See discussions, stats, and author profiles for this publication at: [Link]

net/publication/382574180

E-commerce Strategies in the Digital Age Enhancing Customer Experience

and Market Reach

Conference Paper · May 2024

DOI: 10.1109/ACCAI61061.2024.10602006

CITATION READS

1 374

5 authors, including:

Thinesh Kumar .M Kumar Natarajan

SRM Institute of Science and Technology SRM Institute of Science and Technology
7 PUBLICATIONS 3 CITATIONS 51 PUBLICATIONS 21 CITATIONS

SEE PROFILE SEE PROFILE

Nazim Sha S
SRM Institute of Science and Technology
16 PUBLICATIONS 47 CITATIONS

SEE PROFILE

All content following this page was uploaded by Nazim Sha S on 02 August 2024.

The user has requested enhancement of the downloaded file.

 E-commerce Strategies in the Digital Age
2024 International Conference on Advances in Computing, Communication and Applied Informatics (ACCAI) | 979-8-3503-8944-9/24/$31.00 ©2024 IEEE | DOI: 10.1109/ACCAI61061.2024.10602006

Enhancing Customer Experience and Market

Reach
Thinesh Kumar. M 1, N. Kumar2, Nazim Sha. S2, Noble Kennedy. E2 and Ilankadhir. M2
1
Department of Corporate Secretaryship & Accounting and Finance, Faculty of Science and Humanities, SRM Institute of Science and
Technology, Kattankulathur, Chennai, India
2
Faculty of Management, SRM Institute of Science and Technology, Kattankulathur, Chennai, India

E-mail : thinesh0890@[Link], killaikumar@[Link], salimkani4@[Link], noblekennedy@[Link],

mathikadhir@[Link],

Abstract- The paper highlights the pressing demand for E- there is a growing demand for a comprehensive and
commerce innovation, outlining flaws in existing systems innovative method that collects complex user behavior
and emphasizing the necessary development to match and turns that data into highly tailored and immersive
modern consumer expectations. Existing systems need to shopping experiences. The objective is to address the
capture complex user behavior, necessitating the
limits of existing E-commerce platforms and bring in a
implementation of a comprehensive technique. The proposed
e-commerce system combines advanced data analytics, new era of customer-centric, data-driven, technologically
machine learning, augmented reality (AR), and virtual advanced online shopping [2, 3]. The paper's primary goal
reality (VR) technology. Results and analytical metrics show is to describe and explain a novel E-commerce system
significant progress, with marketing campaign accuracy that aims to improve customer experience and market
rising from 70% to 90% and personalization efficiency reach significantly. The proposed system has a
shifting from low to high. The switch to real-time user data multidimensional strategy includes powerful data
analysis after a two-week delay demonstrates the system's analytics tools, ML algorithms, AR, VR, and
efficiency. Improvements in brand identification, customer omnichannel optimization methodologies. The goal is to
loyalty, and repurchase rates highlight the system's ability to
give businesses a full toolkit that analyzes and forecasts
improve brand-consumer relationships. Despite these
advances, obstacles such as privacy concerns and consumer preferences and integrates the digital and
accessibility issues are highlighted, emphasizing the necessity physical worlds, resulting in a seamless and engaging
for ongoing refinement to remain relevant in the dynamic purchasing experience. The proposed E-commerce system
digital commerce world. The study proposes implementing advances the field by providing a comprehensive and
such new methods to address existing limitations and innovative method beyond typical E-commerce methods.
improve the E-commerce scene. The integration of solid data analytics platforms like
Google Analytics, Mix Panel, and Adobe Analytics
Keywords: E-commerce, Data Analytics, Augmented Reality, ensures a complete insight into customer behavior,
Virtual Reality, Omnichannel Optimization, Consumer
allowing for data-driven decision-making. Collaborative
Experience, Collaborative Filtering, Brand Recognition.
filtering methods such as Singular Value Decomposition
(SVD) and Alternating Least Squares (ALS) elevate
I. INTRODUCTION
recommendation engines to new levels of precision,
revealing latent needs and improving customization.
In the continuously changing realm of digital commerce,
staying ahead of the curve is critical for businesses
Furthermore, AR and VR technology enhances the
looking to survive in a competitive market. The
traditional online shopping experience by giving
introduction of modern technology has created a new
customers immersive interactions and the option to
chance to improve client experiences and widen market
virtually connect with products before purchase [4, 5].
reach. The paper examines the paradigm change by a
The omnichannel optimization tool assures uniformity
proposed E-commerce system combining cutting-edge
across all online and offline touchpoints, strengthening
data analytics, ML techniques, AR, and VR to transform
brand identification and client loyalty. The subsequent
how businesses interact with customers and adapt their
sections of the paper go into the complexities of the
services. The reason for developing the proposed E-
proposed E-Commerce system. Section II presents an
commerce system originates from the understanding that
overview of the system, emphasizing the paradigm
traditional systems of online retail are becoming unable to
change it introduces to client engagement and
fulfill the changing expectations of modern consumers
customization. Section III details the technique, including
[1]. With the influx of data from multiple digital channels,
data collection, integration, analytics tool utilization, ML

