Search

The purpose of this paper is to study how to effectively collect all kinds of consumption information that can be detected by big data on the basis of existing data, and provide support for cigarette marketing and marketing of tobacco industry for precision marketing. In this paper, based on the big data analysis of cigarette data marketing methods and strategies to carry out research, first of all, elaborated the impact and value of big data on cigarette data, then analyzed the methods used in the marketing strategy under the background of big data, and finally analyzed the marketing strategy of Huaihua company of Hunan tobacco company. The results show that the overall performance of Huaihua tobacco company’s cigarette marketing strategy is good, and its brand marketing maintains above 20%.

Since the birth of the Internet, advertising has been developing rapidly through the combination of Internet. Since the first Internet advertisement was released in China, China's Internet advertising has been on the way of development. The rapid development of Internet advertising has brought many opportunities to social economy, but at the same time, it also brings many problems that have not been encountered before. The purpose of this paper is to design a marketing strategy based on big data, collect, analyze and process customer information, so as to realize marketing in a more accurate way. This paper makes statistical research on the advertisement of websites in the precision marketing of big data. Through statistics, 69 web advertisements are found on 5 websites. 25 emails of the author are rubbish advertisements. Therefore, we can see that the current network marketing ethics is seriously out of standard, and the relevant countermeasures are put forward. According to the experiment, the banner advertisement accounts for 67% of the five websites’ advertisements, 4% of the advertisements are plug-in advertisements, 26% are text link advertisements, and 3% of the advertisements are floating picture advertisements. There are the above percentage can be seen, in these several websites, banner advertising is more used, followed by text link advertising.

At present, the market of mobile communications industry tends to be saturated, and the main source of users is realized through the conversion between communications carriers. The competition among the three domestic carriers for existing users is becoming increasingly fierce. By using precision marketing theory and big data analysis methods, this paper takes China Mobile in G Province as an example to study the retention strategy for existing users of communications operators in the context of facilitating faster and more affordable Internet connection and developing 4G services, analyze the existing problems, and put forward corresponding optimization measures and suggestions.

With the continuous expand of electronic commerce, online and offline electronic commerce models are widely used. In view of big data theory, business model theory and business model wheel structure theory in big data era, this paper propose the wheel structure of cross border electronic commerce model in big data era, and makes concrete construction from four levels: consumers, market supply, enterprises and profit model. At the same time, find the breakthrough point of big data mining for precision marketing application, and far use the big data mining method to get the precision marketing strategy in view of the breakthrough point. Through the online and offline electronic commerce user data mining, we can grasp the development trend of electronic commerce, make timely adjustments according to the situation, and realize the effective use of online and offline electronic commerce user data.

As an important field of China's social and economic development, big data plays an important role in channel expansion, service popularization, and precision marketing. The application of big data technology in the financial industry can effectively broaden the marketing channels of financial enterprises and improve their popular service levels. Big data technology is an important support for the healthy development of the financial industry. Used in precision marketing, credit rating, asset pricing, etc. Although it has promoted the informatization development of the financial industry, there are also certain risks. Risks and vulnerabilities such as data security, supervision, transmission rate, rules, etc. frequently appear, threatening the healthy development of the financial industry. On the basis of explaining the application of big data in the development of the financial industry, it analyzes the existing risks in depth, and proposes targeted regulatory measures based on the decision tree algorithm to promote the healthy and sustainable development of the financial industry.

The current sloppy marketing channels and high cost-efficiency ratio of real estate companies make the sales performance of real estate companies poor. How real estate companies can eliminate inventory, reduce marketing costs and raise away from sales performance is the main problem facing real estate companies at present. Based on big data technology, this paper first analyzes the real estate big data precision marketing steps as well as processes. Then, through the analysis of real estate customers' purchase process decision, the design framework of big data precision marketing for real estate companies is proposed. Finally, the current status of real estate marketing is combined with the current market rules to study the marketing strategies that meet the current market rules.

