Artificial Intelligence-Driven Marketing Strategy Optimization:

Innovative Convergence of Big Data and Personalized Marketing

Weiqing Yan

Computer Society, Neusoft Institute Guangdong, 528225 Guangdong, China

Keywords: Artificial Intelligence, Marketing, Big Data Analysis, Personalized Marketing.

Abstract: Personalised marketing has become one of the core strategies of modern marketing. The core question of this

study focuses on how to take advantage of artificial intelligence and big data to improve the efficiency of

personalised marketing while maintaining data privacy and security. The specific application of artificial

intelligence in personalised marketing is analysed in detail through the literature analysis method. Through

big data analysis, consumer needs can be understood more effectively, and more targeted marketing strategies

can be developed, thus improving marketing effectiveness and customer satisfaction. However, the

application in personalised marketing also faces some issues. Among them, data security and privacy are

among the most critical issues. To develop AI systems, a large amount of personal data needs to be collected

and analysed, which raises concerns about the privacy and security of user information. Aiming at these

problems, this paper puts forward a series of suggestions. Firstly, enterprises should establish a perfect data

management system to ensure the quality and security of data. Secondly, enterprises need to build a ‘balance

model between data privacy protection and personalised marketing’ to jointly develop marketing strategies

and continuously optimise personalised marketing algorithm models.

1 INTRODUCTION

Artificial intelligence technology began in the 1950s

and has now become a global hotspot for scientific

and technological research and application. With the

rapid development of new technologies such as big

data, cloud computing, and the Internet of Things, the

application scenarios of AI technology have been

greatly expanded. With the arrival of the Internet era,

the field of marketing has experienced radical

changes, the traditional advertising channels can no

longer meet the needs of enterprises for marketing

effectiveness. Enterprises need to leverage AI

technology and rely on big data analysis to gain a

deeper understanding of users' behavioral patterns

and consumption habits and discover potential market

opportunities.

This study is useful to guarantee the scientificity,

rigor, and accuracy of personalized marketing

strategies, to improve the efficiency of personalized

marketing, and to ensure that personalized marketing

is better put into the market to form productivity. It is

very meaningful to make greater use of the role of big

data as a driver of its development, to reduce the input

of ineffective costs, and to promote the rational and

efficient functioning of society.

While the application of artificial intelligence and

big data on the Internet has brought convenience to

people's lives, it has also given rise to many problems

that need to be solved. Such problems can have a

great impact on people's lives and social stability.

This study focuses on three specific aspects: data

security, privacy protection, and personalized

marketing efficiency. Literature analysis was used to

find and read relevant information and literature, and

the advantage of this method is that it can well

analyze how to improve the efficiency of

personalized marketing by taking advantage of

artificial intelligence and big data while maintaining

data privacy and security.

2 LITERATURE REVIEW

Zhang Weiyu in the Artificial Intelligence

Background of Modern Enterprise Marketing

Strategy Thinking. This article studies the use of

artificial intelligence machine learning algorithms to

optimize the marketing strategy for modern enterprise

marketing to provide thinking, in the optimization of

artificial intelligence marketing aspects of the

contribution to this study. Still, in the data collection

Yan, W.

Artiﬁcial Intelligence-Driven Marketing Strategy Optimization: Innovative Convergence of Big Data and Personalized Marketing.

DOI: 10.5220/0014053500004942

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 45-50

ISBN: 978-989-758-791-7

and analysis of the content involved in the content of

the little, this paper will start from the aspect of data

collection and analysis, explore the data collection

methods, and from which perspective to analyse the

data to supplement the existing research gaps.

collection methods and from which perspectives to

analyse the data to supplement the existing research

gaps (Zhang, 2024).

Guan Fuzhong, in his article New Marketing

Engine for Operators under the Wave of Artificial

Intelligence, researched the need for operators to

make use of big data models to make data more

accurate and reliable, as well as the risks and

challenges foreseen by artificial intelligence, and

contributed to this research in building a collaborative

and efficient big data model. However, not much has

been done in the area of personalised

recommendation, and this paper will start from the

aspect of personalised recommendation, focusing on

the question ‘How to improve the effect of

personalised recommendation from more aspects?’.

to supplement the existing research gaps (Guan,

2024).