Authorized licensed use limited to: SRM Institute of Science and Technology. Downloaded on August 02,2024 at [Link] UTC from IEEE Xplore. Restrictions apply.
 model training, AR/VR integration, and omnichannel precise to satisfy the demands of companies and
optimization. The article finishes with a comprehensive customers. The usage of mixed systems of
discussion of the system's impact on consumer recommendation to enhance e-commerce platform
experiences and market reach. Readers will get insights recommendations is discussed in the article. Despite the
into the planned E-commerce system's revolutionary shortcomings of both content- and collaborative-based
aspects and benefits as it progresses through the filtering, the study suggests a way to boost effectiveness
systematic examination. by incorporating the two with additional feature-based
filtering strategies. Comparative studies have also
The article describes an innovative E-commerce system confirmed the improved performance of that strategy [9].
that uses data analytics, ML, AR, VR, and omnichannel These marketing techniques actively involve customers
optimization to improve customer experiences and expand and ask them to help the company grow. There is no
market reach. Traditional techniques fall quickly and slowing down the trend of marketers shifting their focus
require a multidimensional technique. Integrating to providing customer experiences. As a result,
advanced analytics, collaborative filtering, and immersive experience is now highly valued by customers. The topic
technology transforms online purchasing, enabling is based on studies conducted over twenty years of
organizations to pursue data-driven, customer-centric research on immersive marketing for e-commerce. The
strategies. chapter looks at the gaps in experience that might be
discovered while making an online purchase. It tries to
[Link] WORK use literature to explain experience and online
advertising[10].To enhance customer experience tools,
The introduction of e-commerce has influenced the trend the research also examines market segmentation in the
of online shopping and customer support. In an online digital era. The poll also determines which strategy has
business setting, providing the finest customer service is been suggested as working best to improve the customer
typically the first step toward success, even if e- experience. One element of the research technique is an
commerce is acknowledged as a means of increasing SLR. It entails picking the most significant articles,
corporate competitiveness. Businesses are finding it more gathering information, combining it with other data,
difficult to enhance their performance in this area, yet assessing the publications' quality, and then delivering the
conventional customer service still has many problems, results [11].
including restricted availability, inefficiency, and
expense. An AI customer service model was eventually The research provides a comprehensive and inventive
suggested once the study questions had been formulated analysis of the e-commerce techniques of leading online
and the objectives had been established. Knowledge of merchants, with a specific emphasis on the Turkish
both traditional and AI customer service in e-commerce market. To do that, the study uses the "possible ten types
and pertinent models and papers from previous research of innovation" framework to break down the numerous
were combined to construct the proposed solution [6]. facets of innovation in the e-commerce market. The study
The study investigates the relationship between customer aims to identify potential new avenues for facilitating the
satisfaction, loyalty, trust indicators, and the chatbot application of blue ocean policy [12]. The study proposes
system's service quality element. The data collection an AI-based e-commerce marketing plan for food items
period corresponds to either the post-pandemic transition that boost smallholder farmers' earnings, increase their
era or the post-pandemic new normal. Data analysis in a access to new sectors, and fortify their bargaining power.
quantitative investigation was done using SPLS. The The efficiency of the farming supply chain can be
following characteristics were determined to have little improved by enhancing the proposed e-commerce
effect on adopting chatbots in e-commerce, although platforms' ability to connect farmers with potential
some significant aspects were identified [7]. The research consumers. Farmers can also expand market access,
aimed to employ a network embedding model to develop reduce transaction costs, and minimize information
a trustworthy user recommendation system that would asymmetry by incorporating e-commerce platforms [13].
accept and advise friends based on semantic features. The study's authors aim to identify the various facets of
User provenance data is extracted from Facebook artificial intelligence influencing consumer interaction in
conversation sessions and timelines for trust calculation. the Indian e-commerce industry. The authors also provide
The interest-based similarity between the users is a CAPE model that shows the strategies Indian marketers
determined using the FCA model and semantic and e-commerce companies can employ to increase
complexion embedding techniques. Several statistical customer engagement during a pandemic. The growing
methods are applied to evaluate the effectiveness of the usage of AI in technology has brought about a technical
similarity approaches [8]. revolution that has substantially impacted the new era of
corporate business disruption [14]. The study addresses
More current data indicates that enhancing the the challenge of determining the optimal algorithm for
recommendation system promotes corporate growth. As a producing customized recommendations in online retail
result, recommendation systems must become more by utilizing a transactional data set. More specifically, the

