CN107274191A - A kind of shopping at network return of goods forecasting system based on seller - Google Patents
A kind of shopping at network return of goods forecasting system based on seller Download PDFInfo
- Publication number
- CN107274191A CN107274191A CN201710334392.9A CN201710334392A CN107274191A CN 107274191 A CN107274191 A CN 107274191A CN 201710334392 A CN201710334392 A CN 201710334392A CN 107274191 A CN107274191 A CN 107274191A
- Authority
- CN
- China
- Prior art keywords
- data
- module
- shopping
- goods
- seller
- 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
- G06Q30/01—Customer relationship services
- G06Q30/015—Providing customer assistance, e.g. assisting a customer within a business location or via helpdesk
- G06Q30/016—After-sales
-
- 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
- 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]
Landscapes
- Business, Economics & Management (AREA)
- Accounting & Taxation (AREA)
- Finance (AREA)
- Strategic Management (AREA)
- Development Economics (AREA)
- Engineering & Computer Science (AREA)
- General Business, Economics & Management (AREA)
- Physics & Mathematics (AREA)
- Marketing (AREA)
- General Physics & Mathematics (AREA)
- Economics (AREA)
- Theoretical Computer Science (AREA)
- Entrepreneurship & Innovation (AREA)
- Data Mining & Analysis (AREA)
- Game Theory and Decision Science (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a kind of shopping at network return of goods forecasting system based on seller, shopping at network history data store module, data integration module, data preprocessing module, data-mining module, human-computer interaction interface are included;Seller shopping at network return of goods forecasting system proposed by the present invention and its optimization method, can be achieved the prediction to certain shopping return of goods of this consumer;There is provided for seller and certain shopping results is prejudged, foundation is provided for merchandise sales decision-making, the global optimization of resource distribution is realized to a certain extent.
Description
Technical field
The invention belongs to Artificial Smart-Its field, more particularly to a kind of shopping at network based on seller
Return of goods forecasting system.
Background technology
Consumer has the data such as positive rating, items sold number of packages may be referred at present.This, can be as being before shopping
The reference frame of no shopping.If goods positive rating is high, sale number of packages is more, the risk for buying the article is smaller.This is one
Determine in degree, it is to avoid the shopping loss of consumer.Consumer returns goods, if third-party logistics is, it is necessary to undertake corresponding expense
With;And sellers then need to undertake return of goods cost:(1) seller needs the main return of goods used to audit mode for manual examination and verification side
Formula, this mode often has the following characteristics that:(a) take, return of goods excessive cycle;(b) labor intensive is, it is necessary to a large amount of customer service people
Member;(c) difficult judgment, because artificial judgment is often disputable.Therefore, return of goods rate is reduced, consumer, seller can be reduced
Loss.(2) setting loss, if produced problem with transporter, it is necessary to contact in transportation;If product quality itself is asked
Topic, seller needs to contact with manufacturer.Compared with consumer, sellers need to undertake more cost and risks.Reduction
Return of goods rate is most important for seller.
Data digging method is introduced into seller shopping at network and returns goods predict it is a kind of novel way:Network is returned goods by pin
Seller, transporter and consumer tripartite cooperate completion jointly, in this process, and return of goods platform produces a series of data, its
Include:(1) seller return of goods reason data;(2) data that transporter is produced in delivery and return process;(3) seller
The data such as product quality data, user's Shopping Behaviors custom that detection of returning goods is obtained.Return process is regarded as a "black box", only
The relation of input and output parameter is paid close attention to, sets up and testing needle is to the mathematical modeling of user's return of goods behavior, dug by data
Pick algorithm realizes seller shopping at network return of goods forecasting system.
The system that this patent is related to uses suitable data mining mould based on the magnanimity sales data that seller has been accumulated
Type Develop Data is analyzed, and obtains a seller shopping at network return of goods forecast model.When user buys certain part on shopping platform
During product, the forecast model is based on existing data, adds user's specific behavior pattern in itself, predicts that the user is directed to this part
The return of goods rate of commodity, it is to avoid the excessive economic loss of seller.On the other hand, add during this Shopping Behaviors and fructufy of user
Enter into sales data, to system future amendment, forecast model is further is prepared.
By using above-mentioned technology can cause seller network selling commodity via certain express delivery be shipped for certain user it
The return of goods rate of the preceding commodity of automatic Prediction to a certain extent.Realize the target of seller Automated condtrol marketing risk.
Most of current existing paper is related to the return of goods research of logistics, rather than express delivery research.Logistics has necessarily with express delivery
Difference, logistics is generally enterprises service, transports the goods of big volume, typically there is warehousing management;And express delivery is more
For individual service, it is relatively small to transport measurement of cargo, typically no warehousing management.And currently the research for reverse logistic is present
Following shortcoming:(1) all it is overall discussion, the Different Strategies under multiple dis-tribution model is not discussed in detail.(2) most literature is begged for
By when employ demonstration or simulation method, on the spot investigate the fact data supporting theory analysis.
