CN117541279A - Shopping center industry recommendation index calculation method and system - Google Patents
Shopping center industry recommendation index calculation method and system Download PDFInfo
- Publication number
- CN117541279A CN117541279A CN202311317191.XA CN202311317191A CN117541279A CN 117541279 A CN117541279 A CN 117541279A CN 202311317191 A CN202311317191 A CN 202311317191A CN 117541279 A CN117541279 A CN 117541279A
- Authority
- CN
- China
- Prior art keywords
- data
- industry
- shopping mall
- shopping
- value
- 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.)
- Pending
Links
- 238000004364 calculation method Methods 0.000 title claims abstract description 8
- 238000000034 method Methods 0.000 claims abstract description 25
- 230000000694 effects Effects 0.000 claims abstract description 17
- 238000007781 pre-processing Methods 0.000 claims abstract description 10
- 230000008569 process Effects 0.000 claims abstract description 10
- PEDCQBHIVMGVHV-UHFFFAOYSA-N Glycerine Chemical compound OCC(O)CO PEDCQBHIVMGVHV-UHFFFAOYSA-N 0.000 claims abstract description 4
- 238000004422 calculation algorithm Methods 0.000 claims description 6
- 238000010606 normalization Methods 0.000 claims description 5
- 238000013480 data collection Methods 0.000 claims description 4
- 230000015572 biosynthetic process Effects 0.000 claims description 3
- 238000004140 cleaning Methods 0.000 claims description 3
- 238000003860 storage Methods 0.000 claims description 3
- 238000003786 synthesis reaction Methods 0.000 claims description 3
- 238000010200 validation analysis Methods 0.000 claims description 3
- 230000000052 comparative effect Effects 0.000 abstract description 4
- 238000011161 development Methods 0.000 description 7
- 238000011156 evaluation Methods 0.000 description 7
- 241001122767 Theaceae Species 0.000 description 5
- 238000010586 diagram Methods 0.000 description 4
- 238000012360 testing method Methods 0.000 description 3
- 238000012549 training Methods 0.000 description 3
- 238000012795 verification Methods 0.000 description 3
- 238000004458 analytical method Methods 0.000 description 2
- 230000008859 change Effects 0.000 description 2
- 230000008676 import Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000002093 peripheral effect Effects 0.000 description 2
- 238000011160 research Methods 0.000 description 2
- 238000012800 visualization Methods 0.000 description 2
- 239000000654 additive Substances 0.000 description 1
- 230000000996 additive effect Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000008901 benefit Effects 0.000 description 1
- 238000007405 data analysis Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 230000036541 health Effects 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 238000005065 mining Methods 0.000 description 1
- 238000012821 model calculation Methods 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 238000004451 qualitative analysis Methods 0.000 description 1
- 238000011158 quantitative evaluation Methods 0.000 description 1
- 230000005855 radiation Effects 0.000 description 1
- 238000012216 screening Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR 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; CALCULATING OR 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
- G06Q30/0203—Market surveys; Market polls
Landscapes
- Business, Economics & Management (AREA)
- Strategic Management (AREA)
- Engineering & Computer Science (AREA)
- Accounting & Taxation (AREA)
- Development Economics (AREA)
- Finance (AREA)
- Entrepreneurship & Innovation (AREA)
- Game Theory and Decision Science (AREA)
- Data Mining & Analysis (AREA)
- Economics (AREA)
- Marketing (AREA)
- Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a shopping center industry recommendation index calculation method and a system, wherein the method comprises the following steps: s1: acquiring various shopping center data, including the lunar plateau effect of a target industry store, various crowd data and various city data; s2: preprocessing the various shopping center data to obtain preprocessed various shopping center data; s3: taking the moon plateau effect of the pretreated target industry store as a Y value, taking other types of data of the pretreated various shopping center data as an X value, establishing a regression model for fitting, and determining the data category which positively contributes to the target value in the fitting process; s4: determining a weight of the data category that positively contributes to the target value; s5: and calculating an industry recommendation index according to the data category positively contributing to the target value and the corresponding weight. The invention provides quantitative, comprehensive, dynamic and comparative shopping center assessment results for brands and helps the brands to make more intelligent selections.