Zhang Shuo studied the use of big data analysis to

enhance personalised influence and the use of

advanced technology to improve marketing

efficiency in the article Research on the Innovation

Path of Enterprise Marketing Strategies in the Era of

Digital Economy. It contributes to this research in

terms of innovative marketing strategies, but the

content of natural language processing is not

comprehensively researched, and this paper will start

from the natural language processing aspect to carry

out research to supplement the existing research gaps

(Zhang, 2024).

The researcher explores the specific application

scenarios and effects of big data and artificial

intelligence in personalised marketing through case

studies and empirical research. The focus is on how

big data analytics can be used to develop more

accurate marketing strategies and the decision-

making role of AI in assisting marketing decisions.

This shows that the application of AI in marketing

focuses on data collection and analysis, personalised

recommendations, natural language processing, and

predictive analytics.

Firstly AI technology helps companies in data

collection and analysis to collect and analyse

customer data more effectively, including multi-

channel data such as social media, mobile apps,

online shopping, search engines, etc., to better

understand customer needs and behaviours.At the

same time, personalised recommendations are based

on customers' historical behaviours and interests,

dividing them into different sub-groups, which can

provide personalised product and service

recommendations and improve customer satisfaction

and purchase conversion rates. Secondly, natural

language processing helps companies to better

understand and process customer feedback and

improve customer service quality through techniques

such as sentiment analysis and intent recognition.

Finally, prediction models based on big data and AI

can predict future consumer behaviour and market

trends, providing a basis for corporate marketing

decisions.

Despite the remarkable success of AI and big data

in marketing, it still faces risks in terms of data

privacy and security, technology integration, and

talent development. The convergence of AI-driven

marketing optimisation strategies and big data

personalised marketing provides companies with

unprecedented marketing opportunities. By deeply

analysing customer data, companies can meet

customer needs more accurately and increase

customer satisfaction and loyalty. At the same time,

personalised marketing can also significantly

improve marketing efficiency and reduce marketing

costs. With the continuous development and

improvement of AI and big data technology,

personalised marketing will show its great potential

and value in more industries and fields.

3 ALIBABA'S PERSONALISED

MARKETING STRATEGY AND

THE APPLICATION OF AI

TECHNOLOGY

3.1 Alibaba's Personalised

Recommendation Mechanism

Alibaba has accumulated a large amount of user data

through its e-commerce platform, firstly using user

browsing, purchasing, searching, and other

behavioural data to build an accurate user profile. By

establishing a user profile, companies can more

accurately understand the user's needs, interests,

preferences, and other information, so that they can

more accurately locate the user group. In this way,

when personalised marketing is carried out,

companies can better target specific user groups to

develop marketing strategies and improve the

accuracy and effectiveness of marketing (Letter,

2024).

Secondly, sophisticated algorithms, including

collaborative filtering and content recommendation,

APMM 2025 - International Conference on Applied Psychology and Marketing Management

are employed in conjunction with machine learning to

conduct comprehensive data mining and analysis,

thereby facilitating the generation of precise

recommendations. And real-time analysis of the

user's latest behavioural data, and timely update of the

recommended content to ensure the timeliness and

accuracy of the recommendation.

Finally, when collecting and using user data, Ali

strictly abides by its privacy policy to ensure the

security and compliance of user data and enhance

users' trust in the recommendation system. It will also

continue to optimise and improve its recommendation

algorithms and improve the accuracy of

recommendations and user satisfaction by

introducing new technologies and methods.

3.2 Data Security and Privacy

Protection Measures

Due to the diversity and complexity of data sources,

the quality and reliability of data vary, and there may

be problems such as missing data, errors, and

duplication. These problems will affect the accuracy

and credibility of the data, which will bring some

difficulties to the marketing decisions of enterprises

(Guo et al., 2024). Alibaba in response to the data

privacy and security issues in big data analysis, the

first to take the data encryption and desensitisation

processing, data encryption using the key and

encryption function to complete the replacement and

alteration of computer storage information, the

purpose is to make the data information to change the

basic changes, to enhance the security and integrity of

the information transmission, use, the receiver only

needs to master the key and decryption function can

be the data information All restored (Wang and Ma,

2024). For data that needs to be used for analysis,

testing, and other non-production environments,

Alibaba will also perform desensitisation to reduce

the sensitivity of sensitive information.

