CN117035818B - Marketing management method and system based on big data - Google Patents
Marketing management method and system based on big data Download PDFInfo
- Publication number
- CN117035818B CN117035818B CN202310939577.8A CN202310939577A CN117035818B CN 117035818 B CN117035818 B CN 117035818B CN 202310939577 A CN202310939577 A CN 202310939577A CN 117035818 B CN117035818 B CN 117035818B
- Authority
- CN
- China
- Prior art keywords
- sales
- products
- product
- degree
- association
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
- G06Q30/0201—Market modelling; Market analysis; Collecting market data
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/24—Querying
- G06F16/245—Query processing
- G06F16/2457—Query processing with adaptation to user needs
- G06F16/24578—Query processing with adaptation to user needs using ranking
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/24—Querying
- G06F16/245—Query processing
- G06F16/2458—Special types of queries, e.g. statistical queries, fuzzy queries or distributed queries
- G06F16/2462—Approximate or statistical queries
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Business, Economics & Management (AREA)
- Accounting & Taxation (AREA)
- Data Mining & Analysis (AREA)
- Development Economics (AREA)
- Finance (AREA)
- Strategic Management (AREA)
- General Physics & Mathematics (AREA)
- Probability & Statistics with Applications (AREA)
- Entrepreneurship & Innovation (AREA)
- Computational Linguistics (AREA)
- Databases & Information Systems (AREA)
- General Engineering & Computer Science (AREA)
- Marketing (AREA)
- General Business, Economics & Management (AREA)
- Economics (AREA)
- Game Theory and Decision Science (AREA)
- Fuzzy Systems (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
本发明公开了一种基于大数据的市场营销管理方法及系统，涉及市场营销技术领域，包括数据采集模块、分析模型建立模块、排序选定模块以及综合分析模块；数据采集模块，采集产品销售时的信息，销售时的信息包括将销售量低的产品与其他销售产品进行关联的信息，并将关联的信息传递至分析模型建立模块。本发明结合销售数据将销售量低的产品与其他销售产品进行关联度分析，将销售量低的产品与其关联度最高的销售产品进行关联销售，相比于现有技术根据销售经验对两个产品进行关联，可提高销售量低的产品与其他销售产品关联的精准度，便于对市场营销的产品进行高效的销售，进而便于对市场营销更好地管理。
The invention discloses a marketing management method and system based on big data, which relates to the field of marketing technology and includes a data collection module, an analysis model building module, a sorting and selection module and a comprehensive analysis module; the data collection module collects product sales time The information at the time of sales includes information that associates products with low sales volume with other sales products, and the associated information is passed to the analysis model building module. This invention combines sales data to conduct correlation analysis between products with low sales volume and other sales products, and performs related sales between products with low sales volume and their sales products with the highest correlation. Compared with the existing technology, the two products are analyzed based on sales experience. Correlation can improve the accuracy of the association between products with low sales volume and other sales products, facilitate efficient sales of marketing products, and facilitate better management of marketing.
Description
Technical Field
The invention relates to the technical field of marketing, in particular to a marketing management method and system based on big data.
Background
Marketing refers to the process by which an enterprise or organization attracts, satisfies, and retains customers for purposes of promoting and selling products or services, by studying market demand, formulating marketing strategies, and conducting marketing campaigns. The method is an important link for establishing connection, transferring value, realizing sales and establishing brand images between enterprises and customers, and aims at meeting customer demands and realizing maximization of enterprise profit. To achieve this goal, marketing needs to conduct market research, knowing the needs, preferences and purchasing behavior of customers. Based on the results of the marketing study, the enterprise may formulate marketing strategies including targeting the market, selecting appropriate marketing channels, determining product pricing and promotional campaigns, and the like. The business then communicates with the customer through advertising, marketing, customs, etc., delivering the value of the product or service, and encouraging the customer to purchase and use.
Through an effective marketing strategy, more customers can be attracted and promoted to purchase products or services, so that sales and profits are increased, the marketing can help enterprises to build unique brand images, emotional connection is established with the customers, brand loyalty and praise are increased, the marketing can provide products or services meeting the demands of the customers by knowing the demands of the customers in depth, thereby meeting the demands of the customers, customer satisfaction is enhanced, the enterprises can know the advantages and disadvantages of the competitors through the marketing, and the corresponding strategies are adopted to stand out in competition, the marketing can help the enterprises to find new market opportunities and potential customer groups, and new sales channels and business fields are developed;
the prior art has the following defects: in order to promote the sales of products, the prior art can correlate one product with high sales volume with another product with low sales volume, and a combined sales mode is adopted, and because the two products are mostly correlated according to sales experience at present, the correlation degree of the two products cannot be analyzed, so that the situation that the sales volume of the sold products is reduced due to the correlation with the products with poor sales is easy to occur, the products for marketing are not convenient to sell efficiently, and the marketing is not convenient to manage better.
The above information disclosed in the background section is only for enhancement of understanding of the background of the disclosure and therefore it may include information that does not form the prior art that is already known to a person of ordinary skill in the art.
Disclosure of Invention
The invention aims to provide a marketing management method and a marketing management system based on big data, wherein the method and the system are used for carrying out association degree analysis on a product with low sales volume and other sales products by combining sales data, and carrying out association sales on the product with low sales volume and the sales product with highest association degree.
