DOI:https://doi.org/10.15407/kvt212.02.004
Cybernetics and Computer Engineering, 2023, 2(212)
BULGAKOVA O.S., Phd, Associate professor,
Associate professor of the Department of Applied Information Systems,
ORCID: 0000-0002-6587-8573,
e-mail: sashabulgakova2@gmail.com
Taras Shevchenko National University of Kyiv,
Bohdan Hawrylyshyn str. 24, Kyiv, 04116, Ukraine
MAKOVETSKYI M. Ye., MSc in Computer Science
of the Department of Applied Information Systems,
ORCID: 0009-0006-2169-8745,
e-mail: makovetskyi.mykyta@gmail.com
Taras Shevchenko National University of Kyiv,
Bohdan Hawrylyshyn str. 24, Kyiv, 04116, Ukraine
ZOSIMOV V.V., DSc (Engineering), Associate professor.,
Professor of the Department of Applied Information Systems,
ORCID: 0000-0003-0824-4168,
e-mail: zosimovv@gmail.com
Taras Shevchenko National University of Kyiv,
Bohdan Hawrylyshyn str. 24, Kyiv, 04116, Ukraine
APPROACH TO THE INTELLIGENT AGENTS APPLICATION IN E-COMMERCE SYSTEMS
Introduction. This paper presents the analyze of main consumer behavior models in modern e-commerce systems, such as electronic consumer decision process model, research online – purchase offline concept, also shown architectural solutions of e-commerce systems, including microservice architecture. Proposes the application of artificial intelligence (AI) based on large language models in e-commerce. The main functions of these models include text generation, acting as a 24/7 assistant, and analytics. Specifically, the user cases for store owners include the automatic generation of product descriptions, keywords, and categories, as well as analytics in areas such as customer feedback, user requests, searches, and shopping patterns.
The purpose of the paper is to consider the possibility of use intelligent agents such as chatbots in an e-commerce system to meet customer needs, increase sales and provide personalized information.
Results. The proposed approach demonstrate that that AI models based on large language models can be applied to automate the generation of product descriptions, keywords, categories, and to gain insights into customer feedback, user requests, searches, and shopping patterns. In summary, this paper provides a comprehensive analysis of various consumer behavior models, architectural solutions, and the potential benefits of implementing AI-based solutions in the e-commerce industry.
Conclusions. The results of using intelligent agents in an e-commerce system include the ability to handle a large volume of customer queries simultaneously, provide support, and improve customer satisfaction and retention rates. The use of an intelligent agent in the sales process can also help to recommend products based on the customer’s preferences and browsing history, increasing the likelihood of a sale. The use of microservice architecture in a web application for an online store allows for independent scalability of components and the ability to build a system using different programming languages.
Keywords: e-trade, intelligent agents, consumer behavior model, e-commerce system.
REFERENCES
1 Liao C. Chen J. L. Enhancing consumer engagement in e-commerce websites: An integrated model of e-service quality, customer value, and switching costs. Journal of Retailing and Consumer Services. 2019, Vol. 50, pp. 23-32.
2 Berghausen E. M., Backhaus C. When do consumers choose same-day versus next-day delivery in online shopping? An investigation of the underlying decision-making processes. Journal of Retailing and Consumer Services. 2020, No 55, pp. 102-109.
3 Wagner T., Benlian A., Hess, T. The concept of digital affordances revisited: An exploratory study in the context of business-to-consumer electronic commerce. Journal of Business Research, 2019, 98, pp. 365-376.
4 Faradivah Dwi Azizah et al. Impulsive Buying Behavior: Implementation of IT on Technology Acceptance Model on E-Commerce Purchase Decisions. Golden Ratio of Marketing and Applied Psychology of Business, 2022, 2(1).
https://doi.org/10.52970/grmapb.v2i1.173
5 Se Hun, Lim.; Sukho, Lee., Dan J., Kim. Is Online Consumers’ Impulsive Buying Beneficial for E-Commerce Companies? An Empirical Investigation of Online Consumers’ Past Impulsive Buying Behaviors. Information systems management, 2017, Vol. 34(1), pp. 85-100.
https://doi.org/10.1080/10580530.2017.1254458
6 Wen, Chao. The Impact of Quality on Customer Behavioral Intentions Based on the Consumer Decision Making Process as Applied in E-Commerce. Doctor of Philosophy (Management Science), 2012, P. 144.
7 “https://www.igi-global.com/affiliate/mehdi-khosrow-pourdba/24/” Mehdi Khosrow-Pour, D.B.A. Consumer Behavior, Organizational Development, and Electronic Commerce: Emerging Issues for Advancing Modern Socioeconomies. 2009.
https://doi.org/10.4018/978-1-60566-126-1
8 A. B. Ayoade., A. T. Adigun., B. A. Ojokoh. Towards a Platform-Based Ecosystem for e-Commerce. Proceedings of the 13th International Conference on ICT Applications and Management (ICTAM), 2021, pp. 66-75.
9 WooCommerce system. URL: https://woocommerce.com/
10 Shopify e-commerce system. URL: https://www.shopify.com/
11 OpenCart e-commerce system. URL: https://www.opencart.com/
12 Saleor e-commerce system. URL: https://quintagroup.com/cms/python/saleor
13 Understanding and Selecting a Tokenization Solution, 2020. URL: https://securosis.com.
14 JSON Web Tokens, 2021. jwt.io
15 Password stealing from HTTPS login page and CSRF protection bypass with reflected XSS, 2020. URL: https:// medium.com/@MichaelKoczwara/password-stealing-from-https-login-page-and-csrf-bypass-with-reflected-xss-76f56ebc4516
16 Cross-Site Request Forgery Prevention Cheat Sheet, 2021. URL: https://cheatsheetseries.owasp.org/cheatsheets/Cross-Site_Request_Forgery_Prevention_Cheat_Sheet.html
17 Bulgakova O., Mashkov V., Zosimov V., Popravkin P. Risk of Information Loss Using JWT Token CEUR Workshop Proceedings, 2021, 3101, pp. 292-299.
Received 27.02.2023