CN117314501A - Card data processing method and device, electronic equipment and storage medium - Google Patents
Card data processing method and device, electronic equipment and storage medium Download PDFInfo
- Publication number
- CN117314501A CN117314501A CN202311299693.4A CN202311299693A CN117314501A CN 117314501 A CN117314501 A CN 117314501A CN 202311299693 A CN202311299693 A CN 202311299693A CN 117314501 A CN117314501 A CN 117314501A
- Authority
- CN
- China
- Prior art keywords
- card
- data
- total sales
- activity
- card activity
- 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
- 238000003672 processing method Methods 0.000 title claims abstract description 8
- 238000003860 storage Methods 0.000 title claims description 19
- 230000000694 effects Effects 0.000 claims abstract description 230
- 238000012545 processing Methods 0.000 claims abstract description 49
- 238000012549 training Methods 0.000 claims abstract description 10
- 238000000034 method Methods 0.000 claims description 33
- 238000013139 quantization Methods 0.000 claims description 10
- 239000000284 extract Substances 0.000 abstract description 5
- 238000012384 transportation and delivery Methods 0.000 abstract description 5
- 230000008569 process Effects 0.000 description 6
- 230000008901 benefit Effects 0.000 description 5
- 238000010586 diagram Methods 0.000 description 4
- 238000009826 distribution Methods 0.000 description 4
- 230000006870 function Effects 0.000 description 4
- 238000005457 optimization Methods 0.000 description 4
- 238000004458 analytical method Methods 0.000 description 3
- 238000012360 testing method Methods 0.000 description 3
- 238000005406 washing Methods 0.000 description 3
- 238000004422 calculation algorithm Methods 0.000 description 2
- 238000004364 calculation method Methods 0.000 description 2
- 238000013145 classification model Methods 0.000 description 2
- 238000004891 communication Methods 0.000 description 2
- 238000004590 computer program Methods 0.000 description 2
- 238000010276 construction Methods 0.000 description 2
- 238000011156 evaluation Methods 0.000 description 2
- 230000003993 interaction Effects 0.000 description 2
- 239000004973 liquid crystal related substance Substances 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 101001095088 Homo sapiens Melanoma antigen preferentially expressed in tumors Proteins 0.000 description 1
- 102100037020 Melanoma antigen preferentially expressed in tumors Human genes 0.000 description 1
- 238000013528 artificial neural network Methods 0.000 description 1
- 239000003086 colorant Substances 0.000 description 1
- 230000008094 contradictory effect Effects 0.000 description 1
- 238000013499 data model Methods 0.000 description 1
- 238000003066 decision tree Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000007477 logistic regression Methods 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 238000007726 management method Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000013507 mapping Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000010606 normalization Methods 0.000 description 1
- 238000013439 planning Methods 0.000 description 1
- 238000007637 random forest analysis Methods 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 238000012706 support-vector machine Methods 0.000 description 1
- 230000000007 visual effect Effects 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
- G06Q30/0202—Market predictions or forecasting for commercial activities
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR 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
- G06F16/2455—Query execution
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR 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
- G06F16/28—Databases characterised by their database models, e.g. relational or object models
- G06F16/284—Relational databases
- G06F16/285—Clustering or classification
-
- 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
- G06Q30/0207—Discounts or incentives, e.g. coupons or rebates
- G06Q30/0208—Trade or exchange of goods or services in exchange for incentives or rewards
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Accounting & Taxation (AREA)
- Finance (AREA)
- Development Economics (AREA)
- Strategic Management (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Entrepreneurship & Innovation (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Databases & Information Systems (AREA)
- Game Theory and Decision Science (AREA)
- General Business, Economics & Management (AREA)
- Marketing (AREA)
- Economics (AREA)
- General Engineering & Computer Science (AREA)
- Computational Linguistics (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention relates to the field of financial and scientific data processing, and discloses a card data processing method, which comprises the following steps: acquiring first data and total sales of a first card activity; calculating the association features between the total sales of the first card activity and each piece of information of the first data respectively to obtain a plurality of association features, and converging the plurality of association features to generate sequence features; training an initial prediction model by using the sequence characteristics, acquiring second data of a second card activity in the database, and optimizing the trained initial prediction model to generate a target prediction model; and receiving a request for predicting the to-be-developed card activity initiated by the terminal, analyzing the to-be-developed card activity by utilizing a target prediction model, obtaining the predicted total sales of the to-be-developed card activity, and feeding back the predicted total sales to the terminal. The invention is applied to application scenes such as financial and scientific data processing, extracts the association characteristics among different denomination cards in each card activity, and provides data and decision support with more reference value for card delivery users.
Description
Technical Field
The present invention relates to the field of financial and scientific data processing, and in particular, to a method and apparatus for processing coupon data, an electronic device, and a storage medium.
Background
In the field of financial science and technology, the delivery of coupons (e.g., coupons, points, etc.) to users is a common means of operation that facilitates consumer consumption.
However, in each of the coupon campaigns, small denomination coupons typically contribute to some small order sales, while large denomination coupons may result in larger sales, which results in a lack of comparability and correlation between different denomination coupon data, such that a scientific basis cannot be provided for the operational decisions of the coupon delivery users.
For example, after the promotion, the financial institution K can not obtain specific comparability and relativity of the fueling offer a and the car washing offer B in data, so that a scientific basis can not be provided for an operation decision of the financial institution K.
Therefore, how to improve the comparability and the relativity between the data of different denominations in each time of the card activity, more effectively extract the relativity characteristics between the cards of different denominations in each time of the card activity, and provide data and decision support with more reference value for the card delivery users is a problem to be solved urgently.
Disclosure of Invention
In view of the foregoing, there is a need for a method of processing coupon data that aims at improving the comparability and correlation between the coupon data of different denominations in each of the coupon campaigns, and more effectively extracting the correlation characteristics between the coupons of different denominations in each of the coupon campaigns.