Description
Technical Field
The invention relates to the technical field of shopping center industry recommendation, in particular to a shopping center industry recommendation index calculation method and system.
Background
Traditional shopping center selection schemes are implemented by selection strategies from aspects of city level, producer, commercial volume, resident brand and the like, and mainly based on qualitative analysis, the selection strategies can roughly comprise the following steps:
the shopping mall with large size and high quality is preferred: such shopping centers are often located in first-line or new-line cities, operated by well-known producers, with large commercial volumes and high volumes of customers. Such a selection is particularly suited for brands that require high-end experience stores, and can maximize brand exposure and sales performance.
Shopping centers that tend to bid on, not already in themselves: this strategy stems from the following of the bid. Selecting a shopping mall where an existing core bid exists but its own brand is not already resident reduces the risk of camping and may benefit from the bidding consumer.
Preference for areas of well-defined surrounding facilities and dense population: typically, shopping malls radiate over a range of 3 km. Therefore, stores are arranged in places with concentrated population and rich living facilities, so that brands can attract more customers, the stability of passenger flow is ensured, and the management risk is reduced.
The conventional shopping mall selection scheme can meet the site selection requirements of brands to a certain extent, but still has the following obvious defects:
data limitation: traditional schemes often rely on public, conventional data such as city level, ratings of the producer, business volumes, etc. These data cannot fully reflect the actual daily operational conditions of the shopping mall, such as daily traffic, passenger traffic flow, etc.
Neglecting market dynamics: market environments are constantly changing, and potential consumer groups, consumer needs, strategies for bidding, brand presence, etc. within the radiation range may impact the attractiveness and competitiveness of the shopping mall. The traditional selection evaluation scheme cannot quickly acquire the dynamic information, and the dynamic property is ignored in evaluation and selection.
Information asymmetry: conventional solutions often fail to provide a comprehensive view of all important information about the shopping mall, such as consumer habits of customer groups, demographics of surrounding communities. Such information asymmetry may lead to less than ideal selection of brands.
Unable to quantify and compare laterally: traditional shopping center selection schemes are generally based on qualitative judgment, such as fuzzy concepts like 'large-scale quality' or 'complete set', and lack quantitative standards and indexes. This situation makes it difficult to make accurate lateral comparisons between different shopping malls, increasing the difficulty of brands in making decisions. In addition, due to the lack of quantitative evaluation, brands cannot clearly track and evaluate the effect of their addressing strategies, and cannot adjust and optimize strategies in time.
Disclosure of Invention
The primary purpose of the invention is to provide a shopping center industry recommendation index calculation method, which solves the technical problem that the existing method cannot provide quantitative, comprehensive, dynamic and comparative shopping center evaluation results and helps brands to select more wisely.
It is a further object of the present invention to provide a shopping mall industry recommendation index computing system.
In order to solve the technical problems, the technical scheme of the invention is as follows:
a shopping center industry recommendation index calculating method comprises the following steps:
s1: acquiring various shopping center data, including the lunar plateau effect of a target industry store, various crowd data and various city data;
s2: preprocessing the various shopping center data to obtain preprocessed various shopping center data;
s3: taking the moon plateau effect of the pretreated target industry store as a Y value, taking other types of data of the pretreated various shopping center data as an X value, establishing a regression model for fitting, and determining the data category which positively contributes to the target value in the fitting process;
s4: determining a weight of the data category that positively contributes to the target value;
s5: and calculating an industry recommendation index according to the data category positively contributing to the target value and the corresponding weight.
Further, the various shopping mall data in the step S1 further include industry POI data, city wide crowd figure, population number data, city wide population scale and grade list data, city wide economic statistics data and shopping mall AOI data.
Further, the preprocessing of the data of the shopping malls in step S2 includes performing data collection, cleaning, storage and updating operations on the data of the shopping malls based on the service requirements and the preset rules.