Using machine learning analysis methods could provide an important reference basis for the company's precision marketing. This paper used a series of machine learning analysis methods on the YouTube channel dataset. These algorithms include linear regression, correlation analysis, k-means cluster analysis, and social network analysis. Based on the results of these algorithms, it can be concluded that a moderate negative association exists between length-view, length-ratings, and length-comments where length is the time length for a specific video while views-ratings, views-comments, ratings-comments are positively associated.

Understanding citizens' main transportation modes at urban scale is beneficial to a range of applications, such as urban planning, user profiling, transportation management, and precision marketing. Previous methods on mode inference are mostly focused on utilizing GPS data with high spatiotemporal granularity. However, due to high costs of GPS data collection, the previous work typically is in small scales. In contrast, the cellular data logging interactions between cellphone users and cell towers cover much higher population given the ubiquity of cellphones. Nevertheless, utilizing cellular data introduces new challenges given their low spatiotemporal granularity compared to GPS data. In this paper, we design CellTrans, a novel framework to survey users' main transportation modes (public transportation or private car) at urban scale with cellular data. CellTrans extracts various mobility features that are pertinent to users' main transportation modes and presents solutions for different application scenarios including when there are no labeled users in the studied cities. We evaluate CellTrans on two real-world large-scale cellular datasets covering 3 million users, among which 2,589 users are with labels. We assess our method not only quantitatively with labeled users, but also qualitatively with the whole population. The experiments show that CellTrans infers users' main transportation modes with accuracy over 80% (with a performance gain of 20% compared to state-of-the-art), and CellTrans remains effective when applied at urban scale to the whole population.

Purpose The purpose of this paper is to investigate post-purchase regret and its relationships with complaint and risk aversion in a four-dimensional framework. Design/methodology/approach Using 548 effective samples, this study employed structural equation modeling to test proposed hypotheses. Findings Based on levels of perceived self-responsibility, post-purchase regret due to forgone alternatives, under consideration and over consideration was positively associated with customer complaining, whereas post-purchase regret due to significance change exhibited no such correlation. Moreover, a higher level of risk aversion increased the effect of utilitarian motivation on post-purchase regret due to over consideration but decreased this effect on post-purchase regret due to under consideration. Research limitations/implications First, regret can positively influence consumer complaints. Next, consumers are unlikely to complain to third parties unless they experience strong action regret. Finally, risk aversion can alleviate or reinforce the effect of utilitarian motivation on regret. Future research could examine the customer group who feel less or no regret of their purchases to contribute to regret theory. Practical implications To reduce regret among such consumers, marketers are advised to apply precision marketing techniques to reach their target consumers. Second, to forestall customer regret due to forgone alternatives, sellers should proactively provide target buyers with information regarding their products and those of competing brands. Third, another method of minimizing regret is to ensure that consumers’ risk-aversion activities are effective. Originality/value This study empirically demonstrated a multidimensional scale of regret to illuminate the multicausal role of regret in relation to consumers’ complaining and risk-aversion behaviors.

CTR (Click-Through Rate) Prediction is the key to precision marketing of enterprises, which aims to estimate the probability of a user to click on a given item through combination and synthesis of features. In this paper, a novel feature generation method based on multi-kernel convolutional neural network is proposed. The method uses multi-kernel convolutional neural network to generate local features and recombine them to generate new features. By combining it with DNN (Deep Neural Network) further, a unified model Depth Factor Decomposition Machine Based on Multi-kernel Convolutional Neural Network (DFMBMCNN) is defined. DFMBMCNN utilizes multi-kernel convolutional neural networks to identify sparse but important feature interactions, which can learn arbitrary low-order and high-order feature interactions implicitly. Our comprehensive experiments prove that DFMBMCNN outperforms state-of-the-art models and explore the optimal performance of DFMBMCNN.

With the development of big data technology, predicting users’ purchasing intentions through historical data of users' purchasing behaviors has become an essential strategy for companies to carry out precision marketing and increase sales volume. The data of users’ purchasing behavior is characterized by a large amount, substantial variability, and potential long-term dependency. Therefore, the bidirectional long short-term memory neural network (BiLSTM) model is used in this paper to predict the user's purchasing behavior. First, the model takes user ID as the benchmark of the sequence, capturing the fluctuation law of the user purchase volume and fully mine the long-term dependency of user's purchasing behavior. Second, the BiLSTM model adaptively extracts features, realizes "end-to-end" prediction of user purchase behavior, and reduces feature engineering's subjectivity. This paper verifies the effectiveness of this method based on the real user purchasing behavior data sets. The experiment results prove that the BiLSTM method has high accuracy in the prediction of user purchase behavior.