Authorized licensed use limited to: SRM Institute of Science and Technology. Downloaded on August 02,2024 at [Link] UTC from IEEE Xplore. Restrictions apply.
 study looks at leveraging collaborative filtering
algorithms—most notably, the well-known Alternate
Least Squares algorithm—to look at previous customer
purchases and find patterns in their preferences. The goal
is to create a recommendation system that can offer
personalized product recommendations to specific
customers by examining similar consumers' preferences
and prior purchases. The system's efficacy was measured
using performance metrics, and its proposed accuracy was
assessed by contrasting it with alternative machine
learning techniques. The study highlights how
collaborative filtering can increase e-commerce sales and
improve customer engagement by showcasing its
effectiveness in recognizing trends in consumer behavior Fig.1. Block Diagram for the proposed system
and preferences [15].
The degree of precision ensures that the system knows
In summary, the rise of e-commerce has accelerated explicit user preferences and predicts latent desires,
advances in customer care, recommendation systems, resulting in a deeply engaging and personalized shopping
immersive marketing, and AI integration. Researchers experience. The implementation begins with thorough
emphasize the need for personalizing experiences, data gathering and integration, bringing together
improving recommendations precision, and utilizing AI information from various sources, including web
technology to increase consumer engagement and platforms, mobile apps, and social media outlets.
pleasure. These studies provide insights into refining Following that, a rigorous analysis of the data phase uses
many areas of e-commerce, such as customer care and the chosen analytics tools to generate actionable insights.
marketing techniques, to boost business growth and The subsequent ML model training involves employing
flexibility in the digital landscape. collaborative filtering techniques to gain a sophisticated
understanding of user tastes, paving the way for highly
[Link] SYSTEM accurate personalized suggestions. Furthermore, the
system stands out by seamlessly combining AR and VR
In contrast to existing E-commerce platforms, the technology. The incorporation goes beyond the usual
proposed system marks a paradigm change by combining online shopping experience, allowing customers to see
powerful data analytics tools and advanced ML and engage with products in a virtual real-world setting,
techniques, drastically changing the landscape of improving the entire user experience. The omnichannel
customer engagement and customization. The proposed optimization feature offers a consistent customer journey
system goes beyond basic data tracking, utilizing cutting- across several touchpoints by smoothly combining online
edge tools such as Google Analytics, Mix Panel, and and offline interactions. The unified strategy ensures a
Adobe Analytics to give organizations a complete and consistent brand identity and allows customers to navigate
detailed view of client behavior and preferences. The between channels seamlessly. The benefits of the
proposed system allows for comprehensive data-driven proposed system are numerous. It improves customization
decision-making by providing insights into user by diving into detailed user preferences, resulting in a
interactions, website traffic trends, and purchasing considerably better overall user experience with AR and
activities. At the core of the technique is the use of ML, VR integration. The system promotes consistent brand
notably collaborative filtering algorithms like SVD and identification across all media, increasing brand
ALS. Unlike traditional systems that rely on simple recognition and loyalty. Finally, data-driven insights
recommendation engines, the proposed system thoroughly enable organizations to make more informed decisions,
examines user activity to detect inconspicuous patterns such as refining pricing tactics and marketing campaigns
and similarities among clients. It also results in very for specific client categories. The comprehensive and
accurate personalized recommendations and marketing technologically advanced technique intends to redefine E-
based on the tastes of comparable people. A block commerce norms, enabling businesses to thrive in today's
diagram of the proposed system is shown in Fig. 1. changing digital world.