Further, the preprocessing of the various shopping mall data in step S2 further includes calculating saturation of the shopping mall target industry, specifically:
shopping mall target industry saturation = shopping mall target industry density/city industry density ×100%
Wherein:
shopping mall target industry density = number of industry stores in shopping mall/number of all industry stores in shopping mall
Urban industry density = urban shopping mall industry average duty cycle/grade urban shopping mall industry average duty cycle
Average ratio of urban shopping mall industry = sum of ratios of all shopping mall industries in city/number of shopping malls
Average ratio of equal-grade city shopping mall industry = ratio synthesis/city number of all shopping mall industries in same population scale grade city
The number of industry stores in the shopping center, the number of all industry stores in the shopping center, the sum of the ratio of all shopping center industries in the city, the number of the shopping centers, the ratio of all shopping center industries in the city with the same population scale level are integrated, and the number of the city is obtained from the data of all shopping centers.
Further, the preprocessed shopping mall data includes saturation of target industries of the shopping mall.
Further, the regression model uses the XGBRegresor algorithm.
Further, in the step S3, the SHAP is used to calculate the importance value for the data category in the fitting process, and the data category that has a positive contribution to the target value is determined according to the importance value.
Further, in the step S4, the weights of the data types that positively contribute to the target value are determined specifically:
normalizing the important value of the data category which positively contributes to the target value, wherein the value of the normalization is 0 to 100, and the data category which positively contributes to the target value with the quantile of more than 75% is reserved;
and calculating the duty ratio of the important value of each data category to the sum of the important values of all the data categories with positive contribution to the target value as the weight of the data category according to the important value of each data category with positive contribution to the target value after normalization.
Further, in the step S5, according to the data category that has positive contribution to the target value and the corresponding weight, an industry recommendation index is calculated, which specifically includes:
recommended index= (feature 1 value x weight 1) + (feature 2 value x weight 2) +
The values of feature 1, feature 2, feature k are the values of the data types that each positively contributes to the target value, and the weights 1, 2, and k are the weights of the corresponding data types that each positively contributes to the target value.
A shopping mall industry recommendation index computing system, comprising:
the data acquisition module acquires various shopping center data, including the lunar plateau effect of a target industry store, various crowd data and various city data;
the pretreatment module is used for carrying out pretreatment on the various shopping mall data to obtain pretreated various shopping mall data;
the regression module is used for establishing a regression model for fitting by taking the month average plateau effect of the pretreated target industry store as a Y value and other types of data of the pretreated various shopping center data as an X value, and determining the data category positively contributing to the target value in the fitting process;
a weight validation module that determines a weight of the data category that positively contributes to the target value;
and the calculating module calculates an industry recommendation index according to the data category positively contributing to the target value and the corresponding weight.
Compared with the prior art, the technical scheme of the invention has the beneficial effects that:
the method is characterized in that passenger flow and visiting crowd image data under a statistical shopping center are collected, the change condition of the number of industry stores is monitored on the urban level, and the saturation condition of the same industry is analyzed by monitoring the specific condition of the city and the change condition of the number of stores of the target brands of the same industry on the urban level. Based on the two data, the commercial recommendation index of the shopping center is comprehensively obtained, and various data of the shopping center such as passenger flow, crowd portraits, competition conditions of the same industry and the like are analyzed through an algorithm, so that a quantitative, comprehensive, dynamic and comparative shopping center evaluation result is provided for brands, and the brands are helped to make more intelligent selections.
Drawings
Fig. 1 is a schematic flow chart of a method for calculating a recommendation index of a shopping mall industry according to an embodiment of the present invention.
Fig. 2 is a schematic diagram of treeexplatiner explanation provided in an embodiment of the present invention
Fig. 3 is a schematic diagram of an important feature visualization result provided by an embodiment of the present invention.
Fig. 4 is a schematic diagram of a general industry recommendation index generation flow of a shopping mall according to an embodiment of the present invention.
FIG. 5 is a schematic diagram of a shopping mall industry recommendation index computing system according to an embodiment of the present invention.
