678/1/012081. [12] L. Yang, Y. Li, J. Wang and R. S. Sherratt, ”Sentiment Analysis for E-Commerce Product Reviews in Chinese Based on Sentiment Lexicon and Deep Learning,” in IEEE Access, vol. 8, pp. 23522- 23530, 2020, doi: 10.1109/ACCESS.2020.2969854. [13] Kumar, Dilip PV, Rajeev. (2019). A NEW STRATEGIC APPROACH FOR MARKETING OF HANDICRAFT PRODUCTS. 2. 540-543. [14] Bhat, Jahangir Yadav, Pushpender. (2016). Handicraft Sector: The Comforting Sector of Employment Review. Management Studies and Economic Systems. 3. 111-117. 10.12816/0037561. [15] Srivastav, Gaurav Singh, Pankaj. (2016). INDIAN HANDICRAFT GLOBALIZATION: IN CONTEXT OF EXPORT. 10.4018/978-1-4666-9720-1.ch009. [16] Shah, Amisha Patel, Rajiv. (2018). Problems and Prospects of Rural Handicraft Artisans. Organisational Transformation and Social Change. 12. 72-85.
Copyright © 2023 Urmila Dhadwad, Siddhi Dhomse, Snehal Desai, Pooja Kohok, Shweta Shah. 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.
Paper Id : IJRASET49725
Publish Date : 2023-03-22
ISSN : 2321-9653
Publisher Name : IJRASET
DOI Link : Click Here