[Link]
The proposed E-commerce system utilizes advanced data
collection, analytics, ML, AR/VR integration, and
omnichannel optimization strategies. The novel method
transforms client experiences by providing individualized

Authorized licensed use limited to: SRM Institute of Science and Technology. Downloaded on August 02,2024 at [Link] UTC from IEEE Xplore. Restrictions apply.
 recommendations and immersive interactions, bridging down the user-item interaction matrix into latent
the digital-physical gap. components, capturing complicated interactions, whereas
ALS optimizes by alternating between fixing user and
Data Gathering: item factors, achieving scalability and accuracy. The
To begin the proposed system, a robust data collection regularization process prevents overfitting, ensuring that
process is required, which includes pulling various data models develop a comprehensive understanding of user
from web platforms, mobile apps, and social media. It is behavior, resulting in highly accurate, real-time
accomplished via API integration and web scraping. APIs customized recommendations. The steps involved in E-
offer direct access to real-time transitions, whereas mobile Commerce Strategies are shown in Fig. 2.
apps provide user activity logs. Social media data is
obtained using APIs for organized data and web scraping
for unstructured data. It ensures an extensive dataset is
required to understand client behavior across digital
channels. Combining techniques, such as HTML parsing
and simplified API retrieval, is the foundation for future
analysis and ML.

Integration:
Integration entails combining data from various sources
into a single dataset. Extract, Transform, and Load (ETL)
operations enhance and standardize the extracted data to
assure compatibility. Schema matching and data Fig.2. Steps Involved in E-Commerce Strategies
consolidation are a couple of integration techniques that
assist in solving variations. The single dataset enables a Augmented and Virtual Reality Integration:
more comprehensive perspective of client interactions. The proposed system enhances the user experience by
APIs are critical in facilitating seamless communication facilitating virtual interactions between consumers and
across multiple platforms during integration. The unified products within a realistic environment, thereby
dataset is the foundation for analytics tools and ML integrating AR and VR. It implies the development of
algorithms, which optimize insights and provide tailored immersive environments that surpass conventional
recommendations in the proposed e-commerce system. systems. The technical integration aims to create
environments that accurately represent the real world,
Analytics Tool Utilization: guaranteeing compatibility with a wide range of devices.
The proposed system relies on Google Analytics, Mix Employing its precise methodology augments the overall
Panel, and Adobe Analytics for analysis. Google purchasing encounter and introduces a transformative
Analytics excels at tracking website traffic, population aspect that enables users to traverse the divide between
trends, and engagement metrics. Mix panel specializes in the digital and physical domains effortlessly.
event tracking, which reveals hidden user interactions.
Adobe Analytics provides detailed insights into buying Omnichannel Optimization:
patterns. By combining these methods, the system The proposed system accomplishes omnichannel
acquires a comprehensive understanding of user activity optimization via a robust framework that combines brand
across multiple platforms. The result enables precise data- identity across all connections. Implementing robust
driven decision-making, creating highly customized synchronization mechanisms facilitates uncomplicated
recommendations and targeted marketing tactics, hence customer channel navigation through seamless online and
improving the total customer experience and market offline integration. Ensuring consistency in product
reach. details and promotions is accomplished through API-
based communication, whereas real-time data
Machine Learning Model Training: synchronization aligns consumer information and
The system's foundation is based on training collaborative transactions. Implementing such a dynamic strategy
filtering algorithms, SVD and ALS, which are critical for improves the omnichannel experience, as precise and real-
extracting complex patterns from user activity data and time interactions are established, thereby cultivating
providing exact individualized recommendations. SVD brand awareness and allegiance. The system's technical
efficiently handles sparse matrices, optimizing sophistication relies on establishing an identifiable look
computational resources, whereas ALS is preferred for its across various platforms, thereby strengthening the
scalability and precision, which contribute to solid model brand's identity in the natural and digital domains to
performance. Both algorithms methodically assess the provide customers with an improved and uniform
integrated dataset during training and adjust to user experience.
preferences. The rigorous procedure requires dividing the
dataset into training and validation sets. SVD breaks