Detailed Description
The drawings are for illustrative purposes only and are not to be construed as limiting the present patent;
for the purpose of better illustrating the embodiments, certain elements of the drawings may be omitted, enlarged or reduced and do not represent the actual product dimensions;
it will be appreciated by those skilled in the art that certain well-known structures in the drawings and descriptions thereof may be omitted.
The technical scheme of the invention is further described below with reference to the accompanying drawings and examples.
Example 1
A shopping center industry recommendation index calculating method, as shown in figure 1, comprises the following steps:
s1: acquiring various shopping center data, including the lunar plateau effect of a target industry store, various crowd data and various city data;
s2: preprocessing the various shopping center data to obtain preprocessed various shopping center data;
s3: taking the moon plateau effect of the pretreated target industry store as a Y value, taking other types of data of the pretreated various shopping center data as an X value, establishing a regression model for fitting, and determining the data category which positively contributes to the target value in the fitting process;
s4: determining a weight of the data category that positively contributes to the target value;
s5: and calculating an industry recommendation index according to the data category positively contributing to the target value and the corresponding weight.
The embodiment of the invention is obtained based on diversified data analysis of passenger flow, crowd images and saturation of the same industry. Through deep mining and comprehensive evaluation of the passenger flow scale, the consumer characteristics and the competition conditions of the same industry of the shopping centers, the recommendation index of each shopping center is obtained, and the recommendation index is used as an important reference basis, so that powerful support can be provided for brand selection of the shopping centers, and quantifiable and comparative shopping center evaluation results can be provided.
Example 2
The present embodiment continues to disclose the following on the basis of embodiment 1:
the various shopping center data in the step S1 further include industry POI data, city wide crowd figure, population quantity data, city wide population scale rating list data, city wide economic statistics data and shopping center AOI data.
The shopping centers also comprise data target population indexes obtained by using a TGI (Target Group Index) analysis method, wherein the TGI analysis method is an index reflecting the strength or weakness of the target population in a specific research range (such as a statistical field and a media audience), the target population is generally compared with the overall city level, the target population index can be generally represented by the difference in the specific research range and is used for transverse comparison, and the TGI is 100, namely the average level is represented.
In a specific example, national urban population scale levels are shown in table 1.
Table 1 national urban population Scale rating
The industry POI data may provide detailed information about the point of business; the whole city crowd image and population quantity data can help to know the population distribution, age, income, occupation and other population related statistical information of each city, such as city GDP, consumption level, employment situation and the like, and can provide the information of economic development status, consumption capacity and the like of the city; the urban population scale level listing data can help determine the distribution of the same-level urban industry.
In a further embodiment, the preprocessing the various shopping mall data in step S2 includes performing data collection, cleaning, storage and updating operations on the various shopping mall data based on service requirements and preset rules.
In a further embodiment, the preprocessing the various shopping mall data in step S2 further includes calculating a target industry saturation of the shopping mall, and delineating the number of industry stores in the shopping mall according to the AOI range, based on these data, the target industry saturation of the shopping mall is specifically:
shopping mall target industry saturation = shopping mall target industry density/city industry density ×100%
Wherein:
shopping mall target industry density = number of industry stores in shopping mall/number of all industry stores in shopping mall
Urban industry density = urban shopping mall industry average duty cycle/grade urban shopping mall industry average duty cycle
Average ratio of urban shopping mall industry = sum of ratios of all shopping mall industries in city/number of shopping malls
Average ratio of equal-grade city shopping mall industry = ratio synthesis/city number of all shopping mall industries in same population scale grade city
The number of industry stores in the shopping center, the number of all industry stores in the shopping center, the sum of the ratio of all shopping center industries in the city, the number of the shopping centers, the ratio of all shopping center industries in the city with the same population scale level are integrated, and the number of the city is obtained from the data of all shopping centers.
In a further embodiment, the pre-processed types of shopping mall data include shopping mall target industry saturation.
In a specific embodiment, the calculated shopping mall target industry saturation is shown in Table 2.