Secondly, strict data access control has been

adopted in the management. This refers to the fact

that only authorised users have access to specific

datasets and that each user can only access data within

his/her privileges. It will record all the behaviours of

data access and operation, including access time,

access user, operation type, etc. so that it can be traced

and investigated in the event of a security incident.

Most importantly, Alibaba has formulated a

comprehensive data security management policy,

which specifies the security requirements for all

aspects of data collection, use, storage, and

destruction. Alibaba regularly conducts data security

training for its employees to raise their awareness of

and attention to data security and ensure that they

strictly comply with data security regulations in their

work.

4 SYNERGIES BETWEEN BIG

DATA AND AI IN MARKETING

4.1 Big Data Analytics to Enhance the

Effectiveness of Precision

Marketing

Businesses can better understand their target markets

and consumer needs by collecting and analysing large

amounts of data, including consumer behaviour,

purchase history, social media interactions, and more.

This data-driven approach helps organisations make

more accurate and effective marketing decisions

(Jiang, 2024). This data constitutes the three-

dimensional dimension of the user profile, which

reflects the immediate needs of the user and also

predicts his or her potential purchase intention. And

through personalised recommendation algorithms, it

recommends products or content to users that best

meet their needs. For example, when a user browses

a certain type of product on Taobao or Tmall, the

system will analyse the data based on the user's

historical behaviour and the behaviour of similar

users to recommend other products that the user may

be interested in. At the same time, AI technology can

integrate and analyse data across platforms and

channels. By analysing users ‘behaviour and interests

on social media, as well as their purchase history and

preferences on e-commerce platforms, Alibaba can

gain a deeper understanding of users’ needs and

consumption habits, to provide users with more

personalised services and recommendations.

4.2 Personalised Recommendations

and Customer Stickiness

Improvement

Brands should fully explore customer full lifecycle

data, including browsing, searching, purchasing,

evaluation, after-sales, and other aspects of the data,

through data integration, depicting the customer

journey map, identifying the key touchpoints, and

optimising the key aspects of the experience. Using

personalised recommendation engine, technology

intelligent customer service, and other technical

means, insight into the personalised needs of

customers, to provide tailor-made products, content,

and services, so that customers can feel the ‘exclusive

Artiﬁcial Intelligence-Driven Marketing Strategy Optimization: Innovative Convergence of Big Data and Personalized Marketing

customised’ experience (Wang et al., 2024). At the

same time, personalised recommendation not only

allows users to see the products they like, but also

reduces the time they spend searching and screening

products, making shopping more convenient and

efficient. What's more, the personalised

recommendation system can also adjust the

recommendation strategy in real-time according to

the user's behavioural changes. For example, when a

user shows strong interest in a certain product, the

system will recommend similar products or

collocation promptly. This kind of cross-selling helps

to increase the purchase volume of the user and

improve the unit price and sales. This ability to adjust

dynamically makes the personalised recommendation

system more flexible and intelligent, as well as better

able to meet the diverse needs of users, resulting in a

higher return rate and better user reputation.

4.3 The Challenge of Balancing Data

Privacy and AI

Alibaba has adopted a series of strict security

measures to protect user information. For example,

they take the help of cryptographic knowledge and

related techniques to encrypt a section of data

information of the computer to ensure the security of

user data during transmission and storage (Wang and

Ma, 2024). It also prevents data from being accessed

or leaked by unauthorised personnel through

mechanisms such as access rights control and data

backup. Ali has established a comprehensive data

security management system in response to data

leakage and privacy issues, including the formulation

of data security policies, training employees in data

security awareness, and conducting regular security

audits and risk assessments. These measures not only

raise employees' attention to data security but also

ensure the continuity and effectiveness of data

security management.

In addition, Alibaba has a strong focus on

transparency and security when it comes to

personalised marketing. Users are informed of the

purpose and scope of the data at the time of use, and

their consent is obtained before personalised

recommendations are made. Technical means are also

used to ensure the fairness and accuracy of the

recommendation process and to avoid users being

treated unfairly or misled.