Authorized licensed use limited to: SRM Institute of Science and Technology. Downloaded on August 02,2024 at [Link] UTC from IEEE Xplore. Restrictions apply.
 Implementation and Testing:
During execution, the integrated system, which includes
AR, VR, and ML, is thoroughly tested for functionality
and performance. ML testing covers algorithm validation
for recommendation accuracy across various user
scenarios and model evaluation with training data and
real-world testing. AR and VR features are tested for
immersive interactions and visual accuracy, assuring
compatibility with the appropriate devices. Omnichannel
testing confirms seamless online-to-offline transitions
while ensuring brand consistency. The testing step, which
uses real-world and simulated environments, evaluates Fig.3. Performance Metrics Comparison Graph
ML algorithm robustness and AR/VR capability for
optimal performance, providing a better e-commerce user TABLE II: BRAND RECOGNITION AND LOYALTY METRICS
experience. Existing Proposed
Metric
System [8] System
The E-commerce system connects data from web Brand Recognition Moderate High
platforms, mobile apps, and social media. It uses analytics
tools for insights, collaborative filtering algorithms for Customer Loyalty 3.7/5 4.5/5
exact suggestions, AR/VR for immersive experiences, and Repeat Purchase Rate 15% 28%
omnichannel optimization. Thorough testing validates
functionality, creating a revolutionary and consistent E- Table II compares the performance of the proposed and
commerce user experience. existing systems [8]. The proposed system outperforms
the existing system in terms of critical measures. Brand
[Link] AND ANALYSIS identification is projected to rise from moderate to high
levels, indicating improved visibility. Customer loyalty is
The comparison research across three key parameters expected to increase from 3.7/5 to an impressive 4.5/5,
reveals significant improvements in the proposed E- indicating stronger customer ties. The repeat purchase
commerce system over the existing one. Improved percentage is expected to nearly double, rising from 15%
recommendation accuracy, marketing campaign efficacy, to 28%, demonstrating the system's efficiency in
personalization, and brand recognition all demonstrate the promoting customer retention and boosting repeat sales.
system's transformative impact on user experience,
loyalty, and market reach. Table III: Data-Driven Decision-Making Metrics
Existing Proposed
Table I: Recommendation Accuracy Comparison Metric
System [8] System
Existing Proposed Accuracy of Marketing
Metric 70% 90%
System [8] System Campaigns
Average Precision 0.65 0.85 Personalization
Low High
Recall 0.72 0.90 Effectiveness
F1 Score 0.68 0.88 Time to Analyze User
Two weeks Real-time
Data
Table I compares performance indicators between the
proposed and existing systems[8]. The proposed system Table III compares the proposed system's model
outperforms the previous system in all key parameters, performance to an existing system [8]. The proposed
with notable gains in Average Precision, Recall, and F1 system outperforms the existing system in various ways.
Score. Precision increased from 0.65 to 0.85, indicating It has significantly improved the accuracy of marketing
improved accuracy, while Recall rose from 0.72 to 0.90, initiatives, ranging from 70% to an astonishing 90%. The
indicating higher coverage. The F1 Score increase from personalization efficacy has increased dramatically,
0.68 to 0.88 demonstrates a more balanced trade-off moving from a low to a high level. Furthermore, the time
between precision and Recall, making the proposed necessary to examine user data significantly decreases
method the better choice. The performance Metrics from two weeks to real-time, allowing for timely and
Comparison Graph is shown in Fig. 3 below. dynamic decision-making.

Overall, the proposed system greatly improves key

metrics compared with the existing system. It increases
brand identification, client loyalty, and repeat purchase
rates. Furthermore, the proposed system enhances