In order to achieve the above object, the present invention provides the following technical solutions: a marketing management system based on big data comprises a data acquisition module, an analysis model establishment module, a sorting selection module and a comprehensive analysis module;
the data acquisition module acquires information when the product is sold, wherein the information when the product is sold comprises information for associating the product with other sold products, and the associated information is transmitted to the analysis model establishment module;
the analysis model building module is used for building a data analysis model according to the information of the correlation between the products with low sales and other sales products, generating a correlation index and transmitting the correlation index to the sorting selection module;
the sorting and selecting module is used for sequentially sorting association indexes generated by the products with low sales volume and other sales products, selecting the sales product with the largest association index expression value to be associated with the products with low sales volume, and transmitting information after the association of the products to the comprehensive analysis module;
and the comprehensive analysis module is used for acquiring the associated sales information, comprehensively analyzing the sales condition of the associated products and taking different measures.
Preferably, information of products during sales is acquired based on big data, the support degree, the confidence degree, the lifting degree and the chi-square value of the products with low sales and other sales products are acquired through the data acquisition module, and the support degree, the confidence degree, the lifting degree and the chi-square value are respectively calibrated as ZC k 、ZX k 、TS k 、KF k 。
Preferably, the support degree indicates the probability of purchasing two products simultaneously, that is, the frequency of occurrence of two products simultaneously, and the formula of the support degree is calculated as follows: support = number of simultaneous purchases of two products/total number of transactions, the number of simultaneous purchases of a low sales product and other sales products is marked as Xi, the total number of transactions is marked as Xz, ZC k ＝Xi/Xz；
Confidence represents the probability that if one consumer purchases a certain product, they purchase another product, confidence is used to measure the confidence of the purchase association rule, confidence is calculatedThe formula is: confidence = number of simultaneous purchases of two products/number of purchases of first product, number of simultaneous purchases of low sales product with other sales products is designated Yi, number of purchases of low sales product is designated Yz, ZX k ＝Yi/Yz；
The lifting degree of the two product purchase relations is used for measuring the relative strength of the association relation between the two products, the lifting condition of the probability that the two products are purchased simultaneously relative to the probability that the two products are purchased independently can be presented, and the formula of the lifting degree is calculated as follows: degree of promotion = confidence/support degree, TS k ＝ZX k /ZC k 。
Preferably, the chi-square value is a statistical indicator for measuring the degree of difference between actually observed data and expected data, and can be used to measure the difference between the crossover frequency and the expected frequency of two products when evaluating the purchase association of the two products;
the step of calculating the chi-square value is as follows:
a. constructing a 2x2 cross-table, wherein the rows represent the purchase (purchase or not) of a first product and the columns represent the purchase (purchase or not) of a second product;
b. counting the actually observed data, filling four cells in the cross table, wherein A represents the times of purchasing a first product and purchasing a second product, B represents the times of purchasing the first product but not purchasing the second product, C represents the times of not purchasing the first product but purchasing the second product, and D represents the times of not purchasing the first product and not purchasing the second product;
c. calculating the expected frequency of each cell, wherein the expected frequency is an expected value calculated according to the overall proportion under the independent assumption, and the calculation method comprises the following steps of:
expected frequency of first product purchase: e1 = (a+b)/(a+b+c+d);
desired frequency of first product not purchased: e2 = (c+d)/(a+b+c+d);
expected frequency of second product purchase: e3 = (a+c)/(a+b+c+d);
expected frequency of non-purchase of the second product: e4 = (b+d)/(a+b+c+d);
d. the chi-square value of each cell is calculated, the chi-square value being the sum of the square of the difference between the actual frequency and the desired frequency divided by the desired frequency, the calculation method being:
preferably, the support degree ZC of the product with low sales and other sales products is obtained k Confidence ZX k Degree of lift TS k Chi-square KF k Then, a data analysis model is built through an analysis model building module, and a relevance index GL is generated d k, the formula according to is:
the method comprises the steps of carrying out a first treatment on the surface of the Wherein k is the number of other sales products, k=1, 2, 3, 4, … …, n is a positive integer, and α, β, γ, δ are the supporters ZC respectively k Confidence ZX k Degree of lift TS k Chi-square KF k And alpha, beta, gamma, delta are all greater than 0.
Preferably, after the relevance indexes generated by the products with low sales and other sales are obtained, the generated relevance indexes are ranked in order from large to small by a ranking selection module, and the sales product with the largest relevance index expression value and the products with low sales are selected for associated sales.
Preferably, a specific time period is selected to compare sales conditions before and after product association, the sales growth rate, the cross-sales rate and the repeat-purchasing rate after product association are obtained through the comprehensive analysis module, and after the sales growth rate, the cross-sales rate and the repeat-purchasing rate are respectively calibrated to be ZZL through the comprehensive analysis module j 、JCX j 、CFG j 。
Preferably, the sales increase rate ZZL is obtained j Cross-selling ratio JCX j Repeat purchase rate CFG j Then, a data analysis model is established through the comprehensive analysis module to generate an evaluation index P g o, according to the formula:
the method comprises the steps of carrying out a first treatment on the surface of the Wherein mu 1, mu 2 and mu 3 are sales increase rates ZZL respectively j Cross-selling ratio JCX j Repeat purchase rate CFG j And μ 1, μ 2, μ 3 are all greater than 0.
