CN109063944A - City banking index analysis method and device based on big data analysis technology - Google Patents
City banking index analysis method and device based on big data analysis technology Download PDFInfo
- Publication number
- CN109063944A CN109063944A CN201810563023.1A CN201810563023A CN109063944A CN 109063944 A CN109063944 A CN 109063944A CN 201810563023 A CN201810563023 A CN 201810563023A CN 109063944 A CN109063944 A CN 109063944A
- Authority
- CN
- China
- Prior art keywords
- index analysis
- banking
- analysis model
- data
- banking index
- 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
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
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
-
- 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
- G06Q40/00—Finance; Insurance; Tax strategies; Processing of corporate or income taxes
Landscapes
- Business, Economics & Management (AREA)
- Engineering & Computer Science (AREA)
- Human Resources & Organizations (AREA)
- Strategic Management (AREA)
- Development Economics (AREA)
- Economics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Entrepreneurship & Innovation (AREA)
- Marketing (AREA)
- Educational Administration (AREA)
- General Business, Economics & Management (AREA)
- Physics & Mathematics (AREA)
- Tourism & Hospitality (AREA)
- Quality & Reliability (AREA)
- Operations Research (AREA)
- Game Theory and Decision Science (AREA)
- Accounting & Taxation (AREA)
- Finance (AREA)
- Technology Law (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a kind of city banking index analysis method and device based on big data analysis technology, which comprises obtain finance data；The finance data is inputted into preset banking index analysis model, so that banking index analysis model analyzes the finance data, and obtains city banking index analysis result.The embodiment of the present invention, which has the advantages that, analyzes the finance data according to the banking index analysis model constructed in advance, and obtain city banking index analysis result, the accurate analysis result of city banking index can be obtained, so as to the analysis by index as a result, promoting the development of each city financial circles.
Description
Technical field
The present invention relates to big data field, in particular to a kind of city banking index analysis based on big data analysis technology
Method and device.
Background technique
In the conventional technology, industry decision is achieved generally by business driving method.Currently, in order to improve gold
Raycom skill developmental research is professional, and the industry decision in financial technology field is turned from business driving method to data-driven version
Become.
For the requirement for meeting data-driven version, need to calculate city banking index.City banking index refers to as level-one
Mark, divides into four big two-level index, is financial technology Industry Performance, financial technology mechanism strength, financial technology market scale respectively
With financial technology ecological environment.The flexible strategy of two-level index subdivide three-level index.It altogether include ten or more three-level indexs.Using
Nondimensionalization method calculates the index of individual index, then is weighted, and calculates the index of two-level index, and last weighted calculation, which goes out, always to be referred to
Number.
But the financial situation in each city is different, and wherein financial technology mechanism strength is also different, and the finger of city finance
It is marked on when being calculated, has plenty of positive index, have plenty of negative sense (reverse) index.Positive indicator is higher, and index is lower；
Negative sense index value is higher, and index is bigger.For example GDP total amount is positive index, total amount is bigger, and index is higher.But PM2.5 concentration
It is negative sense index, value is higher, and index is lower.Therefore, how accurate analysis is carried out to city banking index and is related to city
The development of finance.
Summary of the invention
In view of this, the embodiment of the present invention is at least one technical problem for solving to propose in background technique, provide at least
A kind of beneficial selection.
To achieve the goals above, the embodiment of the invention provides a kind of city finance based on big data analysis technology to refer to
Number analysis method, comprising:
Obtain finance data；
The finance data is inputted into preset banking index analysis model, so that banking index analysis model is to the gold
Melt data to be analyzed, and obtains city banking index analysis result.
Preferably, the finance data is inputted preset banking index analysis model, to obtain city banking index
Before analysis result, which comprises
The banking index analysis model is constructed, so that banking index analysis model divides the finance data
Analysis.
Preferably, constructing the banking index analysis model and including:
According to the training data and at least one preset algorithm in the finance data, at least one banking index point is constructed
Analyse model；
According to the test data in the finance data, each banking index analysis model is assessed, is tied according to assessment
Fruit determines the banking index analysis model.