Authorized licensed use limited to: SRM Institute of Science and Technology. Downloaded on August 02,2024 at [Link] UTC from IEEE Xplore. Restrictions apply.
 marketing campaign accuracy, increases personalization [Link]
effectiveness, and reduces the time required to analyze
user data from two weeks to real-time, indicating a In conclusion, the proposed E-commerce system is a
significant improvement in overall marketing novel way to improve customer experience and expand
performance. market reach in the digital age. The system achieves
highly personalized proposals, immersive interactions,
[Link] and consistent brand identity across online and offline
channels by combining powerful data analytics, ML, AR,
The proposed E-commerce system is a huge step to and VR technologies. The collaborative filtering
improving consumer experience and expanding market algorithms, SVD and ALS, effectively extract nuanced
reach. The results of the deployment and testing phases user behavior patterns, resulting in reliable and real-time
demonstrate its success in transforming the digital customized recommendations. AR and VR enhance the
purchasing scene. The integrated technique, combining online buying experience, linking the digital and physical
data analytics, ML, AR, and VR technologies, achieves worlds. Omnichannel optimization creates a cohesive and
outstanding customer interaction and customization smooth consumer experience, increasing brand
outcomes. The collaborative filtering algorithms SVD and recognition and loyalty. However, the system has limits.
ALS effectively extract complex trends from user activity Worries about privacy and data security may arise,
data, resulting in highly accurate and real-time demanding solid steps to address these issues. The
customized recommendations. The usage of AR and VR adoption of AR and VR may cause accessibility issues for
improves the user experience by providing virtual some users. The system's effectiveness depends on its
interactions with items in a realistic setting, linking the accessibility and data quality, which can vary by industry
digital and physical worlds. Omnichannel optimization and region. Future research should address these limits by
ensures a seamless and consistent consumer experience strengthening data security measures, expanding
across several touchpoints, enhancing brand identity and accessibility features for AR and VR, and investigating
loyalty. The system's uses span multiple industries, ways to adapt the system to other data environments.
providing a dynamic and tailored technique for consumer Furthermore, studies might look into integrating emerging
contact. E-commerce enterprises can use the detailed technologies like artificial intelligence and blockchain to
knowledge to develop customized marketing and pricing improve the system's capabilities and meet changing
strategies. The merging of AR and VR creates new market demands. The proposed E-commerce system will
opportunities for online shops by allowing buyers to try require continuous refinement and adaptation to ensure its
products before purchasing them. Omnichannel long-term viability and relevance in the dynamic world of
optimization enables a consistent brand presence, digital commerce.
improving the customer experience across online and
offline channels. The benefits of the proposed system are REFERENCES
numerous. It provides a new degree of personalization by
diving into deep user preferences, resulting in a [1] S. Shedekar, S. K. Shah, and V. Kumbhar, ―Enhancing E-
Commerce Insights: Sentiment Analysis Using Machine
considerably better overall user experience. The seamless
Learning and Ensemble Techniques,‖ 2023 International
integration of AR and VR creates a fresh and engaging Conference on Integration of Computational Intelligent System
buying experience, helping businesses stand out in a (ICICIS), Nov. 2023, doi: 10.1109/icicis56802.2023.10430284.
competitive market. Consistent brand identification across [2] A. Erensoy, A. Mathrani, A. Schnack, Y. Zhao, V. Chitale, and
N. Baghaei, ―Comparing Customer Behaviours: Immersive
all mediums improves brand recognition and customer
Virtual Reality Store Experiences versus Web and Physical
loyalty. Data-driven insights enable firms to make Store Experiences,‖ 2022 IEEE Asia-Pacific Conference on
informed decisions, resulting in more effective marketing Computer Science and Data Engineering (CSDE), Dec. 2022,
efforts and consumer satisfaction. doi: 10.1109/csde56538.2022.10089288.
[3] A. T. Rosário and R. Raimundo, "Consumer Marketing Strategy
and E-Commerce in the Last Decade: A Literature Review,"
The proposed E-commerce system, which incorporates Journal of Theoretical and Applied Electronic Commerce
data analytics, ML, AR, and VR technologies, Research, vol. 16, no. 7, pp. 3003–3024, Nov. 2021, doi
significantly improves consumer experience and market 10.3390/jtaer16070164.
[4] Y. Vakulenko, P. Shams, D. Hellström, and K. Hjort, "Online
reach. Collaborative filtering systems provide exact
retail experience and customer satisfaction: the mediating role
recommendations, and AR and VR provide immersive of last-mile delivery," The International Review of Retail,
interactions. Omnichannel optimization maintains brand Distribution and Consumer Research, vol. 29, no. 3, pp. 306–
consistency. The system's advantages include increased 320, May 2019, doi: 10.1080/09593969.2019.1598466.
[5] H. J. V. L and D. Rajan, ―Enhancing Customer Experience and
personalization, brand familiarity, and data-driven
Sales Performance in a Retail Store Using Association Rule
decision-making to improve consumer happiness. Mining and Market Basket Analysis,‖: 2023 14th International
Conference on Computing Communication and Networking
Technologies (ICCCNT), Jul. 2023, doi:
10.1109/icccnt56998.2023.10307411.

