The Application of Big Data in the Marketing of Live E-Commerce
Platform
Xiang Liang
Fushun No.12 High School, Fushun, China
Keywords: Big Data, Live E-Commerce, Marketing, User Behavior Analysis, Personalized Recommendation.
Abstract: With the rapid development of electronic commerce (e-commerce) and live streaming technology, Live
Streaming Commerce (LSC) platform has be-come an important channel of modern retail industry. In this
context, big da-ta technology provides strong support for the marketing of live streaming e-commerce. This
paper discusses the application of big data in the marketing of LSC platforms, in-cluding user portraits,
accurate recommendations, real-time data analysis and market trend prediction. By analyzing user behavior
data, the platform can build a refined consumer portrait to realize personalized product recommendation and
precision marketing. Real-time data analysis helps platforms optimize live content and engagement strategies
to in-crease user engagement and conversion rates. At the same time, the predictive power of big data provides
merchants with insights into market trends and optimizes supply chain and inventory management. This paper
takes a well-known live streaming e-commerce platform as an example to explain how big data technology
can help it improve marketing effect and realize business value. The research shows that the big data-driven
marketing model is of great significance in improving the competitiveness of the platform and pro-moting the
upgrading of consumption.
1 INTRODUCTION
The rapid development of information technology has
brought Live Streaming Commerce (LSC), which is
the product of the combination of information
technolo-gy development and business model
innovation (Wang et al., 2022). As a new business
mod-el, LSC is rapidly emerging as an important part
of the e-commerce field with its advantages of
enhancing customer engagement, product promotion,
transaction facilitation, and improving online
shopping experiences (Luo et al., 2023). However, in
the increasingly competitive LSC market, how to
improve user experience, optimize marketing
strategies and achieve accurate access has become the
core issue that platforms and merchants need to solve.
In this context, the wide application of big data
technology has inject-ed new vitality into LSC.
Big Data is a term of massive data that have large
volume and difficulties for fur-ther storing and
processes (Sagiroglu et al., 2013). Big data, with its
powerful data analysis and processing capabilities,
can comprehensively improve the marketing
efficiency of LSC plat-forms. In LSC, data are the key
to provide customers with personalized service,
which are collected when consumers are browsing
shopping soft-ware (Akter & Samuel, 2016). From
the collection and analysis of user behavior data to the
application of intelligent recom-mendation
algorithms, big data helps LSC to achieve accurate
matching between users and products. Through the
in-depth mining of user browsing, liking, sharing,
purchasing and other behavioral data, the platform
can precisely target user groups, insight into
consumer preferences, and push personalized
products and content, so as to meet customer needs,
reduce marketing costs, and increase profits (Akter &
Samuel, 2016).
In addition, big data also plays an important role
in real-time monitoring and deci-sion optimization of
LSC. By analyzing key metrics such as number of
viewers, length of stay, transaction rate, etc., the
platform can timely adjust marketing strate-gies and
interactive content to increase user engagement and
purchase intention. More importantly, the predictive
power of big data can help businesses grasp market
trends, layout in advance, and avoid risks (Zhanet al.,
2018). At the same time, big data technology can also
be used for traffic distribution and traffic monitoring
in the broadcast room to maximize the marketing
effect by dynamically adjusting the recommendation
logic and optimizing the allocation of resources. For
Liang, X.
The Application of Big Data in the Marketing of Live E-Commerce Platform.
DOI: 10.5220/0014138700004942
Paper published under CC license (CC BY-NC-ND 4.0)
In Proceedings of the 2nd International Conference on Applied Psychology and Marketing Management (APMM 2025), pages 533-537
ISBN: 978-989-758-791-7
Proceedings Copyright © 2026 by SCITEPRESS – Science and Technology Publications, Lda.
533

example, by monitoring the number of viewers,
length of stay, transaction rate and other key
indicators in the broadcast room, you can quickly find
problems in the marketing link, optimize re-source
allocation and interaction, and maximize the balance
between revenue and user satisfaction.
Therefore, discussing the specific application of
big data in the marketing of live e-commerce
platforms not only helps to understand the operational
logic of this emerg-ing business model, but also
provides innovative ideas for the development of the
industry. By reviewing and summarizing the
literature, user positioning, content opti-mization and
marketing effect evaluation of LSC platforms.
Through the analysis of the deep integration of big
data technology and live e-commerce marketing, it
aims to provide a new perspective and reference for
the development of the industry.