Preferably, constructing at least one according to training data and at least one preset algorithm in the finance data
Banking index analysis model:
Adjust the parameter of the banking index analysis model；
Determine the effect and performance of the corresponding banking index analysis model output of the parameter；
Select effect and the satisfactory banking index analysis model of performance.
Preferably, assessing each banking index analysis model, root according to the test data in the finance data
According to assessment result, determine that the banking index analysis model includes:
Cross validation is carried out to the banking index analysis model；
Calculate the time complexity and space complexity of each banking index analysis model；
It selects time complexity and space complexity is more than the banking index analysis model of preset threshold.
Preferably, acquisition finance data includes:
Using web crawlers technology, the finance data on internet is obtained；Alternatively,
Receive the finance data of typing.
Preferably, after obtaining finance data, the method also includes:
The finance data is pre-processed.
Preferably, to the finance data carry out pretreatment include:
The finance data is cleaned, then the finance data after storage cleaning.
The embodiment of the present invention also provides a kind of city banking index analytical equipment based on big data analysis technology, institute
Stating device includes:
Module is obtained, is configured to obtain finance data；
Analysis module is configured to the finance data inputting preset banking index analysis model, so that banking index
Analysis model analyzes the finance data, and obtains city banking index analysis result.
Preferably, described device further include:
Module is constructed, is configured to construct the banking index analysis model, so that banking index analysis model is to described
Finance data is analyzed.
Preferably, the building module concrete configuration are as follows:
According to the training data and at least one preset algorithm in the finance data, at least one banking index point is constructed
Analyse model；
According to the test data in the finance data, each banking index analysis model is assessed, is tied according to assessment
Fruit determines the banking index analysis model.
Preferably, the building module concrete configuration are as follows:
Adjust the parameter of the banking index analysis model；
Determine the effect and performance of the corresponding banking index analysis model output of the parameter；
Select effect and the satisfactory banking index analysis model of performance.
Preferably, the building module concrete configuration are as follows:
Cross validation is carried out to the banking index analysis model；
Calculate the time complexity and space complexity of each banking index analysis model；
It selects time complexity and space complexity is more than the banking index analysis model of preset threshold.
The embodiment of the present invention has the advantages that according to the banking index analysis model constructed in advance to the finance
Data are analyzed, and obtain city banking index analysis as a result, can obtain city banking index it is accurate analyze as a result, from
And it can be by the analysis of index as a result, promoting the development of each city financial circles.
Detailed description of the invention
Fig. 1 is the process of the embodiment one of the city banking index analysis method of the invention based on big data analysis technology
Figure；
Fig. 2 is the process of the embodiment two of the city banking index analysis method of the invention based on big data analysis technology
Figure；
Fig. 3 is the embodiment one of the city banking index analysis method device of the invention based on big data analysis technology
Schematic diagram；
Fig. 4 is the embodiment two of the city banking index analysis method device of the invention based on big data analysis technology
Schematic diagram.
Specific embodiment
With reference to the accompanying drawings and examples, specific embodiments of the present invention will be described in further detail.Implement below
Example is not intended to limit the scope of the invention for illustrating the present invention.
Embodiment one
Fig. 1 is the process of the embodiment one of the city banking index analysis method of the invention based on big data analysis technology
Figure, as shown in Figure 1, the city banking index analysis method based on big data analysis technology of the present embodiment, can specifically include
Following steps:
S101 obtains finance data；
For the acquisition of finance data, there are a variety of data sources, for example, can by Internet data grabber and/or
The modes such as artificial data typing obtain finance data.
By technological means such as internet data crawler technologies, the financial number of default website is grabbed within a preset time interval
According to etc. information.
Wherein, finance data may include at least one of following: business information of enterprise, city financial policy information, city
The information such as financial public feelings information, the consulting of city money article and city finance.
In the specific implementation, crawler technology can be used to be acquired raw financial data in preset data source website.
Meanwhile on the basis of obtaining finance data, user friendly principle can also be followed, Portable Batch System function may be implemented
With log integrated management function, so that it is guaranteed that can realize that more complete horizontal extendable functions, error tracking function and threshold value are accused
Alert mechanism function etc..
In addition, the embodiment of the present invention also provides data inputting interface, and when needing to carry out artificial amended record to finance data, example
Such as, when needing to increase the dimension of finance data, the finance data issued can will be needed to pass through number by the way of manual entry
It is imported according to typing interface.
The finance data is inputted preset banking index analysis model, so that banking index analysis model pair by S102
The finance data is analyzed, and obtains city banking index analysis result.
Wherein, the construction method of banking index analysis model is described below:
(1) weight of each two-level index is obtained by level analysis analytic approach (AHP)
When regarding first class index as destination layer, two-level index is decision-making level, the vector constituted with three-level index under certain time point
For the solution layer of scheme, then index system has showed certain recursive hierarchy structure, and analytic hierarchy process (AHP) can be used to be sent out
Open up horizontal evaluation number.It is true after studying repeatedly according to data, expertise and the experience of systems analyst
Determine judgment matrix.Judgment matrix table be for upper level unit (element), this level and it in relation to relatively heavy between unit
The comparison for the property wanted.Since our purpose is measuring and calculating index, so judgment matrix constructs only between destination layer and rule layer,
Not development of judgment matrix between solution layer and rule layer.
Analytic hierarchy process (AHP) uses 1-9 Scale Method, provides quantity scale to the comparation and assessment of different situations, as shown in table 1.
Table 1: the scale standard of judgment matrix
| Score value | The scale standard of judgment matrix |
| 1 | It indicates that two elements are compared, there is same importance |
| 3 | Indicate that two elements are compared, another yuan of rope of an element ratio is slightly important |
| 5 | Indicate that two elements are important compared to another yuan of Suo Mingxian of mono- element ratio of |
| 7 | Indicate that two elements are compared, element ratio another element is strongly important |
| 9 | Two elements of table are extremely important compared to mono- element of another yuan of rope that stick together |
Then, the judgment matrix A of evaluation index is successively constructed according to scale value
Wherein A is discrimination matrix, aijFor element i and j important ratio compared with as a result, and have following relationship:
aij=1/aij
aijThere are 9 kinds of values, respectively 1/9,1/7,1/5,1/3,1/1,3,5,7,9, i element is respectively indicated for j element
Significance level is from light to heavy.
In addition, consistency check is also needed to judgment matrix, to avoid the illogical problem that scores is compared.
Then the Maximum characteristic root and its corresponding feature vector, this feature vector for solving judgment matrix are required
The weight coefficient of each index.
(2) all kinds of three-level indexs are normalized
To calculate financial technology index sector, combination of qualitative and quantitative analysis makes the index found out have comparativity, we are right
The statistic of three-level index carries out nondimensionalization processing with 0-1 standardized technique, different, the greatly different in size different indexs by dimension
It is transformed into same level so that data at the same level can compare in organizing.Formula is as follows
Wherein, XmaxFor maximum value, XminFor minimum value
(3) development index is tentatively synthesized
The calculation method of composite index number is the symmetrical change rate for first finding out each three-level index, the actually single order of sequence
Difference relative change rate makes peak, paddy and its drop seem and becomes apparent from the purpose is to make sequence stationary, rule and mean value zero,
So as to subsequent analysis and judgement.Then, the average rate of change between the group of each group index is found out, so that each second level index is comparable.If
Without standardization, the effect in the big sequence group of index value can be strengthened, so that it is small to weaken index value relatively
Sequence and then the weight calculation average rate of change obtained with analytic hierarchy process (AHP) are simultaneously standardized again.
The present embodiments relate to index i.e. be characterized, for meet term habit, there is place to be write as index, some places
Write as feature, it should be understood by those skilled in the art that the two reference is same.
The embodiment of the present invention has the advantages that according to the banking index analysis model constructed in advance to the finance
Data are analyzed, and obtain city banking index analysis as a result, can obtain city banking index it is accurate analyze as a result, from
And it can be by the analysis of index as a result, promoting the development of each city financial circles.
Embodiment two
Fig. 2 is the process of the embodiment two of the city banking index analysis method of the invention based on big data analysis technology
Figure, the city banking index analysis method based on big data analysis technology of the present embodiment on the basis of the above embodiment 1,
Technical solution of the present invention is further introduced in further detail.As shown in Fig. 2, the present embodiment based on big data analysis technology
City banking index analysis method, can specifically include following steps:
S201 obtains finance data.
Since many websites are provided with anti-crawler strategy, when obtaining finance data, it is contemplated that climb reply for counter
Strategy.
The embodiment of the present invention can store data in diversified forms, after obtaining finance data for example, cloud storage.
It can guarantee not interrupting for business demand in this way.And when upgrading service or flow uprush, need to create a large amount of cloud hosts,
The quick creation of cloud host is enable to respond quickly business demand.
S202 pre-processes the finance data.
Wherein, step S202 includes: to clean to the finance data, then the finance data after storage cleaning.
Since the finance data obtained on the internet may be structuring, it is also possible to semi-structured or unstructured
, it is therefore desirable to data cleansing is carried out to the finance data of acquisition.To realize standardization, the sampling of data, data of finance data
It sorts, summarize, specifying the functions such as dependent variable, attribute transformation, data replacement, Data Dimensionality Reduction, data set fractionation, discretization.In addition,
Finance data after cleaning can be loaded into data warehouse, and if the processing result that data warehouse summarizes layer is not able to satisfy gold
Data exhibiting demand can then build Data Mart to store the finance data after cleaning.
In addition, finance data can also be normalized in pretreatment stage.
In addition, since data format is not quite similar, data parsing can be carried out to finance data after obtaining finance data,
To support multiple format data source；Can also duplicate removal processing be carried out to acquired finance data.
S203 constructs the banking index analysis model so that banking index analysis model to the finance data into
Row analysis.
Step S203 includes: A, and according to the training data and at least one preset algorithm in the finance data, building is extremely
A few banking index analysis model；B assesses each banking index point according to the test data in the finance data
It analyses model and the banking index analysis model is determined according to assessment result.
Wherein, the foundation and optimization of banking index analysis model are broadly divided into three steps: aspect of model selection, building number
According to collecting, attempt a variety of models.The sequence for stating three steps well can according to need, and adjust at any time.
The embodiment of the present invention is that the model of building is enable accurately to analyze finance data, can construct a variety of moulds
Type analyzes finance data, then assesses analysis result, and then the optimal model of selection analysis result is as gold
Melt index analysis model.In addition, accurately to be assessed analysis result, it can be by acquired finance data according to default ratio
Example is divided into two parts, and a part is used for test model as test data for constructing model, another part as training data
Analysis result.For example, the finance data of acquisition can be divided in 8 to 2 ratio, that is to say, that 80% finance data conduct
Training data, by 20% data test data.
The embodiment of the present invention can first determine that the feature that model needs.Wherein, feature can include: financial technology industry achievement
The two-level index such as effect, financial technology mechanism strength, financial technology market scale and financial technology ecological environment.Meanwhile each
The subdivision that index is portrayed is carried out under two-level index, for example, ten or more three-level indexs can be chosen as measurement financial technology industry
The base values of development level.
Then finance data collection can be constructed after obtaining finance data by obtaining finance data corresponding with feature.To prevent
Data over-fitting can carry out the data sequence that finance data is concentrated randomly ordered.The structure of data set can be (y, x1,
x2... ..., xn), wherein y is the label value of the data set, x1, x2... ..., xnFor the feature of constructed model, n is constructed mould
The dimension of type.Y corresponds to the test data in finance data, x1, x2... ..., xnTraining data in corresponding finance data.Also
It is to say, when using x1, x2... ..., xnAfter being built into model, the financial analysis of input test value y, test "current" model output refer to
Whether number is accurate.
Simultaneously as the index of city finance has plenty of positive index when being calculated, has plenty of negative sense (reverse) and refer to
Mark, therefore to when analyzing finance data, it is desirable to provide business is explained, or needs to assign weight to each feature.
The embodiment of the present invention can construct a variety of data models, according to the business demand of city financial analysis index, for example, can
Building recurrence, classification or Clustering Model.Actual conditions based on data, such as data scale, the information such as distribution situation of data,
The different models such as logistic regression, support vector machines, decision tree are selected, or according to business demand, design new model algorithm, and remember
Record the effect and performance of every kind of model.
After having constructed data model, the test data in data set can be used to carry out cross validation to model.For example, right
In large-scale data, cross validation need to be rolled over using K；For small-scale data, K folding cross validation can be selected or stay a verifying.
Selected verification method can be recorded in log.
In addition, each data model is all corresponding with many kinds of parameters, after constructing data model, need to carry out different parameters
Adjustment, to seek the optimized parameter of each model, and records the effect and performance of each parameter drag.
For example, for disaggregated model, the accuracy (accuracy) of every kind of model need to be recorded, accuracy (precision),
Area value (Area Under under recall rate (recall), comprehensive evaluation index (F1-score) and receiver operating curves
The ROC Curve, AUC), other results of property can be free.
For another example needing to record the root-mean-square error (RMSE), mean absolute difference of every kind of model for regression model
(MAE) and average absolute percentage error (MAPE), other results of property can be free.
For another example needing to record its silhouette coefficient (Silhouette Coefficient) for Clustering Model.If there is
True value still needs to recording accuracy, accuracy, recall rate, F1 value, AUC value and blue moral index (the adjusted rand of adjustment
Index, ARI).
In addition, developer requires the time complexity and space complexity of assessment models, and will for each class model
Speed and memory occupation rate are recorded in log.Then selecting time complexity and the satisfactory data mould of space complexity
Type.
The finance data is inputted preset banking index analysis model, so that banking index analysis model pair by S204
The finance data is analyzed, and obtains city banking index analysis result.
The step S102 of above-mentioned steps S204 corresponding embodiment one.
The embodiment of the present invention, also offer data management function, for example, rights management, data blood relationship and metadata are checked
Function.
The embodiment of the present invention has the advantages that according to the banking index analysis model constructed in advance to the finance
Data are analyzed, and obtain city banking index analysis as a result, can obtain city banking index it is accurate analyze as a result, from
And it can be by the analysis of index as a result, promoting the development of each city financial circles.
Embodiment three
Fig. 3 is the schematic diagram of the city banking index analytical equipment of the invention based on big data analysis technology, such as Fig. 3 institute
Show, the city banking index analytical equipment based on big data analysis technology of the present embodiment, can specifically include and obtain module 31
With analysis module 32.
Module 31 is obtained, is configured to obtain finance data；
Analysis module 32 is configured to the finance data inputting preset banking index analysis model, so that finance refers to
Number analysis model analyzes the finance data, and obtains city banking index analysis result.
The city banking index analytical equipment based on big data analysis technology of the present embodiment, by using above-mentioned module pair
The realization mechanism of city banking index analysis and the city finance based on big data analysis technology of above-mentioned embodiment illustrated in fig. 1 refer to
The realization mechanism of number analysis method is identical, can refer to the record of above-mentioned embodiment illustrated in fig. 1 in detail, details are not described herein.
Example IV
Fig. 4 is the schematic diagram of the city banking index analytical equipment of the invention based on big data analysis technology, such as Fig. 4 institute
Show, the city banking index analytical equipment based on big data analysis technology of the present embodiment can specifically include:
Module 33 is constructed, is configured to construct the banking index analysis model, so that banking index analysis model is to institute
Finance data is stated to be analyzed.
Further, the building module concrete configuration are as follows:
According to the training data and at least one preset algorithm in the finance data, at least one banking index point is constructed
Analyse model；
According to the test data in the finance data, each banking index analysis model is assessed, is tied according to assessment
Fruit determines the banking index analysis model.
Further, the building module also concrete configuration are as follows:
Adjust the parameter of the banking index analysis model；
Determine the effect and performance of the corresponding banking index analysis model output of the parameter；
Select effect and the satisfactory banking index analysis model of performance.
Further, the building module also concrete configuration are as follows:
Cross validation is carried out to the banking index analysis model；
Calculate the time complexity and space complexity of each banking index analysis model；
It selects time complexity and space complexity is more than the banking index analysis model of preset threshold.
The city banking index analytical equipment based on big data analysis technology of the present embodiment, by using above-mentioned module pair
The realization mechanism of city banking index analysis and the city finance based on big data analysis technology of above-mentioned embodiment illustrated in fig. 2 refer to
The realization mechanism of number analysis method is identical, can refer to the record of above-mentioned embodiment illustrated in fig. 2 in detail, details are not described herein.
Above embodiments are only exemplary embodiment of the present invention, are not used in the limitation present invention, protection scope of the present invention
It is defined by the claims.Those skilled in the art can within the spirit and scope of the present invention make respectively the present invention
Kind modification or equivalent replacement, this modification or equivalent replacement also should be regarded as being within the scope of the present invention.
Claims (13)
1. a kind of city banking index analysis method based on big data analysis technology characterized by comprising
Obtain finance data；
The finance data is inputted into preset banking index analysis model, so that banking index analysis model is to the financial number
According to being analyzed, and obtain city banking index analysis result.
2. being analyzed the method according to claim 1, wherein the finance data is inputted preset banking index
Model, with obtain city banking index analysis result before, which comprises
The banking index analysis model is constructed, so that banking index analysis model analyzes the finance data.
3. according to the method described in claim 2, it is characterized in that, constructing the banking index analysis model and including:
According to the training data and at least one preset algorithm in the finance data, at least one banking index analysis mould is constructed
Type；
According to the test data in the finance data, each banking index analysis model is assessed, according to assessment result, really
The fixed banking index analysis model.
4. according to the method described in claim 3, it is characterized in that, according to the training data in the finance data and at least one
A preset algorithm constructs at least one banking index analysis model:
Adjust the parameter of the banking index analysis model；
Determine the effect and performance of the corresponding banking index analysis model output of the parameter；
Select effect and the satisfactory banking index analysis model of performance.
5. according to the method described in claim 3, it is characterized in that, assessment is every according to the test data in the finance data
A banking index analysis model determines that the banking index analysis model includes: according to assessment result
Cross validation is carried out to the banking index analysis model；
Calculate the time complexity and space complexity of each banking index analysis model；
It selects time complexity and space complexity is more than the banking index analysis model of preset threshold.
6. the method according to claim 1, wherein acquisition finance data includes:
Using web crawlers technology, the finance data on internet is obtained；Alternatively,
Receive the finance data of typing.
7. the method according to claim 1, wherein obtain finance data after, the method also includes:
The finance data is pre-processed.
8. the method according to the description of claim 7 is characterized in that the finance data carry out pretreatment include:
The finance data is cleaned, then the finance data after storage cleaning.
9. a kind of city banking index analytical equipment based on big data analysis technology characterized by comprising
Module is obtained, is configured to obtain finance data；
Analysis module is configured to the finance data inputting preset banking index analysis model, so that banking index is analyzed
Model analyzes the finance data, and obtains city banking index analysis result.
10. device according to claim 9, which is characterized in that described device further include:
Module is constructed, is configured to construct the banking index analysis model, so that banking index analysis model is to the finance
Data are analyzed.
11. device according to claim 10, which is characterized in that the building module concrete configuration are as follows:
According to the training data and at least one preset algorithm in the finance data, at least one banking index analysis mould is constructed
Type；
According to the test data in the finance data, each banking index analysis model is assessed, according to assessment result, really
The fixed banking index analysis model.
12. device according to claim 11, which is characterized in that the building module concrete configuration are as follows:
Adjust the parameter of the banking index analysis model；
Determine the effect and performance of the corresponding banking index analysis model output of the parameter；
Select effect and the satisfactory banking index analysis model of performance.
13. device according to claim 11, which is characterized in that the building module concrete configuration are as follows:
Cross validation is carried out to the banking index analysis model；
Calculate the time complexity and space complexity of each banking index analysis model；
It selects time complexity and space complexity is more than the banking index analysis model of preset threshold.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810563023.1A CN109063944A (en) | 2018-06-04 | 2018-06-04 | City banking index analysis method and device based on big data analysis technology |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810563023.1A CN109063944A (en) | 2018-06-04 | 2018-06-04 | City banking index analysis method and device based on big data analysis technology |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109063944A true CN109063944A (en) | 2018-12-21 |
Family
ID=64820317
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810563023.1A Pending CN109063944A (en) | 2018-06-04 | 2018-06-04 | City banking index analysis method and device based on big data analysis technology |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109063944A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111242779A (en) * | 2020-01-03 | 2020-06-05 | 湖南工商大学 | Financial data characteristic selection and prediction method, device, equipment and storage medium |
| CN112860785A (en) * | 2021-03-31 | 2021-05-28 | 山东财经大学 | Economic data analysis method and system |
-
2018
- 2018-06-04 CN CN201810563023.1A patent/CN109063944A/en active Pending
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111242779A (en) * | 2020-01-03 | 2020-06-05 | 湖南工商大学 | Financial data characteristic selection and prediction method, device, equipment and storage medium |
| CN111242779B (en) * | 2020-01-03 | 2023-08-18 | 湖南工商大学 | Financial data characteristic selection and prediction method, device, equipment and storage medium |
| CN112860785A (en) * | 2021-03-31 | 2021-05-28 | 山东财经大学 | Economic data analysis method and system |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110222267B (en) | Game platform information pushing method, system, storage medium and equipment | |
| WO2020249125A1 (en) | Method and system for automatically training machine learning model | |
| López-Robles et al. | Understanding the intellectual structure and evolution of Competitive Intelligence: A bibliometric analysis from 1984 to 2017 | |
| US9489627B2 (en) | Hybrid clustering for data analytics | |
| CN109409677A (en) | Enterprise Credit Risk Evaluation method, apparatus, equipment and storage medium | |
| CN111324642A (en) | Model algorithm type selection and evaluation method for power grid big data analysis | |
| CN104321794B (en) | A kind of system and method that the following commercial viability of an entity is determined using multidimensional grading | |
| CN106227756A (en) | A kind of stock index forecasting method based on emotional semantic classification and system | |
| CN104573130A (en) | Entity resolution method based on group calculation and entity resolution device based on group calculation | |
| Yao | Financial accounting intelligence management of internet of things enterprises based on data mining algorithm | |
| CN111738843B (en) | Quantitative risk evaluation system and method using running water data | |
| Zhang et al. | Author impact: Evaluations, predictions, and challenges | |
| CN112419029A (en) | Similar financial institution risk monitoring method, risk simulation system and storage medium | |
| Sarantitis et al. | A network analysis of the United Kingdom’s consumer price index | |
| Rabbi et al. | An Approximation For Monitoring The Efficiency Of Cooperative Across Diverse Network Aspects | |
| Molina-Gómez et al. | Air quality and urban sustainable development: the application of machine learning tools | |
| CN109063944A (en) | City banking index analysis method and device based on big data analysis technology | |
| Zhang et al. | Research on borrower's credit classification of P2P network loan based on LightGBM algorithm | |
| Kipkogei et al. | Business success prediction in Rwanda: a comparison of tree-based models and logistic regression classifiers | |
| CN112506930B (en) | Data insight system based on machine learning technology | |
| CN107291722B (en) | Descriptor classification method and device | |
| Zhang et al. | Application of random forest classifier in loan default forecast | |
| Shaji et al. | Weather Prediction Using Machine Learning Algorithms | |
| Porwal et al. | Citation Classification Prediction Implying Text Features Using Natural Language Processing and Supervised Machine Learning Algorithms | |
| Jabir et al. | Big data analytics for strategic and operational decisions |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20181221 |
|
| WD01 | Invention patent application deemed withdrawn after publication |