Authorized licensed use limited to: SRM Institute of Science and Technology. Downloaded on August 02,2024 at [Link] UTC from IEEE Xplore. Restrictions apply.
 View publication stats

[6] N. L. Ping, A. R. C. Hussin, and N. B. M. Ali, ―Constructs for [14] F. Vapiwala and D. Pandita, ―Analyzing the application of
Artificial Intelligence Customer Service in E-commerce,‖ 2019 artificial intelligence for E-Commerce customer engagement,‖
6th International Conference on Research and Innovation in 2022 International Conference on Data Analytics for Business
Information Systems (ICRIIS), Dec. 2020, doi: and Industry (ICDABI), Oct. 2022, doi:
10.1109/icriis48246.2019.9073486. 10.1109/icdabi56818.2022.10041655.
[7] S. Rawat, U. Tyagi, and S. Singhal, ―Recommender Systems in [15] Mahajan, K., Alhasen S., Chaudhari D., Sharanyaa S. &
E-commerce and their Challenges,‖ 2021 3rd International Agrawal D. (2023). Jaya-Mutated Leader Algorithm Based
Conference on Advances in Computing, Communication Deep Feed Forward Neural Network For Intrusion Detection
Control and Networking (ICAC3N), Dec. 2021, doi: Using Cloud Computing, Cybernetics and Systems An
10.1109/icac3n53548.2021.9725681. International Journal, 54(1), 1-26,
[8] B. Raju, M. Sriram, etc. al, "Aspect Based Text Summarization [Link]
Model for the E-Commerce Recommendation System," IEEE [16] Mahajan, K., Suhasini, T., Reddy, S., Mickle Aancy, H., &
Conference Publication | IEEE Xplore. Bhupendra Kumar (2023)Analyzing the Financial Risk Factors
[Link] Impacting the Economic Benefits of the Consumer Electronic
[9] V. Kumar, V. Pal, U. Vashisth, and L. Banda, ―Enhance the Goods Manufacturing Industry in India, Journal of Advanced
Quality of Recommendation System in E-Commerce Manufactured System, 22 (2), 1-25,
Application,‖ 2023 International Conference on Computational [Link]
Intelligence, Communication Technology and Networking [17] T. Vino, [Link],R. V.V. Krishna, T. Karthikeyan, Yogesh
(CICTN), Apr. 2023, doi: 10.1109/cictn57981.2023.10140664. Kumar Sharma, [Link], [Link],
[10] A. B. More, ―Implementing digital age experience marketing to [Link], and Mebratu Markos ―Multicluster Analysis and
make customer relations more sustainable,‖ in Springer eBooks, Design of Hybrid Wireless Sensor Networks Using Solar
2023, pp. 99–119. doi: 10.1007/978-3-031-20443-2_5. Energy," Hindawi, International Journal of Photoenergy,
[11] M. T. Nuseir, G. a. E. Refae, A. I. Aljumah, M. Alshurideh, S. Volume 2022, Article ID 1164613, 8 pages,
Urabi, and B. A. Kurdi, "Digital Marketing Strategies and the [Link]
Impact on Customer Experience: A Systematic Review," in [18] Archana P. Divyabharathi, S.R. Balaji, N. Kumareshan, P.
Studies in computational intelligence, 2023, pp. 21–44. doi: Veeramanikandan, S.T. Naitik, Shaik Mohannad Rafi, Praful V.
10.1007/978-3-031-12382-5_2. Nandankar, G. Manikandan,― Face recognition based vehicle
[12] M. Ş. Akın, ―Enhancing E-commerce Competitiveness: A starter using machine learning‖, Measurement: Sensors 24
comprehensive analysis of customer experiences and strategies (2022) 100575. [Link]
in the Turkish market,‖ Journal of Open Innovation: [19] M. Loukili, F. Messaoudi, and M. El Ghazi, ―Personalizing
Technology, Market, and Complexity, p. 100222, Jan. 2024, Product Recommendations using Collaborative Filtering in
doi: 10.1016/[Link].2024.100222. Online Retail: A Machine Learning Approach,‖ IEEE
[13] V. V. Kumar, G. D. Devi, U. Ajay, M. Sharun, and P. Yukesh, Conference Publication | IEEE Xplore, Aug. 09, 2023.
―Enhancing Smallholder Farmer Livelihoods through AI-Based [Link]
E-Commerce Marketing for Agricultural Products,‖ 2023
International Conference on Sustainable Computing and Data
Communication Systems (ICSCDS), Mar. 2023, doi:
10.1109/icscds56580.2023.10105046.

Authorized licensed use limited to: SRM Institute of Science and Technology. Downloaded on August 02,2024 at [Link] UTC from IEEE Xplore. Restrictions apply.