Preferably, a plurality of evaluation indexes generated within a period of time are obtained, a data set is established by the generated evaluation indexes, and the data set is marked as A, so that A= { P g o}＝{P g 1、P g 2、P g 3、…、P g N }, o is the number of evaluation indices within the data set, o=1, 2, 3, 4, & gt, N being a positive integer;
calculating the average value and the discrete degree value of the evaluation indexes in the data set, and respectively calibrating the average value and the discrete degree value asAnd P g X, if mean->When the evaluation index is larger than or equal to the evaluation index reference threshold value, generating a correlation success signal through the comprehensive analysis module, prompting sales personnel to keep the correlation of the product for further sales, and if the average value is +.>Less than the evaluation index reference threshold and the degree of discretion value P g X is larger than a discrete degree reference threshold, and a correlation stability difference signal is generated through a comprehensive analysis module to prompt sales personnel to timely conduct sales conditions of correlation productsFurther adjust, if mean->Less than the evaluation index reference threshold range and the degree of discretion value P g X is smaller than or equal to a discrete degree reference threshold, and an association failure signal is generated through a comprehensive analysis module to prompt sales personnel to replace associated products for resale, so that the situation that the association condition of the products is bad is found in time;
the calculation formula of the discrete degree value of the evaluation index in the data set is as follows:
the method comprises the steps of carrying out a first treatment on the surface of the In the method, in the process of the invention,mean value of the evaluation index within the data set, P g X is the degree of discretion value of the evaluation index within the data set.
A marketing management method based on big data comprises the following steps:
collecting information when the product is sold, wherein the information when the product is sold comprises information for associating the product with low sales amount with other sold products;
establishing a data analysis model according to information of correlation between the products with low sales and other sales products, and generating a correlation index;
sequentially sequencing association indexes generated by products with low sales and other sales products, and selecting the sales product with the largest association index expression value to be associated with the products with low sales;
and acquiring the associated sales information, comprehensively analyzing the sales condition of the associated products, and taking different measures.
In the technical scheme, the invention has the technical effects and advantages that:
1. according to the invention, the association degree analysis is carried out on the products with low sales volume and other sales products by combining the sales data, and the association sales is carried out on the products with low sales volume and the sales products with highest association degree, compared with the prior art, the association of the two products according to the sales experience can improve the association precision of the products with low sales volume and other sales products, thereby being convenient for carrying out high-efficiency sales on the products for marketing and further being convenient for better management of marketing;
2. according to the invention, through analyzing the conditions of the products after being associated, the supervision and timely adjustment of the sales conditions of the associated products are realized, so that the high-efficiency sales of the products for marketing are further facilitated, and the better management of marketing is further facilitated.
Drawings
For a clearer description of embodiments of the present application or of the solutions of the prior art, the drawings that are needed in the embodiments will be briefly described below, it being obvious that the drawings in the following description are only some embodiments described in the present invention, and that other drawings may be obtained according to these drawings for a person skilled in the art.
FIG. 1 is a schematic diagram of a marketing management method and system based on big data according to the present invention.
FIG. 2 is a flow chart of a marketing management method and system based on big data according to the present invention.
Detailed Description
Example embodiments will now be described more fully with reference to the accompanying drawings. However, the exemplary embodiments may be embodied in many forms and should not be construed as limited to the examples set forth herein; rather, these example embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the concept of the example embodiments to those skilled in the art.
Example 1: the invention provides a marketing management system based on big data, as shown in figure 1, which comprises a data acquisition module, an analysis model establishment module, a sorting selection module and a comprehensive analysis module;
the data acquisition module acquires information when the product is sold, wherein the information when the product is sold comprises information for associating the product with other sold products, and the associated information is transmitted to the analysis model establishment module;
the explanation of low sales products is as follows:
counting the number of days of sales of a product as T, calibrating the number of products sold in the T days as M, calculating the average daily sales of the product through M/T, calibrating the average daily sales of the product as G, and comparing the G with a preset first reference threshold and a second reference threshold, wherein the first reference threshold is smaller than the second reference threshold, if G is larger than or equal to the second reference threshold, the product is calibrated as a product with high sales, if G is smaller than the second reference threshold and larger than or equal to the first reference threshold, the sales of the product is calibrated as a product with normal sales, if G is smaller than the first reference threshold, the sales of the product is indicated to be low;
it should be noted that other sales products refer to products with normal sales volumes.