Table 2 shopping mall target industry saturation
In a further embodiment, the regression model uses the XGBRegresor algorithm.
In a specific embodiment, feature data and tag data are first established, namely an X value and a Y value of the input parameters respectively, wherein the X value is industry saturation, population number, crowd image data, POI number, POI density, city economic data and the like, the Y value is a month average plateau effect (month average sales volume/store area) of a target industry store, and the Y value is a true value. The month average sales data is party data, is brand owned data, and is provided and authorized for use by a brand party. Taking the tea industry as an example, the data samples are shown in table 3:
TABLE 3 Table 3
The data are split into a training set, a verification set and a test set, wherein the data are divided into 80% of the training set, 10% of the verification set and 10% of the test set.
The XGBRegresor algorithm is used for target prediction regression, the predicted target value is the lunar plateau effect of a target industry store, and the XGBRegresor model parameters are shown in table 4.
TABLE 4 Table 4
The evaluation index mainly comprises average absolute error and R square value, and each index value of the training set, the verification set and the test set has the result shown in table 5.
TABLE 5
In a further embodiment, in the step S3, the SHAP is used to calculate an importance value for the data category in the fitting process, and the data category that has a positive contribution to the target value is determined according to the importance value. SHAP (SHapley Additive exPlanations) is a library for interpreting machine learning model predictions, and by calculating Shapley values, the contribution of each feature to model predictions is interpreted, thereby helping us understand the model's prediction cause. Shapley is a concept in cooperative game theory and is used for measuring contribution of participants to cooperative value, and average contribution of each feature to model prediction results can be calculated.
In a specific embodiment, based on a trained model, 400 data samples are used for treeexplatiner interpretation, as shown in fig. 2, and the obtained important feature visualization result is shown in fig. 3, from which the features such as "the saturation of the tea industry", "the GDP (graphic display map) ratio of the third industry of the city", "the age of children of the living population 6-12 years" have a great contribution to the model prediction target. Based on this, all features that contributed positively to the predicted target (importance > 0) can be screened out as shown in table 6:
TABLE 6
In a further embodiment, the determining the weight of the data class that has a positive contribution to the target value in the step S4 is specifically:
normalizing the important value of the data category which positively contributes to the target value, wherein the value of the normalization is 0 to 100, and the data category which positively contributes to the target value with the quantile of more than 75% is reserved for reducing the influence of long tail characteristics, as shown in a table 7;
TABLE 7
Based on the normalized importance values of the data categories that each positively contributed to the target value, the duty ratio of the importance value of each data category to the sum of the importance values of all the data categories that positively contributed to the target value is calculated as the weight of the data category, as shown in table 8.
TABLE 8
In a further embodiment, in the step S5, an industry recommendation index is calculated according to the data category that has a positive contribution to the target value and the corresponding weight, specifically:
recommended index= (feature 1 value x weight 1) + (feature 2 value x weight 2) +
The values of feature 1, feature 2, feature k are the values of the data types that each positively contributes to the target value, and the weights 1, 2, and k are the weights of the corresponding data types that each positively contributes to the target value.
In a specific embodiment, the final recommendation index score is:
recommendation index = tea industry saturation 0.263988+ third industry GDP duty cycle 0.230954+ composition_child age 6-12 years _percentage 0.106585+ other premises district 0.105312+ work_occupation subdivision_public relations/medium_percentage 0.068942+ resident average dominant income 0.063067+ banking financial institution present foreign currency deposit balance 0.051083+ live_occupation subdivision software engineer _percentage 0.048472+ odi 0.046377+ import total 0.039970+ third industry annual same 0.039718
This is wherein:
-the saturation of the tea industry is an industry saturation index
-third industry GDP ratio, banking financial institution's foreign currency deposit balance, resident income, import and export amount, third industry annual homonymy are city economic index data for representing development potential index
-composition_child age_6-12 years old_percentage, work_professional subdivision_customs/media_percentage, live_professional subdivision_software engineer_percentage, etc. are human group image data for representing population quantity and population quality index
-other real estate cells are peripheral cell count statistics for representing basic matching indexes
-Audi is a surrounding Audi brand 4S store quantity statistics for representing brand atmosphere indicators
Specific indexes are different in different industries, and the indexes are used in the recommended indexes of the tea industry.