2 APPLICATION ANALYSIS OF
BIG DATA TECHNOLOGY IN
LIVE E-COMMERCE
MARKETING
2.1 Collect and Analyze User Data
In practical applications, big data technology runs
through the full link of live e-commerce marketing,
helping enterprises to enhance their competitiveness
in multiple links. First of all, In terms of data
collection and analysis, users' behaviors and habits of
watching live broadcast can be collected. For
example, data can be collected and analyzed regarding
the highest number of people watching live
broadcasts, the time of day when a single consumer’s
viewing peaks, the duration of audience watching, and
the types of live broadcasts that attract more viewers
and keep them engaged for longer periods (Mendhe
al., 2020). Secondly, in terms of product selection and
inventory manage-ment, data analysis helps
merchants understand the character-istics and market
de-mand of hot products, so as to optimize product
selection decisions and reduce the risk of lagging
sales. Thirdly, real-time data monitoring can help
anchors adjust their speech skills, interaction methods
and live broad-cast rhythm in time, and improve user
retention and purchase rate. In addition, for high-value
user groups, LSC can develop differentiated
operational strategies through big data analysis, such
as providing exclusive offers or customized ser-vices,
to improve user loyalty and re-purchase rate.
2.2 Precision Marketing Strategy
Through big data technology, artificial intelligence
and user behavior analysis, LSC can achieve full-link
optimization from user positioning to purchase trans-
formation. The premise of precision marketing is a
deep understanding of the target users (Li, 2022).
First of all, the user portrait is constructed through
multidimensional data analysis, including the data of
live streaming platform, shopping plat-form and
social media (such as viewing record, browsing
behavior, shopping cart and search record), age,
gender, region, interest preference, consumption
power and other basic information. In terms of
precision marketing, merchants can use user portrait
data to push personalized ads and live broadcasts
through social media or platforms to attract target
users to participate in live broadcasts. At the same
time, behavioral data such as purchase frequency and
product preference are added. Group according to
user profiles to develop differentiated marketing
strategies. Secondly, by using the recommendation
algorithm, it shows users personalized goods and
content, which improves the conversion rate of
purchase. For example, according to the user's
interests to recommend suitable broadcast room,
combined with collaborative filtering algorithm or
deep learning technology, the user may be interested
in the goods priority display, improve the click rate,
through real-time analysis of live interactive data
(such as bullet screen, likes, comments) to adjust the
list of recommended goods, enhance the user
experience. Finally, precise advertising will reach the
target user group efficiently. LSC platforms could use
social media, search engines, short video platforms
and other channels to reach target users, and choose
the best delivery time by analyzing the active period
and buying habits of users.
2.3 Data-Driven Innovation in Live
Content
Through data-driven, the live streaming industry is
shifting from "experience oriented" to "data
oriented", which not only improves the efficiency of
content creation, but also helps platforms and creators
achieve more accurate user reach and maximize
commercial value. First, platforms should optimize
the contents and innovation planning. It can help
predict users' attention to certain types of contents
based on data trends and plan live broadcast topics
that will worsen market demand in advance to predict
hot spots (Trabucchi & Tommaso, 2019). The
platform can adjust the direction of content or the
APMM 2025 - International Conference on Applied Psychology and Marketing Management
534

form of engagement with real-time data feedback
(e.g., user likes, comments slowing down). While the
use of generative AI can help creators quickly
generate scripts, footage, or scene designs. Secondly,
the plat-form should improve the efficiency of
promoting live content. The use of the intelligent
recommendation algorithm, combined with user
portrait and live con-tent label can help achieve
accurate content recommendation. Which can
improve the click rates and customer retention rate.
By analyzing the conversion effect of promotion
materials, it can help optimize the promotion content
and channels. According to the user behavior of
different platforms, the distribution policy is
customized to achieve multi-platform linkage. For
instance, short video clips are directed to live
broadcasts. Finally, the platforms should optimize the
income management system. The platforms by
adjusting the advertising type and duration
accordingly to the user's viewing behavior, this can
help achieve the optimal advertising revenue. Predict
user behavior, manage user lifecycle, and provide
customized services to potentially high-value users.
2.4 Real-Time Feedback and
Adjustment Mechanism
LSC uses big data real-time feedback and adjustment
mechanism to optimize live streaming process,
product display and user experience through data
collection, analysis and rapid response to improve
conversion rate and sales. The following is the
specific practice and core links of this mechanism.
LSC platforms collect real-time data in a variety of
ways, including user behavior data such as viewing
duration, interaction frequency, commodity click
rate, and length of stay. Sales data such as real-time
order volume, successful payment rate and
merchandise inventory changes. Interactive data such
as user questions, votes, or engagement in red
envelopes. The above real-time feedback provides a
variety of real-time adjustment strategies for LSC,
including content adjustment, commodity adjustment
and optimizing user interaction (Lu et al., 2002). First
of all, by monitoring the audience's attention to a
certain type of product in real time, the anchor can
increase the introduction time of related products or
adjust the focus of explanation, emphasizing the hot
content. When the data feedback viewing time or
interaction volume decreases, the LSC platform
should adjust the rhythm of live broadcast (such as an
increase in interactive links, lottery or new products).