Acquiring information of products during sales based on big data, acquiring the support degree, the confidence degree, the lifting degree and the chi-square value of the products with low sales and other sales products through a data acquisition module, and respectively calibrating the support degree, the confidence degree, the lifting degree and the chi-square value as ZC k 、ZX k 、TS k 、KF k ；
The support degree indicates the probability of purchasing two products simultaneously, namely the frequency of the simultaneous occurrence of the two products, the higher the support degree is, the stronger the association of purchasing among the products is indicated, and the formula of the support degree is calculated as follows: support = number of simultaneous purchases of two products/total number of transactions, the number of simultaneous purchases of a low sales product and other sales products is marked as Xi, the total number of transactions is marked as Xz, ZC k ＝Xi/Xz；
Confidence level indicates the probability that if one consumer purchases a certain product, they purchase another product, confidence level is used to measure the confidence level of the purchase association rule, and a high confidence level indicates the purchase association between two productsThe formula of the strong confidence calculation is: confidence = number of simultaneous purchases of two products/number of purchases of first product, number of simultaneous purchases of low sales product with other sales products is designated Yi, number of purchases of low sales product is designated Yz, ZX k ＝Yi/Yz；
The lifting degree of the two product purchase relations is used for measuring the relative strength of the association relation between the two products, the lifting condition of the probability of simultaneously purchasing the two products relative to the probability of independently purchasing the two products can be presented, the lifting degree is greater than 1, which indicates that positive association exists between the two products, the lifting degree is equal to 1, which indicates that no association exists between the two products, the lifting degree is less than 1, which indicates that negative association exists between the two products, and the formula of the lifting degree calculation is as follows: degree of promotion = confidence/support degree, TS k ＝ZX k /ZC k ；
It should be noted that when the lifting degree is less than 1 or equal to 1, the association of the product with low sales and the sales product is not considered any more, and when the lifting degree is greater than 1, the association of the product with low sales and the sales product is considered again;
for example, to illustrate:
assuming a set of transaction records containing two products E and F, we now want to calculate the support, confidence and promotion between E and F;
calculating the support degree: counting the times of purchasing E and F at the same time, and dividing the times by the total transaction times to obtain the support degree of E and F;
support = number of simultaneous purchases of E and F/total number of transactions
Calculating the confidence coefficient: counting the times of purchasing E, counting the times of purchasing F simultaneously under the condition of purchasing E, and dividing the times of purchasing E and F simultaneously by the times of purchasing E to obtain the confidence degrees of E and F;
confidence = number of simultaneous purchases of E and F/number of purchases of E;
calculating the lifting degree: degree of promotion = confidence/support = (number of simultaneous purchases of E and F/number of purchases of E)/(number of simultaneous purchases of E and F/total number of transactions);
chi-square value is a statistical indicator used to measure the degree of discrepancy between the actual observed data and the expected data, and can be used to measure the discrepancy between the crossover frequency and the expected frequency of two products when evaluating the purchase relevance of two products;
the step of calculating the chi-square value is as follows:
a. constructing a 2x2 cross-table, wherein the rows represent the purchase (purchase or not) of a first product and the columns represent the purchase (purchase or not) of a second product;
b. counting the actually observed data, filling four cells in the cross table, wherein A represents the times of purchasing a first product and purchasing a second product, B represents the times of purchasing the first product but not purchasing the second product, C represents the times of not purchasing the first product but purchasing the second product, and D represents the times of not purchasing the first product and not purchasing the second product;
c. calculating the expected frequency of each cell, wherein the expected frequency is an expected value calculated according to the overall proportion under the independent assumption, and the calculation method comprises the following steps of:
expected frequency of first product purchase: e1 = (a+b)/(a+b+c+d);
desired frequency of first product not purchased: e2 = (c+d)/(a+b+c+d);
expected frequency of second product purchase: e3 = (a+c)/(a+b+c+d);
expected frequency of non-purchase of the second product: e4 = (b+d)/(a+b+c+d);
d. the chi-square value of each cell is calculated, the chi-square value being the sum of the square of the difference between the actual frequency and the desired frequency divided by the desired frequency, the calculation method being:
it should be noted that, the larger the chi-square value is, the more obvious the difference exists between the actually observed data and the expected data, the larger the association relationship between the two products is, and otherwise, the smaller the association relationship between the two products is;
the following is a general relationship between chi-square value size and the association between two products:
less than 1: when the chi-square value is smaller than 1, the difference between the actually observed data and the expected data is smaller, which generally indicates that no obvious association relationship or weak association relationship exists between the two products;
about equal to 1: when the chi-square value is about equal to 1, the difference between the actually observed data and the expected data is consistent with the expected data, and no obvious association relationship exists between the two products;
greater than 1: when the chi-square value is greater than 1, the fact that the actually observed data and the expected data have larger difference is indicated, and a certain association relationship exists between the two products;
significantly greater than 1: when the chi-square value is significantly greater than 1 (typically, a threshold value at a significance level of 0.05 or 0.01), it indicates that the difference between the actually observed data and the expected data is very significant, indicating that a strong association exists between the two products;
the analysis model building module is used for building a data analysis model according to the information of the correlation between the products with low sales and other sales products, generating a correlation index and transmitting the correlation index to the sorting selection module;
obtaining the support degree ZC of the product with low sales and other sales products k Confidence ZX k Degree of lift TS k Chi-square KF k Then, a data analysis model is built to generate a relevance index GL d k, the formula according to is:
the method comprises the steps of carrying out a first treatment on the surface of the Wherein k is the number of other sales products, k=1, 2, 3, 4, … …, n is a positive integer, and α, β, γ, δ are the supporters ZC respectively k Confidence ofDegree ZX k Degree of lift TS k Chi-square KF k Is greater than 0, and alpha, beta, gamma and delta are all greater than 0;
as can be seen from the formula, the higher the support degree, the higher the confidence degree, the higher the lifting degree and the larger the chi-square value of the product with low sales and other sales products, namely the relevance index GL d The higher the expression value of k, the higher the association degree between the product with low sales and the sales product, the lower the support degree between the product with low sales and other sales products, the lower the confidence, the lower the lifting degree, the smaller the chi-square value, namely the association degree index GL d The smaller the expression value of k, the lower the association of a product with low sales and the sales product;