The invention provides a method for processing card data, which comprises the following steps:
acquiring first data of at least one first card activity and total sales of the first card activity from a preset database, wherein the first data comprises guest unit price information, good score information, denomination information of each card, quantity information of released cards and quantity information of consumed cards of the first card activity;
calculating the association features between the total sales of the first card activity and each piece of information of the first data respectively to obtain a plurality of association features, and converging the plurality of association features to generate sequence features;
training a preset initial prediction model by utilizing the sequence characteristics, acquiring second data of at least one second card activity in the database, optimizing the trained initial prediction model, and generating a target prediction model, wherein the time node of the first card activity is earlier than that of the second card activity, and the second data comprises guest unit price information of the second card activity, denomination information of each card and quantity information of released cards;
And receiving a request for predicting the total sales of the to-be-developed card activity initiated by a terminal, analyzing the guest unit price information, the denomination information of each card and the quantity information of the released cards contained in the to-be-developed card activity by using the target prediction model, obtaining the predicted total sales of the to-be-developed card activity and feeding back the predicted total sales to the terminal.
Optionally, before the acquiring the first data of at least one first card activity and the total sales of the first card activity from the preset database, the method further includes:
after each time of the card activity is finished, the first data of each time of the card activity and the total sales of each time of the card activity are acquired to construct the database.
Optionally, the calculating the correlation feature between the total sales of the first card activity and each piece of information of the first data respectively to obtain a plurality of correlation features, merging the plurality of correlation features to generate a sequence feature includes:
calculating the rights and interests cost data of the total sales of the first card activity, and carrying out quantization processing on the first data;
generating a hash map according to the quantized first data and the rights cost data;
And extracting a plurality of associated features of each numerical value in the hash map, and merging the plurality of associated features to generate a sequence feature.
Optionally, the calculating the equity cost data of the total sales of the first card campaign includes:
multiplying the denomination of each card by the number of issued cards to obtain the rights and interests cost data.
Optionally, the generating a hash map according to the first data after quantization processing and the rights cost data includes:
and taking the rights and interests cost data as the abscissa of the hash map, the total sales as the ordinate of the hash map, and the quantized first data as the display content of the hash map.
Optionally, the taking the total sales as an ordinate of the hash map includes:
and carrying out digital scaling processing on the total sales of the first card activity, and taking the total sales after the digital scaling processing as the ordinate of the hash chart.
Optionally, the target prediction model includes a classification table for classifying total sales of all the card activities, and the feeding back the predicted total sales of the card activities to be developed to the terminal corresponding to the request includes:
Inquiring the classification table according to the predicted total sales of the card activity to be developed to obtain a classification grade corresponding to the predicted total sales of the card activity to be developed;
and feeding back the predicted total sales of the card activity to be developed and the corresponding classification level to the terminal corresponding to the request.
In order to solve the above-mentioned problems, the present invention also provides a coupon data processing apparatus, the apparatus comprising:
the system comprises an acquisition module, a storage module and a processing module, wherein the acquisition module is used for acquiring first data of at least one first card activity and total sales of the first card activity from a preset database, wherein the first data comprise guest unit price information, good score information, denomination information of each card, quantity information of released cards and quantity information of consumed cards of the first card activity;
the generation module is used for calculating the correlation characteristics between the total sales of the first card activity and each piece of information of the first data respectively to obtain a plurality of correlation characteristics, and merging the plurality of correlation characteristics to generate a sequence characteristic;
the optimizing module is used for training a preset initial prediction model by utilizing the sequence characteristics, acquiring second data of at least one second card activity in the database, optimizing the trained initial prediction model, and generating a target prediction model, wherein the time node of the first card activity is earlier than that of the second card activity, and the second data comprises guest unit price information of the second card activity, denomination information of each card and quantity information of released cards;
And the feedback module is used for receiving a request for predicting the total sales of the to-be-developed card activity initiated by the terminal, analyzing the guest unit price information, the denomination information of each card and the quantity information of the released cards contained in the to-be-developed card activity by utilizing the target prediction model, obtaining the predicted total sales of the to-be-developed card activity and feeding back the predicted total sales to the terminal.
In order to solve the above-mentioned problems, the present invention also provides an electronic apparatus including:
at least one processor; the method comprises the steps of,
a memory communicatively coupled to the at least one processor; wherein,
the memory stores a card data processing program executable by the at least one processor, and the first data processing program is executed by the at least one processor to enable the at least one processor to perform the card data processing method described above.
In order to solve the above-described problems, the present invention also provides a computer-readable storage medium having stored thereon a coupon data processing program, the first data processing program being executable by one or more processors to implement the coupon data processing method described above.
Compared with the prior art, the method and the device acquire the first data of at least one first card activity and the total sales of the first card activity from the preset database, wherein the first data comprises the guest unit price information, the good score information, the denomination information of each card, the quantity information of the released cards and the quantity information of the consumed cards of the first card activity; and calculating the correlation characteristics between the total sales of the first card activity and each piece of information of the first data respectively to obtain a plurality of correlation characteristics, and merging the plurality of correlation characteristics to generate a sequence characteristic.
The comparability and the relativity between the data of the cards with different denominations in the card activity can be improved, and the difference and the influencing factors between the cards with different denominations can be obtained. In the process of merging the plurality of associated feature generation sequence features, the associated features between the total sales and the first data, such as guest price, good score, and the like, are calculated. These correlation features reflect the relationships and interactions between different denomination coupons, enabling improved analysis of the effects and potential influencing factors of the coupon activity.
And training a preset initial prediction model by using the sequence characteristics, acquiring second data of at least one second card activity in the database, and optimizing the trained initial prediction model to generate a target prediction model. And predicting sales of the card activity to be developed by using the target prediction model, and feeding back a prediction result to the requesting terminal.