As shown in fig. 4, the general industry recommendation index generation method for the shopping center comprises the following steps: based on the data characteristics of the existing data, the method is divided into indexes such as industry saturation, population quantity, population quality, regional development potential, peripheral supporting facility perfection, business atmosphere degree and the like as model calculation input, and finally industry recommendation index results are calculated.
Step1, first, the saturation of the shopping mall target industry needs to be calculated. For this, city industry density and shopping mall industry density of each industry of the whole city are calculated in advance. Then, comparing the industry density of the shopping mall with the industry density of the city to obtain the target industry saturation of the shopping mall, which helps us mark the difference between the average level of the shopping mall and the city and understand the market position of the shopping mall in the industry.
Step2, based on population data population quantity index, the index adopts APP for data collection and is provided by a third-party data provider. By considering the resident population number, the working population number, the living population number, the floating population number and the passenger flow data of the shopping center, and integrating these factors, an accurate population number index can be obtained for judging the potential consumption capacity of the shopping center.
Step3, based on the demographic quality index of the demographic data, the index is collected by APP and provided by a third party data provider. The index depends on a plurality of subdivision indexes such as basic crowd portraits (including age, gender, education level and the like), consumer crowd portraits (including consumption capacity, consumption habit and the like), life crowd portraits (including life style, hobbies, health conditions and the like), work crowd portraits (including occupation, work place, income level and the like).
Step4, calculating the development potential index of the area where the shopping center is located based on the urban economic statistical data. This includes economic indicators of urban economic development (GDP, total amount of social retail consumer goods), industry structure, employment rate, income per capita, etc., as parameters for determining economic development trend and consumption ability of the area.
Step5, acquiring information such as surrounding community house price information, public service facilities (such as schools and hospitals), traffic facilities (such as bus stations and subway stations), business facilities (such as supermarkets, restaurants and entertainment venues) and the like, and taking the information as a reference to embody the matching perfection of the surrounding of the shopping center so as to know the living environment and the living convenience of the place of the shopping center.
Step6, counting whether the head brand of the key industry is in or not to serve as a commercial atmosphere index of the shopping center. This means that the kind, quantity and quality of brands that have entered the shopping mall will be examined to see the commercial competitiveness and appeal of the mall.
Step7, inputting each index generated in the previous six steps into a recommendation index calculation formula as a parameter to obtain a universal industry recommendation index of the shopping center, and providing a basis for brand site selection.
After the algorithm model is operated, the related data of the recommended index can be connected to the score, the score of the recommended index of the shopping center can be presented on the score, and the sorting comparison operation can be carried out on all shopping centers in the city.
Meanwhile, besides ordering shopping centers of cities, indexes such as recommendation indexes, population, POIs and the like can be also browsed. The recommendation indexes are digitalized and displayed in an index refinement mode, including development potential, brand atmosphere, basic matching, population quantity, population quality and the like, and the recommendation indexes of other shopping centers are transversely compared with each other through radar graphs. And the screening result is also supported to be issued to appointed people, so that sharing is realized.
Example 3
The embodiment provides a shopping mall industry recommendation index calculating system, as shown in fig. 5, including:
the data acquisition module acquires various shopping center data, including the lunar plateau effect of a target industry store, various crowd data and various city data;
the pretreatment module is used for carrying out pretreatment on the various shopping mall data to obtain pretreated various shopping mall data;
the regression module is used for establishing a regression model for fitting by taking the month average plateau effect of the pretreated target industry store as a Y value and other types of data of the pretreated various shopping center data as an X value, and determining the data category positively contributing to the target value in the fitting process;
a weight validation module that determines a weight of the data category that positively contributes to the target value;
and the calculating module calculates an industry recommendation index according to the data category positively contributing to the target value and the corresponding weight.
The same or similar reference numerals correspond to the same or similar components;
the terms describing the positional relationship in the drawings are merely illustrative, and are not to be construed as limiting the present patent;
it is to be understood that the above examples of the present invention are provided by way of illustration only and not by way of limitation of the embodiments of the present invention. Other variations or modifications of the above teachings will be apparent to those of ordinary skill in the art. It is not necessary here nor is it exhaustive of all embodiments. Any modification, equivalent replacement, improvement, etc. which come within the spirit and principles of the invention are desired to be protected by the following claims.
Claims (10)
1. The shopping center industry recommendation index calculating method is characterized by comprising the following steps of:
s1: acquiring various shopping center data, including the lunar plateau effect of a target industry store, various crowd data and various city data;
s2: preprocessing the various shopping center data to obtain preprocessed various shopping center data;
s3: taking the moon plateau effect of the pretreated target industry store as a Y value, taking other types of data of the pretreated various shopping center data as an X value, establishing a regression model for fitting, and determining the data category which positively contributes to the target value in the fitting process;
s4: determining a weight of the data category that positively contributes to the target value;
s5: and calculating an industry recommendation index according to the data category positively contributing to the target value and the corresponding weight.
2. The shopping mall industry recommendation index calculating method according to claim 1, wherein the various kinds of shopping mall data in step S1 further include industry POI data, city wide crowd figure, population number data, city wide population scale class list data, city wide economic statistics data and shopping mall AOI data.
3. The shopping mall industry recommendation index calculating method according to claim 1, wherein the preprocessing of the various kinds of shopping mall data in step S2 includes data collection, cleaning, storage and updating of the various kinds of shopping mall data based on business requirements and preset rules.
4. The shopping mall industry recommendation index calculating method according to claim 3, wherein the preprocessing of the various kinds of shopping mall data in step S2 further includes calculating a shopping mall target industry saturation, specifically:
shopping mall target industry saturation = shopping mall target industry density/city industry density ×100%
Wherein:
shopping mall target industry density = number of industry stores in shopping mall/number of all industry stores in shopping mall
Urban industry density = urban shopping mall industry average duty cycle/grade urban shopping mall industry average duty cycle
Average ratio of urban shopping mall industry = sum of ratios of all shopping mall industries in city/number of shopping malls
Average ratio of equal-grade city shopping mall industry = ratio synthesis/city number of all shopping mall industries in same population scale grade city
The number of industry stores in the shopping center, the number of all industry stores in the shopping center, the sum of the ratio of all shopping center industries in the city, the number of the shopping centers, the ratio of all shopping center industries in the city with the same population scale level are integrated, and the number of the city is obtained from the data of all shopping centers.
5. The shopping mall industry recommendation index calculating method according to claim 4, wherein the preprocessed types of shopping mall data include shopping mall target industry saturation.
6. The shopping mall industry recommendation index calculation method according to claim 5, wherein the regression model uses xgbregress algorithm.
7. The shopping mall industry recommendation index calculating method according to claim 6, wherein in the step S3, the SHAP is used to calculate the importance value for the data category in the fitting process, and the data category that positively contributes to the target value is determined according to the importance value.
8. The shopping mall industry recommendation index calculation method according to claim 7, wherein the determining the weight of the data category that positively contributes to the target value in step S4 is specifically:
normalizing the important value of the data category which positively contributes to the target value, wherein the value of the normalization is 0 to 100, and the data category which positively contributes to the target value with the quantile of more than 75% is reserved;
and calculating the duty ratio of the important value of each data category to the sum of the important values of all the data categories with positive contribution to the target value as the weight of the data category according to the important value of each data category with positive contribution to the target value after normalization.
9. The shopping mall industry recommendation index calculating method according to claim 8, wherein the calculating of the industry recommendation index in step S5 according to the data category that positively contributes to the target value and the corresponding weight specifically includes:
recommended index= (feature 1 value x weight 1) + (feature 2 value x weight 2) +
The values of feature 1, feature 2, feature k are the values of the data types that each positively contributes to the target value, and the weights 1, 2, and k are the weights of the corresponding data types that each positively contributes to the target value.