the sorting and selecting module is used for sequentially sorting association indexes generated by the products with low sales volume and other sales products, selecting the sales product with the largest association index expression value to be associated with the products with low sales volume, and transmitting information after the association of the products to the comprehensive analysis module;
after the association degree indexes generated by the products with low sales and other sales products are obtained, the generated association degree indexes are ordered according to the order from large to small, and the sales products with the maximum association degree index expression values and the products with low sales are selected for association sales, so that the association degree analysis can be carried out on the products with low sales and other sales products by combining sales data, and the association sales of the products with low sales and the sales products with the highest association degree can be carried out, compared with the prior art, the association of the two products according to sales experience can be carried out, the association precision of the products with low sales and other sales products can be improved, the efficient sales of the products for marketing can be facilitated, and the better management of marketing can be facilitated;
the comprehensive analysis module is used for acquiring the associated sales information, comprehensively analyzing the sales condition of the associated products and taking different measures;
a specific time period is selected to compare sales before and after product association, for example, weekly, bi-weekly, or tri-weekly may be selected as the time period, and is not specifically limited herein,acquiring the sales growth rate, the cross-sales ratio and the repeat purchase rate of the product after correlation, and respectively calibrating the sales growth rate, the cross-sales ratio and the repeat purchase rate as ZZL through a comprehensive analysis module after acquisition j 、JCX j 、CFG j ；
Calculating the sales growth rate after product association, comprising the following steps:
a. calculating a sum of sales for each product prior to association of the two products during the selected time period;
b. calculating the sum of sales after the association of two products in the same time period;
c. subtracting the sales before the association from the sales after the association to obtain an increase in sales, wherein the increase = sales after the association-sales before the association;
c. calculate growth rate, growth rate= (growth amount/sales before association) ×100%;
d. obtaining sales growth rate ZZL by value of growth rate j ；
Through the calculation, the sales growth rate of the product after correlation can be obtained, the growth rate can be used for evaluating the influence degree of two product correlations on sales, and a higher growth rate indicates that the sales are obviously promoted;
calculating the cross-selling ratio of the products after being correlated, comprising the following steps:
a. counting the number of customers who purchase one of the products and simultaneously purchase the other product during the selected time period;
b. calculating a cross-sales ratio = (number of customers who purchased one of the products and purchased the other product/total number of customers who purchased one of the products) ×100%;
c. obtaining cross-sell ratio JCX by cross-sell ratio value j ；
Through the calculation, the cross-selling ratio of two products after being associated can be obtained, the ratio can be used for evaluating the effect of the associated selling between the products, and a higher cross-selling ratio indicates that customers are more prone to purchasing the associated products at the same time;
calculating the repeated purchase rate after product association, comprising the following steps:
a. counting the number of customers who purchase the associated product again among the customers who purchase one of the products in the selected time period;
b. calculating a repeat purchase rate = (number of customers who purchase the associated product again/customer who purchase one of the products) x 100% among customers who purchase one of the products;
c. acquisition of repeat purchase rate CFG by value of repeat purchase rate j ；
Through the calculation, the re-purchase rate after the product association can be obtained, the ratio can be used for evaluating the influence of the product association sales on the loyalty and the re-purchase behavior of customers, and a higher re-purchase rate indicates that the customers are more prone to re-purchase the associated products;
obtaining the sales growth rate ZZL j Cross-selling ratio JCX j Repeat purchase rate CFG j Then, a data analysis model is established to generate an evaluation index P g o, according to the formula:
the method comprises the steps of carrying out a first treatment on the surface of the Wherein mu 1, mu 2 and mu 3 are sales increase rates ZZL respectively j Cross-selling ratio JCX j Repeat purchase rate CFG j And μ 1, μ 2, μ 3 are all greater than 0;
acquiring a plurality of evaluation indexes generated within a period of time, establishing a data set by the generated evaluation indexes, and calibrating the data set as A, wherein A= { P g o}＝{P g 1、P g 2、P g 3、…、P g N }, o is the number of evaluation indices within the data set, o=1, 2, 3, 4, & gt, N being a positive integer;
calculating the average value and the discrete degree value of the evaluation indexes in the data set, and respectively calibrating the average value and the discrete degree value asAnd P g X, if mean->If the product is larger than or equal to the evaluation index reference threshold, indicating that the sales condition of the associated product is better, generating an association success signal through the comprehensive analysis module, prompting sales personnel to keep the association of the product for further sales, and if the average value is +.>Less than the evaluation index reference threshold and the degree of discretion value P g X is larger than a discrete degree reference threshold value, which indicates that the stability of the sales condition of the associated product is poor, and generates an association stability poor signal through the comprehensive analysis module, so as to prompt sales personnel to further adjust the sales condition of the associated product in time, ensure that the sales condition of the associated product keeps a good and stable state, and if the average value is->Less than the evaluation index reference threshold range and the degree of discretion value P g X is smaller than or equal to a discrete degree reference threshold value, which indicates that the sales condition of the associated product is poor, and generates an association failure signal through the comprehensive analysis module, so as to prompt sales personnel to replace the associated product for resale, and timely find out the condition of poor association condition of the product;
the calculation formula of the discrete degree value of the evaluation index in the data set is as follows:
the method comprises the steps of carrying out a first treatment on the surface of the In the method, in the process of the invention,mean value of the evaluation index within the data set, P g X is a discrete degree value of an evaluation index in the data set;
according to the invention, through analyzing the situation after the association of the products, when the sales situation of the associated products is good, the sales personnel is prompted to keep the association of the products for continuous sales, when the stability of the sales situation of the associated products is poor, the sales personnel is prompted to further adjust the sales situation of the associated products in time, the situation of the sales of the associated products is ensured to keep in a good and stable state, when the sales situation of the associated products is poor, the comprehensive analysis module is used for generating an association failure signal, prompting the sales personnel to replace the associated products for resale, and timely finding out the situation of poor association of the products, thereby realizing supervision and timely adjustment of the sales situation of the associated products, further facilitating efficient sales of the marketing products, and further facilitating better management of marketing.