In recent years, big data has gradually become an important part of people's life. In this case, software that provides ratings for various services (such as catering or accommodation) has emerged in large numbers. These softwares help consumers to comment on their consumption experience in a restaurant, hotel or other stores, such as leave ratings, feedback deficiencies, express praise, etc. These could provide customers who have not been to the store with some consumption suggestions. Such review data provides the possibility for businesses to make service defect analysis. Businesses can improve their services through the shortcomings of the most feedback in the comments, or keep the aspects of the reviews that are generally praised. This paper will use the catering industry as an example, combine review data with the characteristics of the business, distinguish them by different levels of consumption, then construct regression and classifier models. The ultimate goal of this paper is to help businesses find the key reasons that affect their rate (bonus or defect) under a certain consumption level, in order to help businesses achieve the purpose of precision marketing.

The extensive application of the big data in the field of the business world has made a tremendous change in the marketing practice. All kinds of the marketing activities have been becoming more personified, diversified and precise. The precision marketing is a typical one. How does the enterprise make a full use of the precision marketing under the big data to serve its whole operational activity is worthy to be discussed. So, the paper first expounds the roles of the big data on the marketing by way of the document research. Then it analyzes the changing trend of the marketing under the big data and finally puts forward some tactics when the enterprise is engaged in the precision marketing under the big data such as building the platforms for the precision marketing, precise marketing positioning and setting up a perfect customer service system and so on.

With the outbreak of the new technological revolution cross-border e-commerce came into being, building a new way for enterprises to export goods, a trade method that binds commodity trade with Internet information technology to form a convenient and open trade system and achieve trade interconnection of global economies. Many Chinese enterprises participate in cross-border e-commerce exports, but their export marketing strategies have drawbacks, and their marketing targeting and precision are not high, which hinder Chinese cross-border e-commerce enterprises from carrying out international marketing. In the context of big data, cross-border e-merchants can use collected data to establish a customer database, build a customer portrait model through machine learning technology, and use personalized recommendation systems to realize accurate marketing with two-way customer interaction. To address the problems in cross-border e-commerce marketing in the context of big data, this paper studies the user behavior data generated by cross-border e-commerce. Based on a large amount of low-value density behavioral data of cross-border e-commerce consumers, this paper designs a cross-border e-commerce precision marketing system applicable to processing user behavioral data, and provides a reference for those who are engaged in cross-border e-commerce.

To promote the information sharing of orders, production capacity and channels, and support core enterprises to play the synergistic linkage role of information flow on upstream and downstream, production, supply and marketing, with the advocation and support on digital supply chain construction from the Chinese government, this paper focuses on the guidance of market information data to the formulation of precision marketing strategy of featured agricultural products. Taking the questionnaire data of 927 respondents in Shenfu, Liaoning Province as an example, a statistical model was used to analyze the characteristics of consumers’ demand of agricultural products with calcium fruit characteristics, and the important factors that affect their purchase intention. In this way, targeted precision marketing suggestions are put forward. In addition to demonstrating the role of data in precision marketing of featured agricultural products, this research helps to accelerate the digital transformation of the industry and strengthen the new driving force of the real economy.

It is an important part of precision marketing to identify potential consumer members of specific activities in pharmacies based on the big data formed by members' historical consumption information and participation information. The problem of consumer member prediction is abstracted as the binary classification problem of whether the members will use the discount to consume in the drugstore after the drugstore gives the discount to the members. In order to solve the limitations of the traditional marketing model applied to the drugstore and the low accuracy of predicting consumer members, this paper proposes a multi angle feature expression and prediction model for drugstore members. According to the characteristics of pharmacies, such as the particularity of pharmacies and the association between drugs and members' diseases, this paper puts forward a variety of new features from the three perspectives of members' attributes, dynamics and consumption, and constructs a feature set by combining the new features with traditional consumption features. Through a variety of machine learning algorithms to build pharmacy consumer member prediction model and comparison, the results show that the ensemble learning algorithm based on XGBoost has high accuracy in consumer member prediction.