4.4 Big Data and AI for Personalised

Shopping Surprises

Alibaba through big data and AI technology can

accurately analyse customer behaviour and

preferences, such as Taobao's ‘guess you like’ and

history will recommend products that meet the

interests of the customer, so that customers have a

‘just what they want’ feeling, bringing surprises. At

the same time, the system can be based on the

customer's historical data to explore potential needs,

recommending products that they may not be aware

of but need, such as recommending related

accessories after the customer purchases

photographic equipment, to stimulate the desire to

buy and add shopping surprises.

The variety of goods recommended through the

personalised recommendation system is rich,

covering niche and novelty products, such as

personalised and innovative products on Taobao, and

cultural and creative products, which open the door to

a new world for customers to access different goods

with artificial intelligence as the guide and big data as

the basis. The discovery of products that meet the

user's needs will be recommended to customers

promptly to the newly listed products, so that it is the

first time to understand and buy, to meet the freshness

of the psychological, such as the launch of a brand of

new electronic products and customers concerned

about the brand's promotional activities will be

recommended to the relevant interest in the customer.

5 AI-DRIVEN PERSONALISED

MARKETING EFFECT MODEL

5.1 Data Insight Driven Personalised

Recommendation Enhancement

Mechanisms

The construction of consumer behaviour models

based on big data is a core aspect of consumer

behaviour analysis. Through in-depth mining and

analysis of consumer data, enterprises can construct

models that reflect the laws and characteristics of

consumer behaviour, and then provide a scientific

basis for the formulation of marketing strategies

(Zhang and Chen, 2024).

By analysing the recommended content in more

detail, including textual content, images, videos, etc.,

more features such as semantics, sentiment, and

themes are extracted for a more accurate

understanding of the meaning of the content. Match

APMM 2025 - International Conference on Applied Psychology and Marketing Management

the user's behaviour and content characteristics to

recommend more personalised content for the user.

And with the continuous accumulation of user data

and the continuous generation of new content, it is

constantly optimised and adjusted to improve the

accuracy and diversity of recommendations.

5.2 Data Privacy Protection and

Personalised Marketing Balance

Model

To balance personalised marketing and privacy

protection, the government and enterprises must work

together to ensure its effective implementation,

through the government's enactment of laws to

regulate the protection of data privacy, and the

establishment of a sound data security management

system by enterprises. Systematising mechanisms for

balancing data privacy protection and personalised

marketing. A model is proposed that contains data

encryption, user consent, transparency, and

decentralised storage approach to protect user data

using data encryption and desensitisation process

(Wang and Ma, 2024). Demonstrate how to improve

marketing effectiveness while ensuring privacy.

Personalised marketing efficiency while maintaining

user rights and ensuring consumer trust in the

business.

How introducing affective computing in

personalised recommendations can enhance the user

experience. For example, AI identifies the real-time

emotional changes of users through sentiment

analysis, so as to adjust the recommended content and

further personalise it to meet the needs of users,

making the research more cutting-edge and richer.

However, it also makes personalised marketing easy

to fall into the predicament of ‘pseudo-

personalisation’, over-reliance on algorithmic

recommendations, neglecting emotional interaction,

and the user experience being superficial and

programmed (Wang et al., 2024).

In the data privacy section, add the ethical and

legal challenges of AI and big data applications of

affective computing. It is possible to discuss how

companies can comply under different legal

frameworks, such as the EU's GDPR rules, and

explore how to deal with compliance issues while

innovating in technology, adding depth and practical

application to the article.

5.3 Intelligent Interactive Trends in

Personalised Marketing

Add a look at future trends in personalised marketing,

such as incorporating emerging technologies such as

AI voice assistants, virtual reality (VR), and

augmented reality (AR), and predict how these

technologies will make personalised marketing more

interactive and enhance the immersive customer

experience. Combined with the recent emergence of

the ‘meta-universe’, the company will be able to ask

questions about the future development of human

trends, grasp the future trend of personalised

marketing, and achieve more efficient big data

analysis and prediction, to better understand user

needs, improve user experience, and increase market

share and brand value. At the same time, enterprises

should pay constant attention to the development

trend of emerging technologies and continuously

carry out product innovation and technology

upgrading, which can make use of technologies such

as virtual reality and augmented reality to provide an

immersive shopping experience and attract

consumers. In daily operations, enterprises should

actively explore the application of 5G, IoT and other

technologies in marketing to improve marketing

efficiency and user experience (Qi, 2024).