Example 2: the invention provides a marketing management method based on big data as shown in figure 2, which comprises the following steps:
collecting information when the product is sold, wherein the information when the product is sold comprises information for associating the product with low sales amount with other sold products;
establishing a data analysis model according to information of correlation between the products with low sales and other sales products, and generating a correlation index;
sequentially sequencing association indexes generated by products with low sales and other sales products, and selecting the sales product with the largest association index expression value to be associated with the products with low sales;
acquiring the associated sales information, comprehensively analyzing the sales condition of the associated products, and taking different measures;
the embodiment of the invention provides a big data-based marketing management method, which is realized by the big data-based marketing management system, and the specific method and the flow of the big data-based marketing management method are detailed in the embodiment of the big data-based marketing management system, and are not repeated here.
The above formulas are all formulas with dimensions removed and numerical values calculated, the formulas are formulas with a large amount of data collected for software simulation to obtain the latest real situation, and preset parameters in the formulas are set by those skilled in the art according to the actual situation.
While certain exemplary embodiments of the present invention have been described above by way of illustration only, it will be apparent to those of ordinary skill in the art that modifications may be made to the described embodiments in various different ways without departing from the spirit and scope of the invention. Accordingly, the drawings and description are to be regarded as illustrative in nature and not as restrictive of the scope of the invention, which is defined by the appended claims.
It is noted that relational terms such as first and second, and the like, if any, are used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Moreover, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising one … …" does not exclude the presence of other like elements in a process, method, article, or apparatus that comprises an element.
It should be understood that, in various embodiments of the present application, the sequence numbers of the foregoing processes do not mean the order of execution, and the order of execution of the processes should be determined by the functions and internal logic thereof, and should not constitute any limitation on the implementation process of the embodiments of the present application.
Those of ordinary skill in the art will appreciate that the various illustrative elements and algorithm steps described in connection with the embodiments disclosed herein may be implemented as electronic hardware, or combinations of computer software and electronic hardware. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the solution. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present application.
It will be clear to those skilled in the art that, for convenience and brevity of description, specific working procedures of the above-described systems, apparatuses and units may refer to corresponding procedures in the foregoing method embodiments, and are not repeated herein.
In the several embodiments provided in this application, it should be understood that the disclosed systems and methods may be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative, e.g., the division of the units is merely a logical function division, and there may be additional divisions when actually implemented, e.g., multiple units or components may be combined or integrated into another system, or some features may be omitted or not performed. Alternatively, the coupling or direct coupling or communication connection shown or discussed with each other may be an indirect coupling or communication connection via some interfaces, devices or units, which may be in electrical, mechanical or other form.
The units described as separate units may or may not be physically separate, and units shown as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.
In addition, each functional unit in each embodiment of the present application may be integrated in one processing unit, or each unit may exist alone physically, or two or more units may be integrated in one unit.
The foregoing is merely specific embodiments of the present application, but the scope of the present application is not limited thereto, and any person skilled in the art can easily think about changes or substitutions within the technical scope of the present application, and the changes and substitutions are intended to be covered by the scope of the present application. Therefore, the protection scope of the present application shall be subject to the protection scope of the claims.
Claims (6)
1. The marketing management system based on big data is characterized by comprising a data acquisition module, an analysis model building module, a sorting selection module and a comprehensive analysis module;
the data acquisition module acquires information when the product is sold, wherein the information when the product is sold comprises information for associating the product with other sold products, and the associated information is transmitted to the analysis model establishment module;
acquiring information of products during sales based on big data, acquiring the support degree, the confidence degree, the lifting degree and the chi-square value of the products with low sales and other sales products through a data acquisition module, and respectively calibrating the support degree, the confidence degree, the lifting degree and the chi-square value as、、、；
The support degree represents the probability of purchasing two products simultaneously, namely the frequency of the occurrence of the two products simultaneously, and the formula of the support degree is calculated as follows: support = number of simultaneous purchases of two productsThe total transaction times are marked as Xi for products with low sale quantity and other sale products, and Xz for the total transaction times, then +.>；
Confidence indicates if oneThe probability that a consumer purchases a certain product and purchases another product is measured by the confidence, and the confidence is calculated according to the formula: confidence = number of simultaneous purchases of two productsThe number of times of purchasing the first product, the number of times of simultaneously purchasing the product with low sales and other sales products is marked as Yi, the number of times of purchasing the product with low sales is marked as Yz, then +.>；