By giving quick responses to problems and timely
adjust the interpretation or presentation, can help
reduce user loss. Secondly, by having real-time
monitoring of commodity click-through rate and
conversion rate can prioritize the display of hot goods
and avoids unpopular goods that may reduce user
interests. When the data feed-back viewing time or
interaction volume decreases, the LSC platform
should ad-just the rhythm of live broadcast (such as
increasing interactive links, lottery or new products).
The use of real-time inventory monitoring to avoid
user loss due to stock shortages, while improving
conversion by replenishing or recommending
replacement items. Finally, according to the real-time
data of users, the anchor can thank high-value users
by name or respond specifically to improve user
stickiness. If an interactive session (like a raffle or a
red envelope) does not work as expected, adjust the
rules or make the reward more attractive.
3 THE INNOVATIVE WAY OF
DIGITAL TRANSFORMATION
OF LIVE BROADCASTING
PLATFORM
3.1 The Need for Digital
Transformation
Digital transformation is crucial for insurers in the
current market environment. Through digitalization,
customer experience can be enhanced, operational
efficiency improved, risk management capabilities
enhanced and market share expanded. For example,
the use of big data and artificial intelligence
technologies can enable accurate risk assessment and
personalized product recommendations, thereby
increasing customer satisfaction and loyalty (Matt et
al., 2015). At the same time, com-petition in the live
streaming industry is fierce, driving platforms to
build differentiation advantages through
technological innovation and service optimization
(such as personalized recommendation). In addition,
the entry of short video platforms, e-commerce
platforms, and social platforms into the field of live
broadcasting has intensified cross-industry
competition, and also promoted live broadcasting
platforms to improve their technical capabilities and
content diversity.
3.2 Innovation Mode Analysis
LSC is a new retail model that combines live
streaming and e-commerce, and its innovation is
mainly reflected in technological innovation, mode
The Application of Big Data in the Marketing of Live E-Commerce Platform
535

innovation and supply chain and logistics innovation
(Filippetti, 2011). First of all, live streaming e-
commerce not only uses artificial intelligence to
generate personalized live content, virtual anchors or
intelligent customer service, but also uses big data
analysis to accurately recommend products for
consumers. Secondly, celebrities are invited to live
with ordinary people, and the personal influence of
celebrities is used to attract traffic and facilitate
transactions. Finally, LSC partners with local
logistics or instant delivery services to achieve fast
delivery after placing orders and improve user
experience.
3.3 Ecosystem Expansion
The ecosystem of LSC is a complex network that
integrates multiple resources, technologies and
services to support the healthy development and
continuous innovation of the LSC industry. By
leveraging external resources, the ecosystem can be
expanded in terms of marketing and promotion,
related personnel training, and investment (Koenig,
2013). First, by extending live content to social media
and short video platforms, implant brands in
advertisements, and short video promotion can boost
traffic. The use of community operations, such as the
establishment of Wechat, QQ groups and other
private traffic pools, to maintain user stickiness.
Secondly, LSC can provide professional training
courses for anchors, including expression skills,
product recommendation ability, etc. By providing
business operations support, data analysis and live
streaming skills training can enhance consumers'
acceptance and trust in live shopping. Finally, it
supports the growth of start-ups and individual
anchors, and the platform provides financial services
to small and medium-sized merchants, such as loans
and billing.
4 CASE ANALYSIS
4.1 Analysis of Typical Live
E-Commerce Cases at Home and
Abroad
As an important part of modern e-commerce, live
streaming e-commerce plat-form shows diversified
development models at home and abroad. This
section will analyze the main characteristics, business
models and development trends of typical live
streaming e-commerce platforms at home and abroad.
Domestic live streaming e-commerce platforms, such
as Taobao Live (Alibaba), are characterized by an
early start, relying on Alibaba's strong e-commerce
ecosystem, covering all categories of goods, and
significant traffic advantages (Li & Dimitrios, 2006).
Merchants and anchors cooperate closely and
establish a mature supply chain system. The business
model is used to promote the sale of goods through
live broadcasting and earn transaction commission.
Also, by providing advertising services to merchants
can help better generate revenue. With its large user
base, ecological closed loop, and strong data analysis
capabilities, it has increased cooperation with content
creators to improve the diversity of live content.
Foreign live streaming e-commerce platforms, such
as Amazon Live. It is characterized by a professional
anchor team, focusing on commodity demonstration
and evaluation. Relying on Amazon's global logistics
and warehousing system. It has a business model of
selling goods, earning commission and providing
advertising services to brand owners with the help of
broadcast room. With a strong global logistics
network, a rich variety of goods and a mature
consumer base, it will strengthen cooperation with
brands and promote more high-quality goods.