Second, collecting and analysing consumer data is

the cornerstone of personalised marketing.

Enterprises collect data such as consumers' purchase

records, search records, social media activities, etc.,

and use advanced analytical tools and algorithms to

dig deeper into these data. This analysis not only

reveals consumers' explicit needs but also uncovers

underlying consumer trends and preferences. For

example, by analysing consumers' online behaviour,

companies can learn which products or services are

more popular and which marketing messages

resonate better with consumers (Mingqi, 2024). It can

also be based on several classical deep learning

models, e.g., BiLSTM - TabNet model, to accurately

identify and classify customers to implement more

refined marketing strategies and introduce Whale

Optimisation Algorithm (WOA) to further enhance

the model performance to improve the classification

accuracy and practicality. Understanding customers

from data, to carry out personalised recommendations

and improve customer stickiness (Li et al., 2024).

6 CONCLUSION

AI and big data technologies offer great potential for

personalised marketing to improve, especially in

Artiﬁcial Intelligence-Driven Marketing Strategy Optimization: Innovative Convergence of Big Data and Personalized Marketing

terms of increasing accuracy and user experience.

The findings of this study are that AI provides

companies with accurate user profiling, market trend

prediction, and marketing effectiveness evaluation by

intelligently analysing massive amounts of data. Not

only does it help companies develop more effective

marketing strategies, but it also significantly

improves the accuracy and efficiency of marketing

decisions. From this, it further concludes that its

research is based on big data, companies are also able

to provide customised product recommendations and

marketing messages to their customers, which greatly

satisfies consumer demand for personalised and

customised services.

However, the application of AI and big data in

personalised marketing also faces certain challenges,

with data security and privacy protection issues

becoming increasingly prominent. By strengthening

data privacy protection, companies can further

enhance users' trust in the platform and ensure the

stability of their personalised marketing.

In the future, with the continuous progress and

cost reduction of AI and big data technologies,

personalised marketing will usher in a broader

development prospect. Enterprises should aim to

actively embrace these new technologies and

continuously explore new marketing theories and

practical directions for in-depth inquiry. In order to

adapt to the increasing level of digitalisation and the

diversification of consumer needs.

REFERENCES

W.Y. Zhang, Strategic thinking of modern enterprise

marketing in the context of artificial intelligence. China

Exhibition. 17: 115-117 (2024)

F.C. Guan, A new marketing engine for operators under the

wave of artificial intelligence. Commun. Enterp.

Manag. 01: 62-64 (2024)

S. Zhang, Research on the innovation path of enterprise

marketing strategy in the era of digital economy. Mall

Mod. 19: 99-101 (2024)

P. Letter, Research on new media personalised marketing

strategy based on user profile. Collect. Writ. Edit. 06:

59-61 (2024)

X.Z. Guo, W.J. Shi, J.G. Cui, et al. Research on the

innovation of enterprise marketing strategy in the era of

big data. Mall Mod. 19: 108-110 (2024)

D.M. Wang, Y. Ma, Application of data encryption

technology in computer network security protection.

China New Commun. 26: 69-71 (2024)

H. Jiang, Research on the innovation and practice of

marketing strategy in the digital era. Invest. Coop. 08:

178-180 (2024)

M. Wang, X.C. Li, W. Zhang, Research on corporate brand

marketing strategy in the context of big data. Mod.

Mark. (Latter) 10: 166-168 (2024)

D. Zhang, D. Chen, Introduction to consumer behaviour

analysis and personalized marketing practice driven by

big data. Mod. Bus. 21: 51-54 (2024)

S.N. Qi, Research on the integration of enterprise marketing

strategy and digital industry. High Technol. Indust. 30:

85-86 (2024)

P. Mingqi, Personalized marketing strategies: How to

leverage big data to meet consumers' personalized

needs. Acad. J. Bus. Manag. 6 (2024)

Y. Li, C. Meng, J. Tian, Z. Fang, & H. Cao, Data-driven

customer online shopping behavior analysis and

personalized marketing strategy. J. Organ. End User

Comput. 36: 1-22 (2024).

APMM 2025 - International Conference on Applied Psychology and Marketing Management