In recent years, the development of e-commerce platforms has been gaining momentum, which has made the mining and marketing of e-commerce data more and more critical. Major e-commerce platforms and companies are starting to analyse basic information about their customers, extracting useful information from it, accurately screening customer needs and finally developing targeted marketing programmes that can reduce advertising costs while also generating revenue for the company. Based on the background of big data, this paper firstly composes and integrates the theoretical research on big data and precision marketing, analyses the current marketing status of e-commerce, develops a precision marketing plan that meets the characteristics of e-commerce, and combines the big data platform of e-commerce and personalised precision marketing system to adopt a variety of marketing methods in order to facilitate enterprises to optimise and innovate their existing precision marketing strategies and improve their business performance.

At present, there is a lack of in-depth quantitative analysis and research results on the tourist satisfaction of tourism routes. In order to make up for the vacancy in such research field, this paper takes the satisfaction mining of Guizhou industrial heritage routes as an example, and performs relevant research on the interaction with customers and emotional analysis based on social networking platform. First, we establish a theoretical model that affects the intention of sustainable use of the website, and through the expert scoring method to weight the indicators, and sort out the evaluation system of customer satisfaction of tourism website. Then, by analytic hierarchy process, it is combined with empirical analysis to verify the research model and hypotheses, calculate the comprehensive weight of each index, and use the structural equation model to test the hypothesis model of the impact of tourism website interaction on customers and satisfaction. Finally, it is proved to provide personalized and differentiated services and precision marketing.

The rise of self-media, the widespread use of Internet of Things (IoT), and the speed of information dissemination has been greatly increased. The rapid development of the scale and quantity of e-commerce in China, the marketing requirements of e-commerce are constantly innovative. Now, we are able to access rich data conveniently. How to extract the relevant data needed by the e-commerce industry from the massive data and multi-dimensional data has become the direction of big data technology development. Based on the analysis of theories and methods related to big data and precision marketing, this paper composes and studies the application of precision marketing in e-commerce in the era of big data. This paper discusses the method of realizing accurate marketing of goods based on big data technology in the mobile Internet environment, establishes the research architecture of accurate marketing in the context of big data, constructs customer portrait model through neural network, and uses it to apply personalized recommendation system to realize accurate marketing of goods.

The development of e-commerce and the Internet has promoted the rise of the short video shopping platform called TikTok. The increasing scale of trading on the TikTok platform has aroused the increasing concern of people regarding practice and theory, but the influence mechanism of its precision marketing on consumer buying behaviour remains unclear. Combined with the ‘Stimulus–Organism—Response’ framework and Eroglu’s consumer online shopping response model, this study takes precision marketing as an independent variable and online consumer behaviour as a dependent variable. The perceived value of online shopping consumers is the mediating variable, whereas their extroversion is the moderating variable to establish the model. Through a network questionnaire, information is collected from 251 consumers. The positive correlation between precision marketing and the perceived value of online shopping consumers and purchase behaviour is confirmed by empirical research; the relationship between precision marketing and online consumer behaviour is mediated by consumer perceived value. The extraversion of online shopping consumers has a positive moderating effect on the relationship between their perceived value and precision marketing, including the above mediating effect on such a perceived value. The above conclusions provide theoretical basis and practical enlightenment for the network platform to improve its precision marketing effect.

Small and medium-sized enterprises (SMEs) are an important part of the national economic system, which can promote employment, improve people's living standards, and promote economic development and technological innovation. In the new business environment based on big data and artificial intelligence, it is a key issue for SMEs to flexibly use big data services, design competitive marketing strategies, and achieve efficient market management. This paper will explore the impact of marketing environment changes on SMEs in the era of big data, and improve the marketing efficiency of SMEs by establishing relevant models based on big data analysis.

