Marketing Decision Support System Based on Data Mining Technology

Round 1

Reviewer 1 Report

1.      Explicitly,   there is a need to identify what is the gap that is covered by this paper.

2.      The research objectives are missing

3.      The introduction did not reflect the research objectives and  questions

4.      Authors have to identify the problem statement and the motivation for conducting their research.  The problem statement of their research is still vague and it needs clarification. In other words, how marketing decision support systems are related to data mining technology, should be discussed thoroughly.

5.      The contribution of the study to knowledge is still unclear because the gaps are missing

6.      The authors need to add a strong argument about the relationship between marketing decision support systems and data mining technology

7.      The references should be updated to address the relationship between marketing decision support systems and data mining technology

8.      Because the research problem is vague, the conclusions are superficial to some extent which make them lack consistency with the central idea of the topic.

9.      The paper did not give a strong insight into the relationship between marketing decision support systems and data mining technology

10.   The paper did not include research limitations and the agenda for future research.

Author Response

Reply

1. Aiming at the shortcomings of the current marketing decision support system in data integration, historical data, query function and data analysis, this paper constructs a marketing decision support system based on data mining technology.
2. Based on the needs of marketing assistant decision-making, the system determines that the designed MDSS should be able to collect, process and store all kinds of information related to marketing decision-making on the basis of full consultation with users and according to users' habits and requirements of solving problems. In addition, it uses mathematical models, expert experience and knowledge discovered through data mining to assist users to make scientific and reasonable marketing decision analysis, so as to make the marketing decision process more scientific and reasonable, thus improving the efficiency of market management.
3. With the continuous development of business intelligence technology, the research on the application of marketing DSS continues to deepen. The domestic work in this area started late, and there are few research cases of decision support system (DSS) to assist marketing decision-making. Aiming at the shortcomings of the current marketing decision support system in data integration, historical data, query function and data analysis, this paper constructs a marketing decision support system based on data mining technology.
4. Specifically, the decision support system extracts, transforms and loads various business data related to marketing decisions according to the theme, and establishes a unified, standardized and highly shared comprehensive theme data center. On this basis, OLAP and data mining technology are used to analyze data from multiple perspectives and extract potential knowledge from it, so as to establish an efficient marketing decision support system.
5. The system provides assistant decision support for management and decision makers in new product development, product pricing, market maintenance and development, competitor analysis, Customer Relationship Management (CRM), marketing goal formulation, product promotion, advertising promotion, performance evaluation, employee management and many other aspects related to marketing decisions, and lays a solid foundation for enterprise development and market development.
6. According to the design objectives of the system, MDSS can be divided into six levels according to functions: basic data, data extraction, data warehouse, information extraction, information presentation and system management.

(1) Basic data

The basic data layer covers a large amount of basic data accumulated by the mar-keting management department, including historical data and business data stored in many business system databases such as sales management system, customer rela-tionship management system and cost management system.

(2) Data extraction

The data extraction layer performs preliminary processing on the basic data from the database, which is an efficient data processing factory that transforms the basic data from application-oriented to subject-oriented.

(3) Data warehouse

After the data is processed and purified by the extraction layer, it needs to be stored in the data warehouse to directly face data analysis and data mining. The establishment of data warehouse is not to replace the database, but to establish a more comprehensive and complete information application to support high-level decision analysis.

(4) Information extraction (OLAP analysis, data mining)

The data extraction layer initially processes the original data to obtain some valu-able data, while the information extraction layer uses a variety of data analysis tools to extract information useful for decision-making from the data. For example, by analyzing the customer's purchase frequency, purchase volume and recent purchase time, we can predict the future purchase behavior and calculate the customer's career value. The visualization tools in data mining can effectively detect the development trend hidden in the data. In marketing decisions, trends can be used to evaluate marketing plans and predict future sales.

(5) Information display

The information display layer is responsible for displaying the analysis results for users, and can analyze and use the displayed data again to form the final analysis report.

(6) System management

It provides security management for users, permissions, passwords, etc. of the entire system, and completes the publishing of multi-dimensional analysis models, data mining models, customized reports and other functions.