10. A shopping mall industry recommendation index computing system, comprising:
the data acquisition module acquires various shopping center data, including the lunar plateau effect of a target industry store, various crowd data and various city data;
the pretreatment module is used for carrying out pretreatment on the various shopping mall data to obtain pretreated various shopping mall data;
the regression module is used for establishing a regression model for fitting by taking the month average plateau effect of the pretreated target industry store as a Y value and other types of data of the pretreated various shopping center data as an X value, and determining the data category positively contributing to the target value in the fitting process;
a weight validation module that determines a weight of the data category that positively contributes to the target value;
and the calculating module calculates an industry recommendation index according to the data category positively contributing to the target value and the corresponding weight.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311317191.XA CN117541279A (en) | 2023-10-11 | 2023-10-11 | Shopping center industry recommendation index calculation method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311317191.XA CN117541279A (en) | 2023-10-11 | 2023-10-11 | Shopping center industry recommendation index calculation method and system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117541279A true CN117541279A (en) | 2024-02-09 |
Family
ID=89784981
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311317191.XA Pending CN117541279A (en) | 2023-10-11 | 2023-10-11 | Shopping center industry recommendation index calculation method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117541279A (en) |
-
2023
- 2023-10-11 CN CN202311317191.XA patent/CN117541279A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| González-García et al. | Embedding environmental, economic and social indicators in the evaluation of the sustainability of the municipalities of Galicia (northwest of Spain) | |
| Grilo et al. | Determinants of entrepreneurial engagement levels in Europe and the US | |
| Buys et al. | Road network upgrading and overland trade expansion in Sub-Saharan Africa | |
| Karabarbounis | One dollar, one vote | |
| JP2001117973A (en) | Device and method for evaluating real estate, recording medium storing real estate evaluation program and real estate information providing system | |
| Zheng et al. | Land supply and capitalization of public goods in housing prices: Evidence from Beijing | |
| Folfas | FDI between EU member states: gravity model and taxes | |
| Tan | Report on the development of household finance in rural China (2014) | |
| Yang et al. | Modelling the emergence of spatial patterns of economic activity | |
| KR20070097939A (en) | Method for providing real estate information using client/server and computer readable medium for storing program performing the same | |
| Decuseară | Using the general electric/Mckinsey Matrix in the process of selecting the central and east European markets | |
| Karami et al. | Structural analysis of factors affecting the housing in Tabriz metropolis: a future study approach | |
| TWM602260U (en) | Real estate valuation system | |
| Ghose et al. | The economic impact of user-generated content on the Internet: Combining text mining with demand estimation in the hotel industry | |
| Swietek et al. | Visual Capital: Evaluating building-level visual landscape quality at scale | |
| CN117541279A (en) | Shopping center industry recommendation index calculation method and system | |
| Zeydan et al. | A rule-based decision support approach for site selection of Automated Teller Machines (ATMs) | |
| Wang et al. | Optimizing leisure agriculture by analyzing spatial patterns and tourists’ perceptions: evidence from Wuhan, China | |
| Naude et al. | Explaining regional export performance in a developing country: The role of geography and relative factor endowments | |
| JP2022007878A (en) | Real estate transaction price prediction program | |
| Gaus et al. | Agglomeration or market access? The defining factors of firms' location choice | |
| Longhi et al. | Economic integration and manufacturing location in EU accession countries | |
| Otieno et al. | BUSINESS EXCELLENCE PRACTICES AND PERFORMANCE OF FAST MOVING CONSUMER GOODS MANUFACTURING FIRMS IN NAIROBI COUNTY, KENYA | |
| Riahi Samani et al. | Evaluating relocation behavior of establishments: Evidence for the short-term effects of COVID-19 | |
| Shan et al. | Research on management decision based on machine learning: Taking the decision of location selection of a pharmaceutical retail enterprise as an example |
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 |