4.2 Successful Case Marketing
Supported by Big Data
The successful live e-commerce cases supported by
big data provide a strong reference for the industry
(Wright et al, 2019). In the study of foreign successful
cases of Amazon live holiday shopping season
promotion, every year during the holiday shopping
season, Amazon launches live streaming events
featuring professional streamers demonstrating
electronics and lifestyle items. Big data is used to
recommend the most popular promotional items
through Amazon's purchase history and review data.
5 CONCLUSION
The application of big data has significantly
transformed the marketing strategies of live-
streaming e-commerce platforms, creating substantial
value for platforms, merchants, and consumers alike.
By analyzing user behavior data, platforms can
generate precise consumer profiles, enabling
personalized product recommendations and targeted
marketing strategies. This data-driven approach
enhances user experience while boosting product
conversion rates and improving the operational
efficiency of live-streaming sessions. Moreover, the
APMM 2025 - International Conference on Applied Psychology and Marketing Management
536

real-time analytics capability of big data empowers
platforms to dynamically adjust their live-streaming
strategies based on audience engagement metrics and
sales performance, thereby fostering stronger user
loyalty and maximizing traffic monetization. In
addition to enhancing marketing outcomes, big data
plays a critical role in supply chain optimization,
inventory management, and market trend forecasting,
providing merchants with data-driven insights to
inform strategic decisions.
However, the integration of big data into live-
streaming e-commerce is not without challenges.
Issues such as data privacy concerns, algorithmic
biases, and the high cost of technology
implementation remain significant obstacles. Ad-
dressing these challenges requires ongoing efforts
from platforms and businesses to ensure ethical,
secure, and cost-effective use of data technologies.
Looking ahead, the convergence of big data with
emerging technologies such as artificial intelligence
and blockchain will further advance the intelligence
and precision of live-streaming e-commerce
marketing. These innovations will not only enhance
the efficiency of marketing operations but also
accelerate the digital transformation of the retail
industry and drive the evolution of consumer
behavior.
The continuous development of big data
technologies promises to empower live-streaming e-
commerce with new possibilities, offering broader
market potential and more profound impacts across
the industry. In conclusion, big data serves as a
powerful catalyst for the innovation and growth of
live-streaming e-commerce. It not only improves
marketing effectiveness but also reshapes the way
businesses interact with consumers in a highly
competitive digital economy. By leveraging the full
potential of big data, live-streaming platforms can
stay ahead in an ever-changing market, delivering
superior value to all stakeholders involved.
REFERENCES
Wang, Y. et al.: How live streaming changes shopping
decisions in E-commerce: A study of live streaming
commerce. Computer Supported Cooperative Work
(CSCW) 31(4), 701-729 (2022)
Luo, X. et al.: Live streaming commerce: a review and
research agenda. Journal of Computer Information
Systems, 1-24 (2023)
Sagiroglu, S., Sinanc, D.: Big data: A review. 2013
international confer-ence on collaboration technologies
and systems (CTS). IEEE, (2013)
Akter, S., Samuel, F.W.: Big data analytics in E-commerce:
a systematic review and agenda for future research.
Electronic Markets 26, 173-194 (2016)
Zhan, Y.Z. et al.: Unlocking the power of big data in new
product development. Annals of Operations Research
270(1), 577-595 (2018)
Mendhe, C. et al.: A scalable platform to collect, store,
visualize, and analyze big data in real time. IEEE
Transactions on Computational Social Systems 8(1),
260-269 (2020)
Li, W.: Big Data precision marketing approach under IoT
cloud platform information mining. Computational
Intelligence and Neuroscience 1, 4828108 (2022)
Trabucchi, D., Tommaso, B.: Data-driven innovation:
switching the perspective on Big Data. European
Journal of Innovation Management 22(1), 23-40 (2019)
Lu, C.Y. et al.: Feedback control real-time scheduling:
Framework, modeling, and algorithms. Real-Time
Systems 23, 85-126 (2002)
Matt, C., Thomas, H., Alexander, B. Digital transformation
strategies. Business & information systems engineering
57, 339-343 (2015)
Filippetti, A.: Innovation modes and design as a source of
innovation: a firm‐level analysis. European Journal of
Innovation Management 14(1), 5-26 (2011)
Koenig, G.: Business ecosystems revisited. Understanding
Business Ecosystems: How firm Succeed in the New
World of Convergence, Brussels, De Boeck, 69-83
(2013)
Li, L., Dimitrios, B. E-Commerce in China: The case of
travel. International Journal of Information
Management 26(2), 153-166 (2006)
Wright, L.T. et al.: Adoption of big data technology for
innovation in B2B marketing. Journal of Business-to-
Business Marketing 26(3-4), 281-293 (2019)
The Application of Big Data in the Marketing of Live E-Commerce Platform
537