The lifting degree of the two product purchase relations is used for measuring the relative strength of the association relation between the two products, the lifting condition of the probability that the two products are purchased simultaneously relative to the probability that the two products are purchased independently can be presented, and the formula of the lifting degree is calculated as follows: degree of elevation = confidenceSupport degree, then->；
Chi-square value is a statistical indicator used to measure the degree of discrepancy between the actual observed data and the expected data, and can be used to measure the discrepancy between the crossover frequency and the expected frequency of two products when evaluating the purchase relevance of two products;
the step of calculating the chi-square value is as follows:
a. constructing a 2x2 cross table, wherein the rows represent the purchase of a first product and the columns represent the purchase of a second product;
b. counting the actually observed data, filling four cells in the cross table, wherein A represents the times of purchasing a first product and purchasing a second product, B represents the times of purchasing the first product but not purchasing the second product, C represents the times of not purchasing the first product but purchasing the second product, and D represents the times of not purchasing the first product and not purchasing the second product;
c. calculating the expected frequency of each cell, wherein the expected frequency is an expected value calculated according to the overall proportion under the independent assumption, and the calculation method comprises the following steps of:
expected frequency of first product purchase:；
desired frequency of first product not purchased:；
expected frequency of second product purchase:；
expected frequency of non-purchase of the second product:；
d. the chi-square value of each cell is calculated, the chi-square value being the sum of the square of the difference between the actual frequency and the desired frequency divided by the desired frequency, the calculation method being:；
the analysis model building module is used for building a data analysis model according to the information of the correlation between the products with low sales and other sales products, generating a correlation index and transmitting the correlation index to the sorting selection module;
obtaining the support degree of the product with low sales and other sales productsConfidence->Degree of elevation->Chi-square value->Then, a data analysis model is built through an analysis model building module, and a relevance index is generated>The formula according to is:
the method comprises the steps of carrying out a first treatment on the surface of the Wherein k is the number of other sales products, k=1, 2, 3, 4, … …, n is a positive integer, +.>、、、Support degree +.>Confidence->Degree of elevation->Chi-square value->Is a preset proportionality coefficient of>、、、Are all greater than 0;
the sorting and selecting module is used for sequentially sorting association indexes generated by the products with low sales volume and other sales products, selecting the sales product with the largest association index expression value to be associated with the products with low sales volume, and transmitting information after the association of the products to the comprehensive analysis module;
and the comprehensive analysis module is used for acquiring the associated sales information, comprehensively analyzing the sales condition of the associated products and taking different measures.
2. The marketing management system based on big data according to claim 1, wherein after the association index generated by the product with low sales volume and other sales products is obtained, the generated association index is ranked in order from big to small by the ranking selection module, and the sales product with the largest association index expression value is selected to be associated with the product with low sales volume for sale.
3. The marketing management system based on big data according to claim 1, wherein a specific time period is selected to compare sales before and after product association, the sales increase rate, the cross-sales rate and the repeat-purchasing rate after product association are obtained by the comprehensive analysis module, and after the obtaining, the sales increase rate, the cross-sales rate and the repeat-purchasing rate are respectively calibrated by the comprehensive analysis module as、、。
4. The big data based marketing management system of claim 3, wherein the sales growth rate is obtainedCross-sales ratio->Repeat purchase Rate->Then, a data analysis model is established through the comprehensive analysis module to generate an evaluation index +.>The formula according to is:
the method comprises the steps of carrying out a first treatment on the surface of the In (1) the->、、Sales growth rate ∈>Cross-sales ratio->Repeat purchase Rate->Is a preset proportionality coefficient of>、、Are all greater than 0.
5. The big data based marketing management system of claim 4, wherein the plurality of evaluation indexes generated within a period of time are obtained, the data set is established by the generated evaluation indexes, and the data set is marked as A, thenO is the number of evaluation indices within the data set, o=1, 2, 3, 4..n, N is a positive integer;
calculating the average value and the discrete degree value of the evaluation indexes in the data set, and respectively calibrating the average value and the discrete degree value asAnd->If the average value->When the evaluation index is larger than or equal to the evaluation index reference threshold value, generating a correlation success signal through the comprehensive analysis module, prompting sales personnel to keep the correlation of the product for further sales, and if the average value is +.>Less than the evaluation index reference threshold and a degree of discretion value +.>When the average value is larger than the discrete degree reference threshold value, generating a correlation stability difference signal through the comprehensive analysis module, prompting sales personnel to timely further adjust sales conditions of correlation products, and if the average value is +.>Less than the evaluation index reference threshold range and the degree of discretion value +.>When the discrete degree reference threshold value is smaller than or equal to the discrete degree reference threshold value, generating an association failure signal through the comprehensive analysis module, prompting sales personnel to replace associated products for resale, and timely finding out the condition of bad association conditions of the products;
the calculation formula of the discrete degree value of the evaluation index in the data set is as follows:
the method comprises the steps of carrying out a first treatment on the surface of the In (1) the->Mean value of the evaluation index within the data set, +.>The degree of dispersion value of the index is evaluated within the data set.