The target prediction model can be used for predicting the card activity to be developed, so that data and decision support with more reference value are provided for the releasing user to be developed, and the effect and the operation efficiency of the card activity are improved.
The invention is applied to application scenes such as financial and scientific data processing, extracts the association characteristics among different denomination cards in each card activity, provides data and decision support with more reference value for card delivery users, and improves the effect and operation efficiency of the card activity.
Drawings
FIG. 1 is a flowchart of a method for processing coupon data according to an embodiment of the present invention;
FIG. 2 is a schematic block diagram of a card data processing apparatus according to an embodiment of the present invention;
fig. 3 is a schematic structural diagram of an electronic device for implementing a method for processing coupon data according to an embodiment of the present invention;
the achievement of the objects, functional features and advantages of the present invention will be further described with reference to the accompanying drawings, in conjunction with the embodiments.
Detailed Description
The present invention will be described in further detail with reference to the drawings and examples, in order to make the objects, technical solutions and advantages of the present invention more apparent. It should be understood that the specific embodiments described herein are for purposes of illustration only and are not intended to limit the scope of the invention. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
It should be noted that the description of "first", "second", etc. in this disclosure is for descriptive purposes only and is not to be construed as indicating or implying a relative importance or implying an indication of the number of technical features being indicated. Thus, a feature defining "a first" or "a second" may explicitly or implicitly include at least one such feature. In addition, the technical solutions of the embodiments may be combined with each other, but it is necessary to base that the technical solutions can be realized by those skilled in the art, and when the technical solutions are contradictory or cannot be realized, the combination of the technical solutions should be considered to be absent and not within the scope of protection claimed in the present invention.
The invention is applied to application scenes such as financial and scientific data processing, extracts the association characteristics among cards with different denominations in each card activity, provides data and decision support with more reference value for the releasing user waiting for developing the card activity, and improves the effect and operation efficiency of the card activity.
Referring to fig. 1, a flow chart of a method for processing card data according to an embodiment of the invention is shown. The method is performed by an electronic device.
In this embodiment, the method for processing the coupon data includes:
S1, acquiring first data of at least one first card activity and total sales of the first card activity from a preset database, wherein the first data comprise guest unit price information, good score information, denomination information of each card, quantity information of released cards and quantity information of consumed cards of the first card activity.
In this embodiment, the database is a database storing past ticket activity data, and contains details of multiple ticket activities.
Typically the first data for each coupon activity includes the following information: guest price, rate of acceptance, denomination of each card, number of issued cards, and number of consumed cards.
By analyzing the data of the first coupon activity, relevant features are extracted and used for subsequent model construction and prediction.
In one embodiment, before the acquiring the first data of the at least one first card activity and the total sales of the first card activity from the preset database, the method further comprises:
after each time of the card activity is finished, the first data of each time of the card activity and the total sales of each time of the card activity are acquired to construct the database.
The invention will be illustrated by example H (without any limitation of the context):
and acquiring a refueling preferential activity A and a car washing preferential activity B of the financial institution K in the database as a first card coupon activity.
Coupon data for fueling offer a: total sales: 10 ten thousand yuan, guest unit price: 100 yuan, good score: 90%, denomination of each coupon: number of 50 yuan, released coupons: number of 1000 consumed coupons: 800 sheets.
Coupon data for car wash preference B: total sales: 8 ten thousand yuan, guest unit price: 120 yuan, good score: 85%, denomination of each coupon: number of 30 yuan, released coupons: number of 2000, consumed coupons: 600 sheets.
S2, calculating correlation features between the total sales of the first card activity and each piece of information of the first data respectively to obtain a plurality of correlation features, and merging the plurality of correlation features to generate sequence features.
Specifically, the step S2 includes:
calculating the rights and interests cost data of the total sales of the first card activity, and carrying out quantization processing on the first data;
generating a hash map according to the quantized first data and the rights cost data;
and extracting a plurality of associated features of each numerical value in the hash map, and merging the plurality of associated features to generate a sequence feature.
The associated feature refers to an index of a rate of return, a rate of coupon use, an activity participation rate, a customer growth rate, etc. generated between the total sales of the first coupon activity and the respective information of the first data.
The denomination of each card and the number of cards issued are first obtained from the data of the first card campaign. Then, the denomination of each card is multiplied by the number of issued cards to obtain the equity cost data. The equity cost data represents the cost required to place these coupons.
And quantifying the data such as the total sales of the first card activity, the price of the guest, the acceptance rate, the number of the consumed cards and the like. Quantization involves mapping these data to a specific range of values or normalization for subsequent calculation and analysis.
And taking the quantized first data and the rights cost data as inputs to generate a hash map. A hash map is a graph representing a data distribution in terms of points on a two-dimensional plane. The abscissa of the hash map represents equity cost data, and the ordinate represents total sales. The location of each point corresponds to a set of data for the first coupon activity, and the distribution of the data in the hash map can exhibit a correlation characteristic between the data.
And extracting each numerical value from the generated hash graph to obtain a plurality of associated features, and merging the plurality of associated features to generate a sequence feature. For example, image processing algorithms or machine learning methods may be used to capture data patterns and trends in the hash map, resulting in individual values.
Continuing with example H above, for example, for fueling offer A, the equity cost data may be calculated by multiplying the denomination of each card (50 yuan) by the number of issued cards (1000):
rights cost data=50/1000/50000.
For car wash benefit B, the equity cost data may be calculated by multiplying the denomination of each coupon (30 yuan) by the number of issued coupons (2000):
equity cost data = 30/2000 = 60000.
The equity cost data (abscissa) and the total sales (ordinate) are taken as coordinates of the hash map, and other coupon data (guest price, good score, etc.) of the fueling offer a and the car wash offer B are taken as display contents of the hash map.
And taking 10 ten thousand yuan as the total sales of the oiling preferential activity A and 8 ten thousand yuan as the ordinate of the hash chart as the total sales of the car washing preferential activity B.
In the hash, a point a (first color display, red) represents data of the fueling offer a, and a point B (second color display, blue) represents data of the car wash offer B. The correlation characteristics between equity cost data and total sales can be visually seen.
Generating a hash map can help financial institution K better optimize the coupon activity policy.
In step S2, in order to build an effective data model, the correlation features between the data of the first coupon activity are better understood, and a plurality of correlation features are obtained by acquiring each correlation feature between the total sales of the first coupon activity and other data of the first coupon activity except the total sales, and the plurality of correlation features are converged to generate a sequence feature, so that sales prediction accuracy of subsequent coupon activities is improved.
In one embodiment, before the calculating the correlation feature between the total sales of the first card activity and the respective information of the first data, a plurality of correlation features are obtained, and the plurality of correlation features are combined to generate the sequence feature, the method further includes:
and carrying out data quantization processing on the total sales amount, the unit price of customers, the good score of each card, the quantity of released cards and the quantity of consumed cards of the first card activity.
In one embodiment, the data quantization process includes: and converting the data of the non-numeric type in the first data of the first card activity into numeric type.
The data quantization processing process comprises the following steps:
1. the total sales are converted into numeric data, possibly the amounts into corresponding numeric values.
2. The guest price is converted into numerical data, and it is also possible to convert the amount into a corresponding numerical value.
3. The good score is converted to a percentage or fraction, for example 90% to 0.9.
4. The denomination is converted into numeric data, for example 50-ary into 50.
5. The number of issued tickets is converted into integer data, for example 1000 to 1000.
6. The number of consumed cards is converted into integer type data, for example, 800 sheets are converted into 800.
Through these data quantization processes, non-numeric data is converted into numeric data for subsequent calculation and analysis. The processed data may be used to calculate the equity cost data for the first coupon activity, generate a hash map, and extract a plurality of associated features that are merged to generate a sequence feature for use in subsequent model construction and prediction.
In one embodiment, the calculating the equity cost data for the total sales of the first coupon activity comprises:
multiplying the denomination of each card by the number of issued cards to obtain the rights and interests cost data.
The benefit cost data serves to help gauge the relationship between the cost and benefit of the coupon activity. By calculating the equity cost data, the actual cost required to deliver these coupons, i.e., the sum of the denominations of the coupons multiplied by the number of impressions, can be known. This is very important to businesses, and can help them decide on the investment and return of the coupon activity.
In general, the equity cost data is one of the important indexes in the management and decision of the card activity, can help enterprises reasonably control the cost, forecast profits, evaluate the profits, and finally optimize the card activity strategy, and promote the sales and profitability of the enterprises.
In one embodiment, the generating a hash map according to the quantized first data and the rights cost data includes:
and taking the rights and interests cost data as the abscissa of the hash map, the total sales as the ordinate of the hash map, and the quantized first data as the display content of the hash map.
In one embodiment, the taking the total sales as the ordinate of the hash map includes:
and carrying out digital scaling processing on the total sales of the first card activity, and taking the total sales after the digital scaling processing as the ordinate of the hash chart.
The equity cost data and the total sales are corresponding to the abscissa and the ordinate of the hash chart, the equity cost data and the total sales of the first card activity are required to be guaranteed to have the same unit and magnitude, and the association relationship between the equity cost data and the total sales can be better displayed by performing digital scaling treatment (for example, the total sales are 10 ten thousand yuan, 100 bits can be reduced and 100K is used for representing).
A hash map is a graph representing a data distribution in terms of points on a two-dimensional plane. The position of each point is determined by the values of the abscissa and the ordinate. By taking the equity cost data as the abscissa and the total sales as the ordinate, and showing at each point other coupon data of the first coupon activity than the total sales, the association and distribution between these data can be visually seen on the hash map.
Other coupon data is displayed at each point of the hash map, and different indicia, colors, or sizes may be used to distinguish the different data, making the image easier to understand and interpret.
In step S2, the equity cost data is taken as the abscissa of the hash map, the total sales are taken as the ordinate, and the other ticket data of the first ticket activity than the total sales are shown on the hash map. The generated hash map can intuitively know the association characteristics between the data, so that the sales condition of the card activity can be better analyzed and predicted.
S3, training a preset initial prediction model by using the sequence characteristics, acquiring second data of at least one second card activity in the database, optimizing the trained initial prediction model, and generating a target prediction model, wherein the time node of the first card activity is earlier than that of the second card activity, and the second data comprises guest unit price information of the second card activity, denomination information of each card and quantity information of released cards.
In this embodiment, the initial predictive model is trained using the sequence feature of the first coupon activity as a training set and the second data of the second coupon activity as a test set;
the initial multi-classification model includes, but is not limited to, logistic regression, decision trees, support vector machines, K-nearest neighbor algorithms, random forests, neural networks, and the like.
After the initial predictive model is obtained, the initial predictive model is evaluated using the test set data (second data for the second coupon activity).
The predictive performance of the model is evaluated by comparing the initial predictive model to generate an error value between the predicted total sales of the second coupon activity and the actual total sales of the actual second coupon activity. The evaluation index includes root mean square error (Root Mean Squared Error, RMSE), mean absolute percentage error (Mean Absolute Percentage Error, MAPE), and the like.
And optimizing the initial prediction model according to the evaluation result, wherein the optimization comprises the steps of adjusting the super parameters of the model and selecting different characteristic combinations so as to improve the prediction accuracy and generalization capability of the initial prediction model, and finally obtaining the target prediction model through repeated optimization training process.
In other embodiments, the target prediction model is used to categorize the total sales of all the card activities in the database into different levels, resulting in a classification table that categorizes the total sales of all the card activities, e.g., three levels of high, medium, and low, and possibly further levels (e.g., 10 levels). Each level corresponds to a range of total sales. The goal prediction model may categorize different denominations of the coupon activity, e.g., into high, medium, and low-level sales categories. That is, the goal prediction model may rank the total sales of the non-occurring coupon activity in addition to predicting the total sales of the non-occurring coupon activity.
The time node of the first ticket activity is earlier than the time node of the second ticket activity. Meaning that in constructing and optimizing the multi-classification model, it is ensured that the data is arranged in chronological order, ensuring that the data of the second coupon activity occurs after the first coupon activity.
In one embodiment, the obtaining the first data of the at least one second coupon activity of the database optimizes the initial predictive model to generate a target predictive model, including:
testing the initial predictive model with second data of the second coupon activity to generate a predicted total sales of the second coupon activity;
and acquiring the actual total sales of the second card activity, and optimizing the initial prediction model according to the error value between the actual total sales and the predicted total sales to generate the target prediction model.
Continuing with example H above, an initial predictive model is constructed using, for example, features in the coupon data of fueling offer A and car wash offer B, such as total sales, guest price, acceptance rate, denomination of each coupon, number of issued coupons, etc., as input features.
Second data of at least one second coupon activity is obtained from the database. These data include the price of the customer for the second ticket campaign, the denomination of each ticket, and the number of tickets issued.
For example, the second data of the second coupon activity C: guest price: 110 yuan, denomination per coupon: number of 40 yuan, released coupons: 1500 sheets.
The initial predictive model is tested using the second data for the second coupon activity C to generate a predicted total sales for the second coupon activity C. The predicted total sales are the predicted total sales of the second card activity C based on characteristics such as the unit price of the customer, the denomination of each card, and the number of cards issued.
Assuming that the predicted total sales of the candidate model for the second coupon activity C is 9.5 ten thousand yuan, and the actual total sales of the second coupon activity is 9 ten thousand yuan.
The actual total sales and the predicted total sales of the second ticket activities C are calculated, resulting in an error value between them. In this example, the error value is 9-9.5 ten thousand = -0.5 ten thousand.
Based on this error value, the initial predictive model is optimized to more accurately predict the total sales of the second coupon activity. Optimization includes parameter adjustment, feature selection, model improvement, etc., to obtain a more accurate target prediction model.
S4, receiving a request for predicting the total sales of the to-be-developed card activity initiated by the terminal, analyzing the guest unit price information, the denomination information of each card and the quantity information of the released cards contained in the to-be-developed card activity by using the target prediction model, obtaining the predicted total sales of the to-be-developed card activity and feeding back the predicted total sales to the terminal.
In this embodiment, after the target prediction model is obtained, the target prediction model is put into actual production for use, and the total sales of the card to be developed is predicted at the current moment or in the absence of the card to be developed.
Continuing with example H above, financial institution K is now planning to push out the coupon activity D to be developed, preset data as follows: presetting a guest unit price: 110 yuan, presetting the denomination of each card: 40 yuan, presetting the quantity of the released cards: 1800 sheets.
And processing preset data of the card activity D to be developed by using the constructed target prediction model to obtain a predicted total sales amount, and feeding back a prediction result to a terminal corresponding to the financial institution K.
And processing the preset guest price of the card activity D to be developed, the preset denomination of each card and the preset quantity of the released cards as input features through a target prediction model to obtain the predicted total sales.
Assuming that the target prediction model predicts that the predicted total sales of the to-be-developed coupon activity D is 9.8 ten thousand yuan, and feeding back the predicted total sales of 9.8 ten thousand yuan to the terminal corresponding to the financial institution K. The financial institution K can now evaluate the potential sales of the card activity D to be developed and whether it is necessary to adjust the customer price, denomination or number of impressions, etc. according to this prediction.
In step S4, the preset data of the card activity to be developed is processed by using the constructed target prediction model, so as to obtain a predicted total sales amount, and the prediction result is fed back to the terminal corresponding to the financial institution K. This prediction may help financial institution K to better plan and optimize the policies for the coupon activity to be developed.
In other embodiments, the objective prediction model includes a classification table for classifying total sales of all the card activities, and the feeding back the predicted total sales of the card activities to be developed to the terminal corresponding to the request includes:
inquiring the predicted total sales of the card activity to be developed into the classification table to obtain a classification grade corresponding to the predicted total sales of the card activity to be developed;
and feeding back the predicted total sales of the card activity to be developed and the corresponding classification level to the terminal corresponding to the request.
In order to accurately classify the predicted total sales of the card activities, after the target prediction model is obtained, the target prediction model is used to classify the total sales of all the card activities in the database into different grades, so as to obtain a classification table for classifying the total sales of all the card activities, for example, classifying the total sales into three grades of high, medium and low, and further classifying the total sales into more grades (for example, 10 grades). Each level corresponds to a range of total sales.
And when a request for generating the predicted total sales of the card activity to be developed is received, processing the predicted total sales of the card activity to be developed by using the target prediction model to obtain the predicted total sales.
And inquiring the predicted total sales into a classification table to find the corresponding classification level. For example, if the total sales are predicted to be 9.8 ten thousand yuan, the classification table is queried to see that it corresponds to medium level.
And feeding back the predicted total sales and the corresponding classification level to the terminal corresponding to the request. The financial institution K can learn the predicted total sales of the card activity to be developed and learn the classification level corresponding to the predicted total sales, thereby better evaluating the effect and potential of the activity.
Fig. 2 is a schematic block diagram of a card data processing device according to an embodiment of the present invention.
The first data processing apparatus 100 according to the present invention may be installed in an electronic device. Depending on the implemented functions, the first data processing apparatus 100 may include an acquisition module 110, a generation module 120, an optimization module 130, and a feedback module 140. The module of the invention, which may also be referred to as a unit, refers to a series of computer program segments, which are stored in the memory of the electronic device, capable of being executed by the processor of the electronic device and of performing a fixed function.
In the present embodiment, the functions concerning the respective modules/units are as follows:
the obtaining module 110 is configured to obtain, from a preset database, first data of at least one first coupon activity and total sales of the first coupon activity, where the first data includes guest unit price information, good score information, denomination information of each coupon, number of issued coupons, and number of consumed coupons of the first coupon activity.
And the generating module 120 is configured to calculate correlation features between the total sales of the first coupon activity and each piece of information of the first data, obtain a plurality of correlation features, and combine the plurality of correlation features to generate a sequence feature.
And the optimizing module 130 is configured to train a preset initial prediction model by using the sequence features, acquire second data of at least one second card activity in the database, optimize the trained initial prediction model, and generate a target prediction model, where a time node of the first card activity is earlier than a time node of the second card activity, and the second data includes guest unit price information of the second card activity, denomination information of each card, and number information of issued cards.
And the feedback module 140 is configured to receive a request initiated by a terminal to predict the total sales of the to-be-developed card activity, analyze, by using the target prediction model, the guest unit price information, the denomination information of each card and the number information of the released cards, so as to obtain the predicted total sales of the to-be-developed card activity, and feed back the predicted total sales to the terminal.
In one embodiment, before the acquiring the first data of the at least one first card activity and the total sales of the first card activity from the preset database, the method further comprises:
after each time of the card activity is finished, the first data of each time of the card activity and the total sales of each time of the card activity are acquired to construct the database.
In one embodiment, the calculating the correlation feature between the total sales of the first card activity and each piece of information of the first data respectively to obtain a plurality of correlation features, merging the plurality of correlation features to generate a sequence feature includes:
calculating the rights and interests cost data of the total sales of the first card activity, and carrying out quantization processing on the first data;
generating a hash map according to the quantized first data and the rights cost data;
And extracting a plurality of associated features of each numerical value in the hash map, and merging the plurality of associated features to generate a sequence feature.
In one embodiment, the calculating the equity cost data for the total sales of the first coupon activity comprises:
multiplying the denomination of each card by the number of issued cards to obtain the rights and interests cost data.
In one embodiment, the generating a hash map according to the quantized first data and the rights cost data includes:
and taking the rights and interests cost data as the abscissa of the hash map, the total sales as the ordinate of the hash map, and the quantized first data as the display content of the hash map.
In one embodiment, the taking the total sales as the ordinate of the hash map includes:
and carrying out digital scaling processing on the total sales of the first card activity, and taking the total sales after the digital scaling processing as the ordinate of the hash chart.
In one embodiment, the target prediction model includes a classification table for classifying total sales of all the card activities, and the feeding back the predicted total sales of the card activities to be developed to the terminal corresponding to the request includes:
Inquiring the classification table according to the predicted total sales of the card activity to be developed to obtain a classification grade corresponding to the predicted total sales of the card activity to be developed;
and feeding back the predicted total sales of the card activity to be developed and the corresponding classification level to the terminal corresponding to the request.
Fig. 3 is a schematic structural diagram of an electronic device for implementing a method for processing data of a card according to an embodiment of the present invention.
In the present embodiment, the electronic device 1 includes, but is not limited to, a memory 11, a processor 12, and a network interface 13, which are communicably connected to each other via a system bus, the memory 11 storing therein a card data processing program 10, the first data processing program 10 being executable by the processor 12. Fig. 3 shows only the electronic device 1 with the components 11-13 and the coupon data processing program 10, it will be understood by those skilled in the art that the structure shown in fig. 3 is not limiting of the electronic device 1 and may include fewer or more components than shown, or may combine certain components, or a different arrangement of components.
Wherein the storage 11 comprises a memory and at least one type of readable storage medium. The memory provides a buffer for the operation of the electronic device 1; the readable storage medium may be a non-volatile storage medium such as flash memory, hard disk, multimedia card, card memory (e.g., SD or DX memory, etc.), random Access Memory (RAM), static Random Access Memory (SRAM), read Only Memory (ROM), electrically Erasable Programmable Read Only Memory (EEPROM), programmable Read Only Memory (PROM), magnetic memory, magnetic disk, optical disk, etc. In some embodiments, the readable storage medium may be an internal storage unit of the electronic device 1; in other embodiments, the nonvolatile storage medium may also be an external storage device of the electronic device 1, such as a plug-in hard disk, a Smart Media Card (SMC), a Secure Digital (SD) Card, a Flash memory Card (Flash Card) or the like, which are provided on the electronic device 1. In this embodiment, the readable storage medium of the memory 11 is generally used to store an operating system and various types of application software installed in the electronic device 1, for example, to store codes of the card data processing program 10 in one embodiment of the present invention, and the like. Further, the memory 11 may be used to temporarily store various types of data that have been output or are to be output.
Processor 12 may be a central processing unit (Central Processing Unit, CPU), controller, microcontroller, microprocessor, or other data processing chip in some embodiments. The processor 12 is typically used to control the overall operation of the electronic device 1, such as performing control and processing related to data interaction or communication with other devices, etc. In this embodiment, the processor 12 is configured to execute the program code or process data stored in the memory 11, for example, execute the card data processing program 10.
The network interface 13 may comprise a wireless network interface or a wired network interface, the network interface 13 being used for establishing a communication connection between the electronic device 1 and a terminal (not shown).
Optionally, the electronic device 1 may further comprise a user interface, which may comprise a Display (Display), an input unit such as a Keyboard (Keyboard), and optionally a standard wired interface, a wireless interface. Alternatively, in some embodiments, the display may be an LED display, a liquid crystal display, a touch-sensitive liquid crystal display, an OLED (Organic Light-Emitting Diode) touch, or the like. The display may also be referred to as a display screen or display unit, as appropriate, for displaying information processed in the electronic device 1 and for displaying a visual user interface.
It should be understood that the embodiments described are for illustrative purposes only and are not limited to this configuration in the scope of the patent application.
The card data processing program 10 stored in the memory 11 of the electronic device 1 is a combination of instructions that, when executed in the processor 12, can implement:
acquiring first data of at least one first card activity and total sales of the first card activity from a preset database, wherein the first data comprises guest unit price information, good score information, denomination information of each card, quantity information of released cards and quantity information of consumed cards of the first card activity;
calculating the association features between the total sales of the first card activity and each piece of information of the first data respectively to obtain a plurality of association features, and converging the plurality of association features to generate sequence features;
training a preset initial prediction model by utilizing the sequence characteristics, acquiring second data of at least one second card activity in the database, optimizing the trained initial prediction model, and generating a target prediction model, wherein the time node of the first card activity is earlier than that of the second card activity, and the second data comprises guest unit price information of the second card activity, denomination information of each card and quantity information of released cards;
And receiving a request for predicting the total sales of the to-be-developed card activity initiated by a terminal, analyzing the guest unit price information, the denomination information of each card and the quantity information of the released cards contained in the to-be-developed card activity by using the target prediction model, obtaining the predicted total sales of the to-be-developed card activity and feeding back the predicted total sales to the terminal.
In particular, the specific implementation method of the above-mentioned card data processing program 10 by the processor 12 may refer to the description of the relevant steps in the corresponding embodiment of fig. 1, which is not repeated herein.
Further, the modules/units integrated in the electronic device 1 may be stored in a computer readable storage medium if implemented in the form of software functional units and sold or used as separate products. The computer readable medium may be nonvolatile or nonvolatile. The computer readable medium may include: any entity or device capable of carrying the computer program code, a recording medium, a U disk, a removable hard disk, a magnetic disk, an optical disk, a computer Memory, a Read-Only Memory (ROM).
The computer readable storage medium stores the card data processing program 10, where the first data processing program 10 may be executed by one or more processors, and the specific embodiment of the computer readable storage medium is substantially the same as the embodiments of the card data processing method described above, and will not be described herein.
In the several embodiments provided in the present invention, it should be understood that the disclosed apparatus, device and method may be implemented in other manners. For example, the above-described apparatus embodiments are merely illustrative, and for example, the division of the modules is merely a logical function division, and there may be other manners of division when actually implemented.
The modules described as separate components may or may not be physically separate, and components shown as modules may or may not be physical units, may be located in one place, or may be distributed over multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment.
In addition, each functional module in the embodiments of the present invention 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 integrated units can be realized in a form of hardware or a form of hardware and a form of software functional modules.
It will be evident to those skilled in the art that the invention is not limited to the details of the foregoing illustrative embodiments, and that the present invention may be embodied in other specific forms without departing from the spirit or essential characteristics thereof.
The present embodiments are, therefore, to be considered in all respects as illustrative and not restrictive, the scope of the invention being indicated by the appended claims rather than by the foregoing description, and all changes which come within the meaning and range of equivalency of the claims are therefore intended to be embraced therein. Any reference signs in the claims shall not be construed as limiting the claim concerned.
Furthermore, it is evident that the word "comprising" does not exclude other elements or steps, and that the singular does not exclude a plurality. A plurality of units or means recited in the system claims can also be implemented by means of software or hardware by means of one unit or means. The terms second, etc. are used to denote a name, but not any particular order.
Finally, it should be noted that the above-mentioned embodiments are merely for illustrating the technical solution of the present invention and not for limiting the same, and although the present invention has been described in detail with reference to the preferred embodiments, it should be understood by those skilled in the art that modifications and equivalents may be made to the technical solution of the present invention without departing from the spirit and scope of the technical solution of the present invention.
Claims (10)
1. A method of processing coupon data, the method comprising:
Acquiring first data of at least one first card activity and total sales of the first card activity from a preset database, wherein the first data comprises guest unit price information, good score information, denomination information of each card, quantity information of released cards and quantity information of consumed cards of the first card activity;
calculating the association features between the total sales of the first card activity and each piece of information of the first data respectively to obtain a plurality of association features, and converging the plurality of association features to generate sequence features;
training a preset initial prediction model by utilizing the sequence characteristics, acquiring second data of at least one second card activity in the database, optimizing the trained initial prediction model, and generating a target prediction model, wherein the time node of the first card activity is earlier than that of the second card activity, and the second data comprises guest unit price information of the second card activity, denomination information of each card and quantity information of released cards;
and receiving a request for predicting the total sales of the to-be-developed card activity initiated by a terminal, analyzing the guest unit price information, the denomination information of each card and the quantity information of the released cards contained in the to-be-developed card activity by using the target prediction model, obtaining the predicted total sales of the to-be-developed card activity and feeding back the predicted total sales to the terminal.
2. The method of claim 1, wherein prior to said retrieving from a predetermined database first data for at least one first coupon activity and a total sales of said first coupon activity, said method further comprises:
after each time of the card activity is finished, the first data of each time of the card activity and the total sales of each time of the card activity are acquired to construct the database.
3. The method for processing card data according to claim 1, wherein said calculating the correlation characteristics between the total sales of the first card activity and the respective information of the first data, respectively, to obtain a plurality of correlation characteristics, and merging the plurality of correlation characteristics to generate a sequence characteristic, comprises:
calculating the rights and interests cost data of the total sales of the first card activity, and carrying out quantization processing on the first data;
generating a hash map according to the quantized first data and the rights cost data;
and extracting a plurality of associated features of each numerical value in the hash map, and merging the plurality of associated features to generate a sequence feature.