Many state-of-the-art researches focus on predicting infection scale or threshold in infectious diseases or rumor and give the vaccination strategies correspondingly. In these works, most of them assume that the infection probability and initially infected individuals are known at the very beginning. Generally, infectious diseases or rumor has been spreading for some time when it is noticed. How to predict which individuals will be infected in the future only by knowing the current snapshot becomes a key issue in infectious diseases or rumor control. In this report, a prediction model based on snapshot is presented to predict the potentially infected individuals in the future, not just the macro scale of infection. Experimental results on synthetic and real networks demonstrate that the infected individuals predicted by the model have good consistency with the actual infected ones based on simulations.

For the past few years, thanks to the booming development of mobile Internet and big data, the combination of mobile Internet and big data technology has created a new mobile Internet precision marketing method. However, because the technology is so imperfect, although many enterprises have applied the technology for marketing, there are still many deficiencies. Therefore, put forward the data analysis research of marketing development status in the era of big data. The author investigated and studied the current situation of mobile Internet marketing in the context of big data, and analyzes the problems existing in the current mobile Internet precision marketing and the reasons behind the problems. In consideration of these disadvantages, this paper further proposes the optimization and improvement strategy. The optimization strategy can adapt to the majority of enterprises, reduce capital investment at the same time, and enhance of internet marketing. Finally, in order to verify the actual effect of the optimization measures in this paper, a comparative experiment was conducted on 100 enterprises involved in mobile internet marketing. Through the research of the comparison results, the success rate of the optimized mobile internet marketing strategy has been greatly improved compared with the traditional way, and the marketing success rate has been effectively improved.

In the face of the ever-changing and fierce marketing environment, enterprises are facing more and more pressure and challenges in the marketing process, and their traditional marketing methods have been unable to meet the needs of consumers. China’s insurance industry has been developing for nearly 40 years since the reform and opening up, and it has also developed by leaps and bounds in recent years. At the same time, China's insurance industry presents a rapid development of diversification and scale. Firstly, based on the previous studies, this paper combs the literature on the current situation of precision marketing and big data mining at home and abroad, studies the relationship between big data mining and precision marketing on the basis of mastering certain related concepts and theories, and applies k-means algorithm to cluster the real sample data of a insurance company, and determines the minimum SSE and the most pseudo-F statistics through cyclic iteration. The optimal number of clusters can be determined by the large method. After modeling, through the analysis of each kind of sample characteristics, the user portraits are constructed, and the product preferences and precision marketing suggestions of all kinds of users are given respectively. Finally, the clustering results are divided into five categories, and the number of customers in each category presents an inverted pyramid structure, which is in line with the characteristics of the insurance company's pyramid customer group, and the marketing strategies for these five customer groups are given respectively.

With the rapid development of the exhibition industry and the economy, e-sports is undoubtedly one of the most popular exhibition projects nowadays. The rise of E-sports has also led to the development of E-sports advertising marketing. This article is to discuss the advertising marketing in e-sports competition in China and the prospect of the market, especially the advertising strategies used by major brands and the example of League of Legends. It is claimed that it is the era of digitization and precision now. Only by sufficient researching, reasonable technology and conducting social marketing, precision marketing and personalized marketing, can advertising marketing be fully developed. Several suggestions have been put forward in this article.

In the era of data based on big data and cloud computing, how to effectively utilize big data information technology and establish a precision marketing model in line with enterprise development among massive users and improve enterprise performance is an important topic that needs to be discussed by the academic community. Based on the big data theory, precision marketing theory and previous research literature, this paper established a precision marketing model in line with the development of enterprises. Taking Xiaohongshu App as an example, the precision marketing model was further tested and relevant suggestions were put forward. The research results of this paper hopes to have certain reference value for other enterprises.

At present, with the rapid development of social information technology, data information presents an explosive growth. In the era of big data, the precision marketing of big data information has become the key to the competition of various e-commerce enterprises in the data age and began to pay attention to the research on precision marketing. By mining and analyzing the massive data, e-commerce enterprises can obtain more accurate user information and make personalized marketing strategies to achieve better marketing effect. This paper will analyze the precision marketing of small- and medium-sized e-commerce enterprises of big data and put forward corresponding marketing strategies.