7. References have been updated.
8. The conclusion has been revised as follows: The marketing decision-making process is a market-oriented management decision-making process involving product decision-making, price decision-making, pro-motion decision-making and other factors. The marketing DSS based on data warehouse designed in this paper can effectively support the management decision in this complex process. The comparative study shows that when the running time reaches 80 seconds, the itemsets of SVM and Bayesian classifier are 43, 111 and 182, respectively. Similarly, when the running time reaches 90, the itemsets of SVM and Bayesian classifier are 293, 356 and 670, respectively. The method in this paper requires less iterations than the support vector machine method and Bayesian classifier method in the implementation process, has strong self-organization and adaptive ability, and has higher accuracy. The marketing decision support system based on data mining technology can effectively discover the marketing knowledge hidden in the data, and better meet the various decision-making requirements of marketing.
9. The discussion on the relationship between marketing decision support system and data mining technology has been supplemented. Please see the section (2) Architecture design of marketing DSS.
10. Since the establishment of marketing decision data warehouse is also a continuous improvement process, it is necessary to study more marketing decision models and data mining algorithms in line with marketing characteristics. In addition, the real-time research of marketing decision support system needs to be strengthened.

Author Response File: Author Response.docx

Reviewer 2 Report

The study mainly concerned about designing the DSS system. 

Incoperation of data mining techniques in DSS in not a novel concept.

Experiemts conducted has some series flaws.

The presentation of the manuscript is very poor. It is not upto the standard of a scientific publication.

Author Response

Reply

China's work in this area started late, and there are few DSS research cases to assist marketing decision-making. In view of the shortcomings of current marketing decision support system in data integration, historical data, query function and data analysis, this paper analyzes the characteristics of marketing decision, discusses the application of data warehouse, OLAP and data mining technology in marketing decision support system, and designs a marketing decision support system based on data mining technology. The system provides assistant decision support for management and decision makers in new product development, product pricing, market maintenance and development, competitor analysis, Customer Relationship Management (CRM), marketing goal formulation, product promotion, advertising promotion, performance evaluation, employee management and many other aspects related to marketing decisions, and lays a solid foundation for enterprise development and market development.

Thank you for your comments. The manuscript has been revised according to the suggestions.

Author Response File: Author Response.docx

Reviewer 3 Report

1. The abstract is a mesh. Half of the abstract contains background information and more than half discusses results which could be part of the result and discussion section.
2. The abstract needs rewriting and organized as follow: limitations of existing studies in a glance, problem statement, methodology, contributions, results and applications.
3. Introduction is un-necessirly long. 
4. The contributions mentioned are trivial. The OLAP has its own intrinsic features which cannot be claimed as the authors own one. Similarly, the Marketing Framework by itself makes use of OLAP which again has love level of novelity for a research article. 

Author Response

Reply

1. The abstract has been rewritten.
2. With the continuous development of business intelligence technology, the research on the application of decision support system (DSS) continues to deepen. China's work in this area started late, and there are few DSS research cases to assist marketing decision-making. In view of the shortcomings of current marketing decision support system in data integration, historical data, query function and data analysis, this paper analyzes the characteristics of marketing decision, discusses the application of data warehouse, OLAP and data mining technology in marketing decision support system, and designs a marketing decision support system based on data mining technology. Through experimental comparison, the proposed method produces more frequent itemsets than SVM and Bayesian classifier. In this study, when the running time reaches 80 seconds, the itemsets of SVM and Bayesian classifier are 43, 111 and 182, respectively. Similarly, in the figure, when the running time reaches 90, the itemsets of SVM and Bayesian classifier are 293, 356 and 670, respectively. The research shows that with the continuous development of data mining technology, the system cannot only help users to conduct scientific and reasonable marketing decision analysis, make the marketing decision process more scientific and reasonable, but also can bring new ideas to enterprise decision makers, and promote the continuous improvement and progress of the system.
3. The introduction has been adjusted.
4. The innovation of this paper is that the marketing decision support system proposed in this paper can solve the problem of information asymmetry in the game with other companies and sales agents in sales. It adopts a message mechanism, which allows managers to get the information of rival companies and the pre-determined agent team at the first time, and know all the sales in the next few days, so as to take the lead in the whole sales.