4. A method of processing ticket data as claimed in claim 3 wherein said calculating equity cost data for the total sales of said first ticket activity comprises:
Multiplying the denomination of each card by the number of issued cards to obtain the rights and interests cost data.
5. The method of claim 3, wherein the generating a hash map from the quantized first data and the equity cost data comprises:
and taking the rights and interests cost data as the abscissa of the hash map, the total sales as the ordinate of the hash map, and the quantized first data as the display content of the hash map.
6. The method of claim 5, wherein said assigning the total sales as the ordinate of the hash map comprises:
and carrying out digital scaling processing on the total sales of the first card activity, and taking the total sales after the digital scaling processing as the ordinate of the hash chart.
7. The method for processing the data of the card according to claim 1, wherein the target prediction model includes a classification table for classifying the total sales of all the card activities, and the feeding back the predicted total sales of the card activities to be developed to the terminal corresponding to the request includes:
Inquiring the classification table according to the predicted total sales of the card activity to be developed to obtain a classification grade corresponding to the predicted total sales of the card activity to be developed;
and feeding back the predicted total sales of the card activity to be developed and the corresponding classification level to the terminal corresponding to the request.
8. A coupon data processing apparatus, the apparatus comprising:
the system comprises an acquisition module, a storage module and a processing module, wherein the acquisition module is used for acquiring first data of at least one first card activity and total sales of the first card activity from a preset database, wherein the first data comprise guest unit price information, good score information, denomination information of each card, quantity information of released cards and quantity information of consumed cards of the first card activity;
the generation module is used for calculating the correlation characteristics between the total sales of the first card activity and each piece of information of the first data respectively to obtain a plurality of correlation characteristics, and merging the plurality of correlation characteristics to generate a sequence characteristic;
the optimizing module is used for training a preset initial prediction model by utilizing the sequence characteristics, acquiring second data of at least one second card activity in the database, optimizing the trained initial prediction model, and generating a target prediction model, wherein the time node of the first card activity is earlier than that of the second card activity, and the second data comprises guest unit price information of the second card activity, denomination information of each card and quantity information of released cards;
And the feedback module is used for receiving a request for predicting the total sales of the to-be-developed card activity initiated by the terminal, analyzing the guest unit price information, the denomination information of each card and the quantity information of the released cards contained in the to-be-developed card activity by utilizing the target prediction model, obtaining the predicted total sales of the to-be-developed card activity and feeding back the predicted total sales to the terminal.
9. An electronic device, the electronic device comprising:
at least one processor; the method comprises the steps of,
a memory communicatively coupled to the at least one processor; wherein,
the memory stores a card data processing program executable by the at least one processor, the first data processing program being executed by the at least one processor to enable the at least one processor to perform the card data processing method of any one of claims 1 to 7.
10. A computer-readable storage medium, having stored thereon a coupon data processing program, the first data processing program being executable by one or more processors to implement the coupon data processing method of any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311299693.4A CN117314501A (en) | 2023-10-08 | 2023-10-08 | Card data processing method and device, electronic equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311299693.4A CN117314501A (en) | 2023-10-08 | 2023-10-08 | Card data processing method and device, electronic equipment and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117314501A true CN117314501A (en) | 2023-12-29 |
Family
ID=89236868
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311299693.4A Pending CN117314501A (en) | 2023-10-08 | 2023-10-08 | Card data processing method and device, electronic equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117314501A (en) |
-
2023
- 2023-10-08 CN CN202311299693.4A patent/CN117314501A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110837931B (en) | Customer churn prediction method, device and storage medium | |
| CN111881158B (en) | Processing method, device, computer system and readable storage medium for managing report data | |
| CN114048436A (en) | Construction method and construction device for forecasting enterprise financial data model | |
| KR102330423B1 (en) | Online default forecasting system using image recognition deep learning algorithm | |
| CN114663198A (en) | Product recommendation method, device and equipment based on user portrait and storage medium | |
| CN110751285A (en) | Training method and system and prediction method and system of neural network model | |
| US20220351004A1 (en) | Industry specific machine learning applications | |
| CN110766481A (en) | Client data processing method and device, electronic equipment and computer readable medium | |
| CN115423578B (en) | Bid bidding method and system based on micro-service containerized cloud platform | |
| CN115081025A (en) | Sensitive data management method and device based on digital middlebox and electronic equipment | |
| CN110910241A (en) | Cash flow evaluation method, apparatus, server device and storage medium | |
| CN116468547A (en) | Credit card resource allocation method and system based on data mining | |
| CN114282951B (en) | Network retail prediction method, device and medium | |
| CN115809930A (en) | Anti-fraud analysis method, device, equipment and medium based on data fusion matching | |
| CN115049137A (en) | Prediction method and device of transaction yield, storage medium and electronic equipment | |
| CN117314501A (en) | Card data processing method and device, electronic equipment and storage medium | |
| CN114548620A (en) | Logistics punctual insurance service recommendation method and device, computer equipment and storage medium | |
| CN113689020A (en) | Service information prediction method, device, computer equipment and storage medium | |
| US20220308934A1 (en) | Prediction system, prediction method, and program | |
| CN116308158B (en) | National asset supervision and management system | |
| CN118071482A (en) | Method for constructing retail credit risk prediction model and consumer credit business Scorebetad model | |
| CN117788133A (en) | Method for constructing retail credit risk prediction model and retail credit score model | |
| CN117994017A (en) | Method for constructing retail credit risk prediction model and online credit service Scoredelta model | |
| KR20210112974A (en) | System and method for creating brand index using concentration ratio and computer program for the same | |
| CN117994016A (en) | Method for constructing retail credit risk prediction model and consumer credit business Scorebeta model |
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 |