This study combs through relevant literature, adopts a combination of typical sampling and random sampling, collects three big data technology-driven interactive marketing e-commerce companies in a specific period of Sina Weibo sample data for research, obtains historical information and data, and constructs a model. Through relevant analysis to eliminate invalid variables, we creatively selected three variables of Internet hot words, activities, and microtopics as independent variables and used marketing effects as dependent variables to carry out empirical analysis and study the marketing innovation of three representative companies based on big data technology. We discussed the use of self-media in interactive marketing e-commerce and the situation of marketing innovation based on self-media, focusing on the interactive relationship between marketing innovation and Internet word-of-mouth (brand image). Through research, we have derived the three-force model, which is the biggest result of this research, and provided a reference model for interactive marketing e-commerce companies to carry out follow-up marketing innovation based on the media. Limited to the level of research and ability, there are some deficiencies in the research, such as barrage marketing, big data marketing, and emotional computing, that have not been analyzed in depth. This article fully considers the dependence of small and medium e-commerce companies on e-commerce platforms in the era of big data and conducted detailed market research on their precision marketing strategies in the era of big data. This will be a new field that does not come from media marketing. This article intends to summarize a series of experiences and laws from special to general, from individuality to generality, so as to give full play to the role of personalized marketing in increasing website traffic and order conversion, in order to personalize the use of data by other e-commerce companies with marketing provides some valuable experiences and methods for reference.

In user cluster analysis, users with the same or similar behavior characteristics are divided into the same group by iterative update clustering, and the core and larger user groups are detected. In this paper, we present the formulation and data mining of the correlation rules based on the clustering algorithm through the definition and procedure of the algorithm. In addition, based on the idea of the K-mode clustering algorithm, this paper proposes a clustering method combining related rules with multivalued discrete features (MDF). In this paper, we construct a method to calculate the similarity between users using Jaccard distance and combine correlation rules with Jaccard distances to improve the similarity between users. Next, we propose a clustering method suitable for MDF. Finally, the basic K-mode algorithm is improved by the similarity measure method combining the correlation rule with the Jaccard distance and the cluster center update method which is the ARMDKM algorithm proposed in this paper. This method solves the problem that the MDF cannot be effectively processed in the traditional model and demonstrates its theoretical correctness. This experiment verifies the correctness of the new method by clustering purity, entropy, contour, and other indicators.

As the Internet retail industry continues to rise, more and more consumers choose to shop online, especially Chinese consumers. Using consumer behavior data left on the Internet to predict repurchase behavior is of great significance for companies to achieve precision marketing. This paper proposes an improved deep forest model, and the interactive behavior characteristics of users and goods are added into the original feature model to predict the repurchase behavior of e-commerce consumers. Based on the Alibaba mobile e-commerce platform data set, first construct a feature engineering that includes user characteristics, product characteristics, and interactive behavior characteristics. And then use our proposed model to make predictions. Experiments show that the model’s overall performance with increased interactive behavior features is better and has higher accuracy. Compared with the existing prediction models, the improved deep forest model has certain advantages, which not only improves the prediction accuracy but also reduces the cost of training time.

As a method of promotion, precision marketing is likely to expand significantly because of the explosive growth of the internet and data collection techniques needed to drive it. Precision marketing is best evidenced by direct mail activity and telesales.

This article starts with the analysis of the existing electronic commerce system, summarizes its characteristics, and analyzes and solves its existing problems. Firstly, the characteristics of the relational database My Structured Query Language (MySQL) and the distributed database HBase are analyzed, their respective advantages and disadvantages are summarized, and the advantages and disadvantages of each are taken into account when storing data. My SQL is used to store structured business data in the system, while HBase is used to store unstructured data such as pictures. These two storage mechanisms together constitute a data storage subsystem. Secondly, considering the large amount of data in the e-commerce system and the complex calculation of the data mining algorithm, this paper uses MapReduce to realize the parallelization of the data mining algorithm and builds a Hadoop-based commodity recommendation subsystem on this basis. We use JavaEE technology to design a full-featured web mall system. Finally, based on the impact of cloud computing, mobile e-commerce is analyzed, including relevant theories, service mode, architecture, core technology, and the application in e-commerce, which can realize e-commerce precision marketing, find the optimal path of logistics, and take effective security measures to avoid transaction risks. This method can avoid the disadvantages of the traditional e-commerce, where large-scale data cannot be processed in a timely manner, realize the value of mining data behind, and realize the precision marketing of e-commerce enterprises.

User lifetime value assessment is complex but important which requires continuous observation of users’ behavior with massive time and resource consumption. To overcome the difficulty, this paper improves the RFM model to realize behavior observation and proposes an evaluation model from the perspective of market segmentation based on AHP method. Under real conditions, the model can be used to analyze the comprehensive value of users in two cities as well as the difference of regions and market segments. Results prove that proposed model performs remarkably and has practical significance for service providers.

Electronic toll collection (ETC) is an electronic non-stop toll collection system for expressways which brings drivers huge convenience when vehicle passes through the toll gates without stopping. Recently, China has a huge market and its credit card business has greatly contributed to the retail business of banks. Therefore, accurate marketing for the potential users is very important for the banking business. Users can be fully portrayed to explore the characteristics of potential ETC users based on telecom big data. Under such situations, we propose an advanced K-means clustering algorithm in view of silhouette coefficient which can distinctly increase the accuracy of clustering and improve the performance of k-means clustering. By applying this advanced algorithm in the precision marketing scenario of ETC credit card, the key elements, which affect customers’ ETC processing, can be obtained. This method brings new ideas and new momentum to the development of vertical industries.

In the current Internet marketing, many enterprises face the problem that they cannot find the key marketing points and waste huge advertising expenses, which is the result of the traditional advertising industry covering an excessive number of non-target users. Compared to the traditional marketing, precision marketing can help companies handle this problem to some extent through careful selection of target customers. Steam of literature has studied the big data on which precision marketing rely, including the acquisition of big data and the segmentation of user profiles, as well as tools and channels for precision marketing promotion. However, a well-designed precision marketing system has not been established, leading to uncertainty in suitability when companies employ precise marketing as a marketing tool. Though precision marketing is expected to improve marketing's economic benefits, companies lack quantitative indicators to show the relationship between precision marketing and benefits achieved. In this paper, we explore the relationship between precision marketing relying on big data and company's development ability. We find companies that invest more in marketing and whose industry is more competitive are more inclined to use precision marketing. We also find that precision marketing can help improve the company's development ability. Specifically, precision marketing has a positive impact on the company's return on net assets and the growth rate of total assets.

Inspection and certification industry is an important part of modern service industry, at present, most of the world’s inspection and certification institutions only include a narrow field of inspection and certification services and could not meet the customer’s increasingly improving inspection comprehensive, extensive, timeliness, accuracy, convenience and other aspects of the needs. So, it’s extremely significant to plan a practical marketing strategy for inspection and certification e-commerce platform. In order to solve this problem, through the analysis of the precision marketing process of the inspection and certification e-commerce platform, this paper proposes the personalized recommendation mechanism for precision marketing, and forms the precision marketing model of the inspection and certification e-commerce platform. The model is effectively applied in China’s inspection and certification e-commerce service cloud platform - CCTEK, could provide detailed guidance for inspection and certification e-commerce platform, which promotes the inspection and certification e-commerce platform using personalized recommendation and other big data technology to achieve precision marketing.

With the growth of users' personalized demand for e-commerce visual design and the rapid development of machine learning technology, a large number of Internet pages are automatically designed and generated by computers. After being generated, effective evaluation mechanisms are needed for verification and feedback. At present, the evaluation model of visual design generally takes traditional web pages as the research object, and there is little research on the complexity and marketing characteristics of e-commerce information. It is necessary to consider how visual design can promote the effectiveness of communication between users and web pages from the perspectives of psychology, behavior and content. This paper proposes a "multi-dimensional visual performance evaluation model" for the evaluation after the generation of contemporary e-commerce web page design. This paper first constructs the visual marketing system and discusses the circulation mechanism of user demand import, e-commerce web page design, multi-dimensional visual performance evaluation and visual precision marketing. Under the system, a relational model of how "visual performance indicators (aesthetic performance, search behavior performance, information usefulness performance)" based on "scene factors" affect "overall evaluation" is proposed, defined as a multidimensional visual performance evaluation model, and verified by quantitative experiments. The model provides visual design basis for designers and recyclable evaluation data for machine learning generated pages.

In the context of the Internet era, people’s individual needs and consumer desires for products have become involved and diversified. In view of the shortcomings of small ceramic enterprises and manual workshops in design and operation, this paper studies the ideas of designing and building the marketing platform for ceramic products of Changsha Kiln. Based on the creative material synthesis platform of Changsha Kiln ceramic art, this paper makes a detailed analysis of the three design and marketing methods in the platform, including process, function and style, and analyzes their experience value. Changsha Kiln ceramic product design and marketing platform follows the principles and concepts of design marketing, and applies service design and precision marketing to the platform construction planning, so as to solve the problem of increasing the added value of products, realize commercial interests and meet the needs of all parties, and provide reference for the research of ceramic product innovation. And provide a reference for ceramic product innovation research.

In view of the old information management system function which is not perfect, it cannnot effectively classify and mine massive data. This paper uses. Net language, SQL Server 2015 database, Apriori algorithm and other technologies to build a system platform and database with perfect functions, which can complete data analysis, and achieve the purpose of precision marketing of clothing products. The system adopts B/S mode and uses MVC mode to design the system architecture. Then, based on the perspective of marketing, the factors are verified, and the precise marketing segmentation model is constructed. The operation and debugging of the system shows that the system can fully meet the needs of precision marketing, and it can effectively manage the user information of precision marketing.

The marketing system of bank financial products is analyzed and the deficiencies of current marketing system is discussed in this paper. Then, the working ideas and methods of precise marketing for personal financial products are established through the intensive analysis on precision marketing strategy for personal financial products. During the researching process, we discuss the construction approach of customer segmentation model, the correlation analysis between customers and products, and between products and products. The clustering algorithm and association rule algorithm for product marketing are also analyzed. Finally, the application process of precise marketing of personal financial products in actual marketing activities are introduced by certain cases, and the final marketing effects are evaluated according to the precise marketing strategy.

To help power companies quickly and precisely find target consumers for different purposes from resident users, a method based on association rule mining is proposed. First, users’ four electricity features including daily electricity consumption (DEC), electricity consumption stability (ECS), potential of peak load shifting (PPLS) and typical electricity consumption patterns (TECP) and basic attributes (population, employment status, cooking type, etc.) are extracted. Then, the association rules between basic attributes and electricity features are obtained by FP-growth algorithm, which can guide power companies to select the target users. Finally, using a sample to evaluate obtained rules, the results demonstrate that the proposed method is practical and effective.

With the rapid development of the Internet, the application of big data is more and more extensive. Compared with traditional marketing, big data marketing has significant advantages in market information acquisition, data processing and analysis, and data application. For the automotive industry, the traditional marketing mode is facing severe challenges due to the development of big data technology. In view of this form, a new marketing mode based on big data marketing, which is called precision marketing, came into being. The new automobile precision marketing mode based on big data can be implemented from the following aspects: precise positioning based on big data analysis, accurate push based on big data mining, and fine management based on big data application.

This paper mainly studies the use of Apache + PHP + MySQL and big data computing technology to design a commodity trading platform based on big data analysis. This commodity trading platform has multi-style data analysis. The front desk has user personal data analysis, including footprint, order analysis, purchase preferences, consumption information, etc. There are various kinds of marketing data analysis of the platform in the background, including sales profile data analysis, peer hot sales data analysis, sales ranking, etc. In addition, big data computing technology is used to analyze user behavior, collect all access ways of user browsing platform, and process the collected data in depth, so as to obtain a real-time dynamic effect map, dynamically display the access amount and proportion of each access way, and extract valuable information from it, so as to develop an effective promotion plan for the platform and achieve precision marketing.