Author Response File: Author Response.docx

Round 2

Reviewer 1 Report

The revised version is improved. It addressed the required amendments. The most important amendment that is required is to clearly identify the gap(s) and explain its contribution. I suggest the authors add a small paragraph to the introduction to justify why this paper is needed .

Author Response

At present, the marketing decision support system still has deficiencies in data integration, historical data, query function and data analysis. There are few domestic research cases of decision support system (DSS) for auxiliary marketing decision-making, so this paper constructs a marketing decision support system based on data mining technology. The system collects, processes and stores all kinds of information related to marketing decisions according to users' habits and requirements for solving problems, and makes use of mathematical models, expert experience and knowledge discovered through data mining to conduct scientific and reasonable marketing decision analysis. The results of this study are conducive to a more scientific and reasonable marketing decision-making process, thus improving the efficiency of market management.

Author Response File: Author Response.docx

Reviewer 2 Report

It is recommended to get the support of data mining expert/statistician to design and conduct the experiemants for the evaluation the performance of the new system.

Pl. also see the attached report.

Comments for author File: Comments.pdf

Author Response

Thank you for your suggestion. Here are my modifications.

1. The section “Prediction of data mining in decision support systems” has been supplemented to support the value prediction of the model.
2. Relevant explanations of the formula in the text have been supplemented, and the purpose is as follows: The classification analysis of the decision tree is mainly to train the decision tree or Bayesian neural network through the transaction samples in the transaction database to form the classification rules for the sample points in the sample. It can explain the main and secondary attributes that form classification differences in the samples, and can classify and predict the samples with set attributes according to the classification rules in the decision tree. The system uses ID3 algorithm, a representative algorithm based on information gain theory, to realize decision tree analysis. Decision tree analysis can obtain the levels and categories of various influencing factors and the resulting sales level.

The meaningless equation has been deleted. Equation (8) has been supplemented. The formula format has been adjusted.

3. This article adds the average absolute percentage error MAPE to evaluate the accuracy of the prediction. A feasible prediction is one with an average absolute percentage error between 20% and 50%, and a good prediction is one with an average absolute percentage error below 20%.
4. Thank you for your suggestion. After consideration, I decided to delete testing for Bayesian classifiers and support vector machines, and designed to validate the data mining prediction model established based on BP networks in decision support systems.
5. Based on the report of past research, I added another critical statement: Although the application of DSS has achieved initial results, there are not many successful examples, especially traditional DSS. The data shows that the DSS success-fully put into use abroad only accounts for about 30% of the total R&D, and the same is true in China. There are many reasons for the failure of DSS development, but there are two main reasons. First, traditional DSS can only provide data-level support in the process of auxiliary decision-making. However, the data needed for practical decision-making is often distributed and heterogeneous, which limits the adaptability of the system and does not meet the needs of the decision-making process. Secondly, the traditional DSS requires the decision-makers not only to have professional domain knowledge, but also to have higher knowledge of DSS construction model, which makes it difficult for the decision-makers to understand and accept. With the emergence of data warehouse, online analytical processing and data mining technology, a new generation of decision support system based on DW, OLAP and DM has been proposed. Because of the inherent connection and complementarity among the three, combining them to design a new DSS architecture, that is, a solution based on data warehouse and using data mining and OLAP tools as means, can give full play to their respective ad-vantages. Utilizing the massive data existing in the enterprise to mine valuable knowledge and rules can provide more effective support for decision-making. The new decision support system is data-driven, which is less difficult to develop. It makes up for the shortcomings of traditional DSS system, and has become a hot direction of the development of decision support system.
6. The long sentences in the text have been split.

Author Response File: Author Response.docx

Reviewer 3 Report

The concerns raised are addressed.

Author Response

Thank you very much.

Author Response File: Author Response.docx