6. A big data based marketing management method, implemented by the big data based marketing management system of any of the claims 1-5, comprising the steps of:
collecting information when the product is sold, wherein the information when the product is sold comprises information for associating the product with low sales amount with other sold products;
establishing a data analysis model according to information of correlation between the products with low sales and other sales products, and generating a correlation index;
sequentially sequencing association indexes generated by products with low sales and other sales products, and selecting the sales product with the largest association index expression value to be associated with the products with low sales;
and acquiring the associated sales information, comprehensively analyzing the sales condition of the associated products, and taking different measures.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310939577.8A CN117035818B (en) | 2023-07-28 | 2023-07-28 | Marketing management method and system based on big data |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310939577.8A CN117035818B (en) | 2023-07-28 | 2023-07-28 | Marketing management method and system based on big data |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117035818A CN117035818A (en) | 2023-11-10 |
| CN117035818B true CN117035818B (en) | 2024-03-22 |
Family
ID=88632809
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310939577.8A Active CN117035818B (en) | 2023-07-28 | 2023-07-28 | Marketing management method and system based on big data |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117035818B (en) |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2003048901A2 (en) * | 2001-12-04 | 2003-06-12 | Kimberly-Clark Worldwide, Inc. | Business planner |
| CN109658132A (en) * | 2018-11-29 | 2019-04-19 | 深圳冠思大数据服务有限公司 | A kind of sale effect artificial intelligence analysis's method and system |
| CN109670861A (en) * | 2018-11-30 | 2019-04-23 | 深圳冠思大数据服务有限公司 | Commodity on shelf sale effect method for improving and system based on artificial intelligence |
| CN110880136A (en) * | 2018-09-06 | 2020-03-13 | 北京京东尚科信息技术有限公司 | Recommended methods, systems, devices, and storage media for companion products |
| CN114331256A (en) * | 2021-11-30 | 2022-04-12 | 李萌 | Commercial size distribution evaluation system |
| CN114493705A (en) * | 2022-01-27 | 2022-05-13 | 广东工业大学 | Product sales influencing factor monitoring system oriented to full life cycle |
| CN114943561A (en) * | 2022-06-08 | 2022-08-26 | 中凯达设施管理(北京)有限公司 | A marketing management system |
| CN115577991A (en) * | 2022-12-08 | 2023-01-06 | 南京风船云聚信息技术有限公司 | Business intelligent data analysis system and analysis method based on big data |
-
2023
- 2023-07-28 CN CN202310939577.8A patent/CN117035818B/en active Active
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2003048901A2 (en) * | 2001-12-04 | 2003-06-12 | Kimberly-Clark Worldwide, Inc. | Business planner |
| CN110880136A (en) * | 2018-09-06 | 2020-03-13 | 北京京东尚科信息技术有限公司 | Recommended methods, systems, devices, and storage media for companion products |
| CN109658132A (en) * | 2018-11-29 | 2019-04-19 | 深圳冠思大数据服务有限公司 | A kind of sale effect artificial intelligence analysis's method and system |
| CN109670861A (en) * | 2018-11-30 | 2019-04-23 | 深圳冠思大数据服务有限公司 | Commodity on shelf sale effect method for improving and system based on artificial intelligence |
| CN114331256A (en) * | 2021-11-30 | 2022-04-12 | 李萌 | Commercial size distribution evaluation system |
| CN114493705A (en) * | 2022-01-27 | 2022-05-13 | 广东工业大学 | Product sales influencing factor monitoring system oriented to full life cycle |
| CN114943561A (en) * | 2022-06-08 | 2022-08-26 | 中凯达设施管理(北京)有限公司 | A marketing management system |
| CN115577991A (en) * | 2022-12-08 | 2023-01-06 | 南京风船云聚信息技术有限公司 | Business intelligent data analysis system and analysis method based on big data |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117035818A (en) | 2023-11-10 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Abdellaoui et al. | Risk aversion elicitation: reconciling tractability and bias minimization | |
| Borle et al. | The impact of survey participation on subsequent customer behavior: An empirical investigation | |
| Mehta | Service quality as predicator of patient satisfaction: a study of the health care sector | |
| Rudolf et al. | Price setting before and during the pandemic: evidence from Swiss consumer prices | |
| Jankalová | Service quality-object of Business excellence measuring | |
| CN117035818B (en) | Marketing management method and system based on big data | |
| CN120106902B (en) | Activity voucher issuance method, system, intelligent terminal and storage medium | |
| Sikka Kainth et al. | Consumption values: scale development and validation | |
| Azami | Factors affecting customers’ purchasing behavior in online shopping | |
| Enza Wella et al. | Service quality dealer identification: the optimization of K-Means clustering | |
| CN113887969A (en) | An intelligent evaluation method for the use behavior of retail customers' terminal equipment | |
| CN118505052A (en) | Sign information acquisition, evaluation, analysis and management system based on intelligent data analysis | |
| CN117372065A (en) | Intelligent product pricing method and system based on user information | |
| JP6927894B2 (en) | Service content management device and service content management method | |
| SHEN et al. | The effects of time-limited pressure and perceived value on consumers’ intention to purchase: A study of travel fairs | |
| Putri et al. | The Influence of User Experience on Decisions PLN Mobile User Purchases | |
| Pratama et al. | Analysis of the Impact of Covid-19 and Company Policies on Sales Volume in the New Normal Period (Case Study: Medan Market Center) | |
| Planing | Measuring consumer innovativeness: an empirical re-evaluation of Roger’s innovativeness scale | |
| Rukmansyah | The Influence of Customer Engagement, Customer Loyalty and Customer Experience on Sales Achievement (Kasus: Imunicare by Bio Farma). | |
| Dubé et al. | Income and wealth effects on private-label demand: evidence from the great recession | |
| Sattapong et al. | The influence of 7P’s of marketing on consumer purchase decisions on online food delivery service: an empirical study in Bangkok its Metropolitan Areas | |
| US20250232321A1 (en) | Information generation device, information generation method, and storage medium | |
| Mawoli | Service quality and customer satisfaction: evidence from deposit money banks’ customers in Gwagwalada, FCT Abuja-Nigeria | |
| Šumak et al. | An empirical study of factors affecting the adoption of self-service checkout terminals in Slovenia | |
| Wu et al. | Interviewer Ratings of Physical Appearance in a Large-Scale Survey in China |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |