CN110097430A - A kind of auto metal halide lamp product intelligent matching system based on artificial intelligence - Google Patents
A kind of auto metal halide lamp product intelligent matching system based on artificial intelligence Download PDFInfo
- Publication number
- CN110097430A CN110097430A CN201910379331.3A CN201910379331A CN110097430A CN 110097430 A CN110097430 A CN 110097430A CN 201910379331 A CN201910379331 A CN 201910379331A CN 110097430 A CN110097430 A CN 110097430A
- Authority
- CN
- China
- Prior art keywords
- metal halide
- halide lamp
- data
- auto metal
- lamp product
- 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
- G06Q30/00—Commerce
- G06Q30/06—Buying, selling or leasing transactions
- G06Q30/0601—Electronic shopping [e-shopping]
- G06Q30/0623—Item investigation
- G06Q30/0625—Directed, with specific intent or strategy
- G06Q30/0629—Directed, with specific intent or strategy for generating comparisons
-
- 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
- G06Q40/03—Credit; Loans; Processing thereof
Landscapes
- Business, Economics & Management (AREA)
- Accounting & Taxation (AREA)
- Finance (AREA)
- Engineering & Computer Science (AREA)
- Strategic Management (AREA)
- Marketing (AREA)
- Economics (AREA)
- Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Development Economics (AREA)
- Theoretical Computer Science (AREA)
- Technology Law (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The present invention relates to auto metal halide lamp product intelligent matching system technical fields, and disclose a kind of auto metal halide lamp product intelligent matching system based on artificial intelligence, Matching Model generation module including single automobile financial product and newly into the Matching Model generation module of the optimal auto metal halide lamp product of user, the Matching Model generation module of single automobile financial product includes first information acquiring unit, first information acquiring unit is connected with data processing unit by signal, data processing unit is connected with matching generation unit by signal, it matches generation unit and comparing unit is connected with by signal.The auto metal halide lamp product intelligent matching system based on artificial intelligence, has realization intelligent screening, breakneck acceleration block, reduce the labor intensity of staff, improve the efficiency of auto metal halide lamp product, and screening can reduce screening error on a large scale, the advantages that optimal auto metal halide lamp product can be selected, improve the factor of merit of auto metal halide lamp product.
Description
Technical field
The present invention relates to auto metal halide lamp product intelligent matching system technical field, specially a kind of vapour based on artificial intelligence
Vehicle financial product intelligent Matching system.
Background technique
Further be deep into auto metal halide lamp in current sale of automobile market, consumption terminal automobile credit scale
Through having reached the scale of construction of tera-scale.Under such huge scale of construction, bank, auto metal halide lamp, guarantee system, financing lease, consumption gold
Melt the financial product that company etc. is proposed up to ten thousand kinds of different credit requirements, it is contemplated that same financing corporation can also push away in different cities
Different product out, the quantity of financial product is just more huge, and its quantity also increasingly increase in, in current business
In, directly dock client credit operation personnel need by the whole credit data of client it is written be delivered to financial product examine
It criticizes at member, based on the auto metal halide lamp air control model inside financing corporation, examination & approval person determines whether the client can be by the finance
The loan of product.For credit operation personnel, such a large amount of financial product item now, only continuous
After the loan of multiple financial products is attempted on ground, just a satisfied loan can be found for client.It is the most key, because
The mechanism of every financial product can all inquire Central Bank's reference of client, so each trial of business personnel can be limited at one
Financial product influences the success rate of loan to avoid Central Bank's reference information of multiple inquiry client.
Auto metal halide lamp product selection at present is mostly artificial selection, and artificial screening working strength is larger, and the efficiency screened
Lower, simultaneously because artificial screening range is smaller, error is larger, and the factor of merit of last auto metal halide lamp product is lower.
Summary of the invention
(1) the technical issues of solving
In view of the deficiencies of the prior art, the auto metal halide lamp product intelligent matching based on artificial intelligence that the present invention provides a kind of
System has realization intelligent screening, and breakneck acceleration block reduces the labor intensity of staff, improves auto metal halide lamp product
Efficiency, and a wide range of screening can reduce screening error, can select optimal auto metal halide lamp product, improve auto metal halide lamp product
The factor of merit the advantages that, solving the selection of current auto metal halide lamp product is mostly artificial selection, and artificial screening working strength is larger,
And the efficiency of screening is lower, simultaneously because artificial screening range is smaller, error is larger, and the last auto metal halide lamp product factor of merit is lower
The problem of.
(2) technical solution
Has realization intelligent screening for realization is above-mentioned, breakneck acceleration block reduces the labor intensity of staff, improves
The efficiency of auto metal halide lamp product, and a wide range of screening can reduce screening error, can select optimal auto metal halide lamp product, improve
The purpose of the factor of merit of auto metal halide lamp product, the invention provides the following technical scheme: a kind of auto metal halide lamp based on artificial intelligence
Product intelligent matching system, Matching Model generation module including single automobile financial product and newly into the optimal auto metal halide lamp of user
The Matching Model generation module of product, the Matching Model generation module of the single automobile financial product include that the first information obtains
Unit, the first information acquiring unit are connected with data processing unit by signal, and the data processing unit passes through signal
It is connected with matching generation unit, the matching generation unit is connected with comparing unit by signal, and the comparing unit passes through
Signal is connected with financial product database, and the comparing unit is connected with output unit by signal.
Preferably, described includes newly the second acquisition of information into the Matching Model generation module of the optimal auto metal halide lamp product of user
Unit, second information acquisition unit are connect with data processing unit signal, and the matching generation unit is connected by signal
There is preferentially unit, the preferentially unit is connect by signal with output unit.
Preferably, the data processing unit includes data cleansing function, while data acquisition system is split into training data
Collection and test data set.
Preferably, the financial product database has included consumer finance company etc. and has been proposed up to ten thousand kinds of different credit requirements
Financial product.
Preferably, the matching unit includes logistic regression algorithm and XGBoost algorithm, and the algorithm is as follows:
Preferably, the preferentially unit includes out of kilter method, and the out of kilter method is as follows:
F (n)=G (N)+H (N) g (n).
Preferably, the first information acquiring unit mainly obtains historical user's representation data, vehicle information data and loan
Money information data, second acquisition of information mechanism mainly obtain active user's representation data, vehicle information data and provide a loan well letter
Cease data.
Preferably, the single automobile financial product Matching Model generation module specific steps are as follows:
A. it is directed to single automobile financial product, by way of artificially collecting or extract in back-end data base, is obtained
The initial historical data comprising user's credit information and result.
B. data cleansing is carried out to the historical data of acquisition, data dump normally will be inconsistent, and ensure every data
All it is marked as " providing a loan successfully " or " loan is unsuccessful ".
C. data set is split as training dataset and test data set according to a certain percentage.
D. it is based on training dataset, using logistic regression algorithm, is differentiated to obtain the intelligent Matching of the auto metal halide lamp product
Model.
E. by testing the effect of each intelligent algorithm model generated on test set, optimal people is evaluated in selection
The intelligent Matching model of work intelligent algorithm and corresponding matching discrimination model as the auto metal halide lamp product.
F. all automobile credit products are directed to, above-mentioned A to E step is repeated, to be generated for each auto metal halide lamp product
Optimal intelligent Matching discrimination model.
Preferably, it is described newly into the Matching Model generation module concrete operation step of the optimal auto metal halide lamp product of user such as
Under:
G. user's representation data newly into user, purchased information of vehicles, required credit information are acquired.
H. data cleansing is carried out to the data of acquisition.
L., in the matching discrimination model that data after cleaning are fed to multiple auto metal halide lamp products, obtaining one " can be borrowed
The auto metal halide lamp product set of money success ".
K. the gold for being best suitable for user's actual conditions can be selected in the auto metal halide lamp product set of " success of providing a loan " at this
Melt product, for example the foundation first payment, loan interest rate, length of maturity etc. select optimal auto metal halide lamp product.
(3) beneficial effect
Compared with prior art, the present invention provides a kind of, and the auto metal halide lamp product intelligent based on artificial intelligence matches system
System, have it is following the utility model has the advantages that
The auto metal halide lamp product intelligent matching system based on artificial intelligence, by be provided with first information acquiring unit,
Second information acquisition unit, data processing unit and matching unit are artificially collected by first information acquiring unit or rear
The mode extracted in client database obtains the initial historical data comprising user's credit information and result, then passes through data
Processing unit carries out data cleansing to the historical data of acquisition, will not be inconsistent data dump normally, and ensure every data all
It is marked as " providing a loan successfully " or " loan is unsuccessful ", data set is split as to training dataset and test according to a certain percentage
Data set is based on training dataset, using logistic regression algorithm, differentiates mould to obtain the intelligent Matching of the auto metal halide lamp product
Type, by testing the effect of each intelligent algorithm model generated on test set, optimal artificial intelligence is evaluated in selection
The intelligent Matching model of algorithm and corresponding matching discrimination model as the auto metal halide lamp product, for all automobile credits
Product repeats above-mentioned A to E step, to generate optimal intelligent Matching discrimination model for each auto metal halide lamp product, later
It, then will be after cleaning by customer information input system to newly being generated into the Matching Model of the optimal auto metal halide lamp product of user
Data are fed in the matching discrimination model of multiple auto metal halide lamp products, obtain one can " success of providing a loan " auto metal halide lamp product
Set, does not need artificial screening, time saving and energy saving, which has realization intelligent screening, and breakneck acceleration block reduces staff
Labor intensity, improve the efficiency of auto metal halide lamp product, and a wide range of screening can reduce screening error, can select optimal
Auto metal halide lamp product improves the factor of merit of auto metal halide lamp product.
Detailed description of the invention
Fig. 1 is a kind of working principle of the auto metal halide lamp product intelligent matching system based on artificial intelligence proposed by the present invention
Figure；
Fig. 2 is single automobile in a kind of auto metal halide lamp product intelligent matching system based on artificial intelligence proposed by the present invention
The Matching Model generation module work flow diagram of financial product；
Fig. 3 is in a kind of auto metal halide lamp product intelligent matching system based on artificial intelligence proposed by the present invention newly into user
The Matching Model generation module work flow diagram of optimal auto metal halide lamp product.
Specific embodiment
The technical scheme in the embodiments of the invention will be clearly and completely described below, it is clear that described implementation
Example is only a part of the embodiment of the present invention, instead of all the embodiments.Based on the embodiments of the present invention, this field is common
Technical staff's every other embodiment obtained without making creative work belongs to the model that the present invention protects
It encloses.
Please refer to Fig. 1-3, a kind of auto metal halide lamp product intelligent matching system based on artificial intelligence, including single automobile gold
Melt the Matching Model generation module of product and newly into the Matching Model generation module of the optimal auto metal halide lamp product of user, single automobile
The Matching Model generation module of financial product includes first information acquiring unit, and first information acquiring unit is connected with by signal
Data processing unit, data processing unit are connected with matching generation unit by signal, and matching generation unit is connected by signal
There is comparing unit, comparing unit is connected with financial product database by signal, and the comparing unit is connected with by signal
Output unit.
It include newly the second information acquisition unit, the second letter into the Matching Model generation module of the optimal auto metal halide lamp product of user
Breath acquiring unit is connect with data processing unit signal, is matched generation unit by signal and is connected with preferentially unit, preferentially unit
It is connect by signal with output unit.
Data processing unit includes data cleansing function, while data acquisition system is split into training dataset and test data
Collection.
Financial product database includes the financial product that consumer finance company etc. is proposed up to ten thousand kinds of different credit requirements.
Matching unit includes logistic regression algorithm and XGBoost algorithm, and the algorithm is as follows:
The out of kilter method algorithm steps are as follows, be in logistic regression usingEquation carries out
Mapping, wherein z is exactly the z of linear function because g (z) finally export when sample class probability value, we can be
Threshold value is set as 0.5, g (z) and regards 1 as more than or equal to 0.5, less than 0.5 regards 0 as, in this way we can using logistic regression come
Two classification auto metal halide lamp product of processing, then utilizesFormula selection
High quality car financial product, and pass throughIt is predicted, finally according under gradient
Drop method is minimized, which isFinally patrolled by a series of algorithm steps
Collect regression algorithmAnd
XGBoost algorithmPass through loss functionEvolution obtains.
Preferentially unit includes out of kilter method, and the out of kilter method is as follows: F (n)=G (N)+H (N) g (n), this is preferentially
Algorithm algorithm steps are as follows, and the first step is put into initial node So in open table, F (S0)=G (S0)+h (S0)；Second step
If open table is sky, problem is unsuccessfully exited without solution；First node taking-up in open table is put into closed by third step
In table, and remember that the node is n；Whether the 4th step is destination node investigation node n.If so, having found the solution of problem, move back
Out, it is carried out without being destination node in next step, whether the 5th step investigation node is expansible, and it is not expansible to be returned to second step, it can
With regard to carrying out in next step, the 6th step extends node n for extension, generates the evaluation function that child node calculates each child node, and is each
A child node is set to point to the pointer of father node, and then these nodes are put into open table, and the 7th step is according to evaluation function
The size of value carries out sequence (minimum just first in open table) from small to large to the node in open table, wherein (n)
For node depth, h (n) is not in the number of Digital sum.
First information acquiring unit mainly obtains historical user's representation data, vehicle information data and credit information data,
Second acquisition of information mechanism mainly obtains the good credit information data of active user's representation data, vehicle information data.
The Matching Model generation module of single automobile financial product specific steps are as follows:
A. it is directed to single automobile financial product, by way of artificially collecting or extract in back-end data base, is obtained
The initial historical data comprising user's credit information and result.
B. data cleansing is carried out to the historical data of acquisition, data dump normally will be inconsistent, and ensure every data
All it is marked as " providing a loan successfully " or " loan is unsuccessful ".
C. data set is split as training dataset and test data set according to a certain percentage.
D. it is based on training dataset, using logistic regression algorithm, is differentiated to obtain the intelligent Matching of the auto metal halide lamp product
Model.
E. by testing the effect of each intelligent algorithm model generated on test set, optimal people is evaluated in selection
The intelligent Matching model of work intelligent algorithm and corresponding matching discrimination model as the auto metal halide lamp product.
F. all automobile credit products are directed to, above-mentioned A to E step is repeated, to be generated for each auto metal halide lamp product
Optimal intelligent Matching discrimination model.
Newly into the Matching Model generation module of the optimal auto metal halide lamp product of user specific steps are as follows:
G. user's representation data newly into user, purchased information of vehicles, required credit information are acquired.
H. data cleansing is carried out to the data of acquisition.
L., in the matching discrimination model that data after cleaning are fed to multiple auto metal halide lamp products, obtaining one " can be borrowed
The auto metal halide lamp product set of money success ".
K. the gold for being best suitable for user's actual conditions can be selected in the auto metal halide lamp product set of " success of providing a loan " at this
Melt product, for example the foundation first payment, loan interest rate, length of maturity etc. select optimal auto metal halide lamp product.
In conclusion being somebody's turn to do the auto metal halide lamp product intelligent matching system based on artificial intelligence, passes through the first information and obtain list
The mode that member is artificially collected or extracted in back-end data base obtains the initial history comprising user's credit information and result
Then data carry out data cleansing by historical data of the data processing unit to acquisition, will not be inconsistent data dump normally,
And ensure that every data is all marked as " providing a loan successfully " or " loan is unsuccessful ", data set is split as according to a certain percentage
Training dataset and test data set are based on training dataset, using logistic regression algorithm, to obtain the auto metal halide lamp product
Intelligent Matching discrimination model, by testing the effect of each intelligent algorithm model generated, selection evaluation on test set
The intelligent Matching model of optimal intelligent algorithm and corresponding matching discrimination model as the auto metal halide lamp product, for
All automobile credit products repeat above-mentioned A to E step, to generate optimal intelligent for each auto metal halide lamp product
With discrimination model, later to newly being generated into the Matching Model of the optimal auto metal halide lamp product of user, by customer information input system,
In then matching discrimination model that data after cleaning are fed to multiple auto metal halide lamp products, obtaining one can " success of providing a loan "
Auto metal halide lamp product set, do not need artificial screening, time saving and energy saving, which has a realization intelligent screening, breakneck acceleration block,
The labor intensity for reducing staff improves the efficiency of auto metal halide lamp product, and a wide range of screening can reduce screening and miss
Difference can select optimal auto metal halide lamp product, improve the factor of merit of auto metal halide lamp product.
It should be noted that the terms "include", "comprise" or its any other variant are intended to the packet of nonexcludability
Contain, so that the process, method, article or equipment for including a series of elements not only includes those elements, but also including
Other elements that are not explicitly listed, or further include for elements inherent to such a process, method, article, or device.
In the absence of more restrictions, the element limited by sentence "including a ...", it is not excluded that including the element
Process, method, article or equipment in there is also other identical elements.
It although an embodiment of the present invention has been shown and described, for the ordinary skill in the art, can be with
A variety of variations, modification, replacement can be carried out to these embodiments without departing from the principles and spirit of the present invention by understanding
And modification, the scope of the present invention is defined by the appended.
Claims (9)
1. a kind of auto metal halide lamp product intelligent matching system based on artificial intelligence, the matching mould including single automobile financial product
Type generation module and newly into the Matching Model generation module of the optimal auto metal halide lamp product of user, it is characterised in that: the single vapour
The Matching Model generation module of vehicle financial product includes first information acquiring unit, and the first information acquiring unit passes through signal
It is connected with data processing unit, the data processing unit is connected with matching generation unit by signal, and the matching generates single
Member is connected with comparing unit by signal, and the comparing unit is connected with financial product database, the comparison by signal
Unit is connected with output unit by signal.
2. a kind of auto metal halide lamp product intelligent matching system based on artificial intelligence according to claim 1, feature exist
In: described includes newly the second information acquisition unit into the Matching Model generation module of the optimal auto metal halide lamp product of user, and described the
Two information acquisition units are connect with data processing unit signal, and the matching generation unit is connected with preferentially unit by signal,
The preferentially unit is connect by signal with output unit.
3. a kind of auto metal halide lamp product intelligent matching system based on artificial intelligence according to claim 1, feature exist
In: the data processing unit includes data cleansing function, while data acquisition system is split into training dataset and test data
Collection.
4. a kind of auto metal halide lamp product intelligent matching system based on artificial intelligence according to claim 1, feature exist
In: the financial product database includes the financial product that consumer finance company etc. is proposed up to ten thousand kinds of different credit requirements.
5. a kind of auto metal halide lamp product intelligent matching system based on artificial intelligence according to claim 1, feature exist
In: the matching unit includes logistic regression algorithm and XGBoost algorithm, and the algorithm is as follows:
6. a kind of auto metal halide lamp product intelligent matching system based on artificial intelligence according to claim 1, feature exist
In: the preferentially unit includes out of kilter method, and the out of kilter method is as follows:
F (n)=G (N)+H (N) g (n).
7. a kind of auto metal halide lamp product intelligent matching system based on artificial intelligence according to claim 1, feature exist
In: the first information acquiring unit mainly obtains historical user's representation data, vehicle information data and credit information data, institute
It states the second acquisition of information mechanism and mainly obtains the good credit information data of active user's representation data, vehicle information data.
8. a kind of auto metal halide lamp product intelligent matching system based on artificial intelligence according to claim 1, feature exist
In: the single automobile financial product Matching Model generation module specific steps are as follows:
A. it is directed to single automobile financial product, by way of artificially collecting or extract in back-end data base, is obtained initial
The historical data comprising user's credit information and result.
B. data cleansing is carried out to the historical data of acquisition, data dump normally will be inconsistent, and ensure every data all by
Mark into " providing a loan successfully " or " loan is unsuccessful ".
C. data set is split as training dataset and test data set according to a certain percentage.
D. it is based on training dataset, using logistic regression algorithm, to obtain the intelligent Matching discrimination model of the auto metal halide lamp product.
E. by testing the effect of each intelligent algorithm model generated on test set, optimal artificial intelligence is evaluated in selection
It can the intelligent Matching model of algorithm and corresponding matching discrimination model as the auto metal halide lamp product.
F. all automobile credit products are directed to, above-mentioned A to E step is repeated, to be generated most for each auto metal halide lamp product
Good intelligent Matching discrimination model.
9. a kind of auto metal halide lamp product intelligent matching system based on artificial intelligence according to claim 2, feature exist
In: it is described newly into the Matching Model generation module of the optimal auto metal halide lamp product of user specific steps are as follows:
G. user's representation data newly into user, purchased information of vehicles, required credit information are acquired.
H. data cleansing is carried out to the data of acquisition.
L., in the matching discrimination model that data after cleaning are fed to multiple auto metal halide lamp products, obtaining one " can provide a loan into
The auto metal halide lamp product set of function ".
K. it can select and be best suitable for the finance of user's actual conditions and produce in the auto metal halide lamp product set of " success of providing a loan " at this
Product, for example the foundation first payment, loan interest rate, length of maturity etc. select optimal auto metal halide lamp product.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910379331.3A CN110097430A (en) | 2019-05-08 | 2019-05-08 | A kind of auto metal halide lamp product intelligent matching system based on artificial intelligence |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910379331.3A CN110097430A (en) | 2019-05-08 | 2019-05-08 | A kind of auto metal halide lamp product intelligent matching system based on artificial intelligence |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110097430A true CN110097430A (en) | 2019-08-06 |
Family
ID=67447255
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910379331.3A Pending CN110097430A (en) | 2019-05-08 | 2019-05-08 | A kind of auto metal halide lamp product intelligent matching system based on artificial intelligence |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110097430A (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111340546A (en) * | 2020-02-25 | 2020-06-26 | 中信银行股份有限公司 | Method, device, computer equipment and readable storage medium for improving marketing efficiency of banking business |
| CN111339766A (en) * | 2020-02-19 | 2020-06-26 | 云南电网有限责任公司昆明供电局 | Operation ticket compliance checking method and device |
| CN111369341A (en) * | 2020-03-05 | 2020-07-03 | 厦门正北科技有限公司 | Intelligent risk scoring system for clients before automobile financial loan |
| CN111861757A (en) * | 2020-07-20 | 2020-10-30 | 深圳鼎盛电脑科技有限公司 | Financing matching method, system, equipment and storage medium |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20110246385A1 (en) * | 2009-10-26 | 2011-10-06 | Bank Of America Corporation | Automatically recalibrating risk models |
| CN107798600A (en) * | 2017-12-05 | 2018-03-13 | 深圳信用宝金融服务有限公司 | The credit risk recognition methods of the small micro- loan of internet finance and device |
| CN108711107A (en) * | 2018-05-25 | 2018-10-26 | 上海钱智金融信息服务有限公司 | Intelligent financing services recommend method and its system |
| CN109389490A (en) * | 2018-09-26 | 2019-02-26 | 深圳壹账通智能科技有限公司 | Loan product matching process, device, computer equipment and storage medium |
-
2019
- 2019-05-08 CN CN201910379331.3A patent/CN110097430A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20110246385A1 (en) * | 2009-10-26 | 2011-10-06 | Bank Of America Corporation | Automatically recalibrating risk models |
| CN107798600A (en) * | 2017-12-05 | 2018-03-13 | 深圳信用宝金融服务有限公司 | The credit risk recognition methods of the small micro- loan of internet finance and device |
| CN108711107A (en) * | 2018-05-25 | 2018-10-26 | 上海钱智金融信息服务有限公司 | Intelligent financing services recommend method and its system |
| CN109389490A (en) * | 2018-09-26 | 2019-02-26 | 深圳壹账通智能科技有限公司 | Loan product matching process, device, computer equipment and storage medium |
Non-Patent Citations (4)
| Title |
|---|
| 中国支付清算协会金融大数据研究组编著: "《金融大数据创新应用》", 30 June 2018, 中国金融出版社 * |
| 佚名: "logistic回归梯度下降法", 《HTTPS://WWW.DOCIN.COM/P-1991390343.HTML》 * |
| 沈晨昱: "XGBoost原理及其应用", 《计算机产品与流通》 * |
| 涂序彦等: "《广义人工智能》", 31 August 2012, 国防工业出版社 * |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111339766A (en) * | 2020-02-19 | 2020-06-26 | 云南电网有限责任公司昆明供电局 | Operation ticket compliance checking method and device |
| CN111340546A (en) * | 2020-02-25 | 2020-06-26 | 中信银行股份有限公司 | Method, device, computer equipment and readable storage medium for improving marketing efficiency of banking business |
| CN111369341A (en) * | 2020-03-05 | 2020-07-03 | 厦门正北科技有限公司 | Intelligent risk scoring system for clients before automobile financial loan |
| CN111861757A (en) * | 2020-07-20 | 2020-10-30 | 深圳鼎盛电脑科技有限公司 | Financing matching method, system, equipment and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110097430A (en) | A kind of auto metal halide lamp product intelligent matching system based on artificial intelligence | |
| CN110223168B (en) | Label propagation anti-fraud detection method and system based on enterprise relationship map | |
| CN111882446B (en) | Abnormal account detection method based on graph convolution network | |
| CN105608318B (en) | Crowdsourcing marks integration method | |
| CN105184574B (en) | A kind of detection method for applying mechanically trade company's classification code fraud | |
| CN106599935B (en) | Three decision unbalanced data oversampler methods based on Spark big data platform | |
| CN109636591A (en) | A kind of credit scoring card development approach based on machine learning | |
| CN109089314A (en) | A kind of indoor orientation method of the wifi sequence assistant GPS based on proposed algorithm | |
| CN107862347A (en) | A kind of discovery method of the electricity stealing based on random forest | |
| CN109739844B (en) | Data classification method based on attenuation weight | |
| CN107507038A (en) | A kind of electricity charge sensitive users analysis method based on stacking and bagging algorithms | |
| CN107817404A (en) | A kind of Portable metering automatization terminal trouble-shooter and its diagnostic method | |
| CN113096388A (en) | Short-term traffic flow prediction method based on gradient lifting decision tree | |
| CN105426441B (en) | A kind of automatic preprocess method of time series | |
| CN108596664B (en) | Method, system and device for determining unilateral transaction fee of electronic ticket | |
| CN106251241A (en) | A kind of feature based selects the LR Bagging algorithm improved | |
| CN108734567A (en) | A kind of asset management system and its appraisal procedure based on big data artificial intelligence air control | |
| Xu et al. | A novel algorithm for urban traffic congestion detection based on GPS data compression | |
| CN115358481A (en) | Early warning and identification method, system and device for enterprise ex-situ migration | |
| CN111755081A (en) | Method for generating and screening MOFs (metal-organic frameworks) with high methane adsorption rate | |
| CN108596227A (en) | A kind of leading influence factor method for digging of user power utilization behavior | |
| Zhu et al. | Loan default prediction based on convolutional neural network and LightGBM | |
| Yan et al. | The identification algorithm and model construction of automobile insurance fraud based on data mining | |
| CN107742131A (en) | Financial asset sorting technique and device | |
| CN116681461A (en) | Layering and grading amplification method based on off-line medicine retail market |
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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20190806 |
|
| RJ01 | Rejection of invention patent application after publication |