The content of the invention
The technical problems to be solved by the invention are the deficiencies for background technology there is provided a kind of net based on seller
Network shopping return of goods forecasting system, it realizes the return of goods rate of certain buying behavior of automatic prediction client.
The present invention uses following technical scheme to solve above-mentioned technical problem
A kind of shopping at network return of goods forecasting system based on seller, includes shopping at network history data store module, number
According to integration module, data preprocessing module, data-mining module, human-computer interaction interface;
Wherein, shopping at network history data store module, for collecting and storing seller during shopping at network, transport
Side and the historical rudiment data of consumer;
Data integration module, for extracting required data from heterogeneous database;
Data preprocessing module, for being pre-processed to the result that data integration module is obtained;
Data-mining module, the result for being obtained to data preprocessing module carries out data mining, and then obtains system
Predict the outcome.
It is used as a kind of further preferred scheme of the shopping at network return of goods forecasting system based on seller of the present invention, network purchase
Thing history data store module includes sale shopping platform data memory module and express company's data memory module, the sale
Shopping platform data memory module is used to store seller and the interaction data of consumer, express company's data memory module
Purchase and the fast delivery data of the return of goods for storing seller and consumer.
It is used as a kind of further preferred scheme of the shopping at network return of goods forecasting system based on seller of the present invention, the number
It is used to obtain seller data, consumer data and fast delivery data according to integration module.
It is used as a kind of further preferred scheme of the shopping at network return of goods forecasting system based on seller of the present invention, the number
Data preprocess module includes data regularization module, data cleansing module, data transformation module;
Wherein, data regularization module, the reduction for obtaining data set is represented;
Data cleansing module, for carrying out data scrubbing:Complete, correct, consistent data message is stored in shopping at network
In history data store module;
Data transformation module, is applied to the form of data mining for converting the data into.
As a kind of further preferred scheme of the shopping at network return of goods forecasting system based on seller of the present invention, pass through Piao
The result that plain bayesian algorithm and Ensemble Learning Algorithms are obtained to data preprocessing module.
The present invention uses above technical scheme compared with prior art, with following technique effect:
Seller shopping at network return of goods forecasting system proposed by the present invention and its optimization method, can be achieved to this consumer
The prediction that certain shopping is returned goods;There is provided for seller and certain shopping results prejudged, for merchandise sales decision-making provide according to
According to realizing the global optimization of resource distribution to a certain extent.
Brief description of the drawings
Fig. 1 is the electronic business transaction return process figure that the system is related to;
Fig. 2 is the seller shopping at network return of goods prediction flow chart that the system is related to;
Fig. 3 is the NB Algorithm flow chart that the system is related to;
Fig. 4 is the integrated study optimization method flow chart that the system is related to.
Embodiment
Technical scheme is described in further detail below in conjunction with the accompanying drawings:
Embodiment one
As shown in figure 1, the present invention is based on hyundai electronicses shopping return process.Shopping at network be related to consumer, transporter,
Seller and manufacturer.Wherein, consumer, transporter and seller constitute main data source.Because current electric business is flat
Platform and express company lack unified information planning, the time of each Development of Management Information System and source are inconsistent, and use is opened
Send out platform, data structure and data base management system also different, cause separate between each system, information can not be exchanged
And fusion, gradually form " information island ".Need exist for using a kind of multi-source heterogeneous database data fusion method, realize three
The interaction of square information and shared there is provided a safe and reliable, high-quality Informatization Service.For further Develop Data digger
Provide safeguard.
As shown in Fig. 2 present invention is disclosed a kind of seller shopping at network return of goods forecasting system, to predict that certain is sold
The probability of the return of goods;It includes:Shopping at network history data store, data integration module, data preprocessing module, data mining mould
Block and decision support module.Each module is introduced in detail below.
Shopping at network history data store is a Distributed Heterogeneous Database environment, wherein mainly comprising two data
Storehouse:(1) sell in shopping platform data warehouse, the database and contain seller and the interaction data of consumer;(2) express delivery is public
The purchase for containing seller and consumer is taken charge of in data warehouse, the database and fast delivery data of returning goods.
Data integration module is mainly extracts required data from heterogeneous database, and they include:(1) number formulary is sold
According to;(2) consumer data;(3) fast delivery data.
The result that data preprocessing module is obtained for data integration module carries out the operation of three aspects, and they include:(1)
Hough transformation;(2) data cleansing;(3) data are converted.
Data-mining module is directed to the result Develop Data mining algorithm that data preprocessing module is obtained, wherein typical bag
Include NB Algorithm as shown in Figure 3 and Ensemble Learning Algorithms are as shown in Figure 4.
Decision support module on the basis of data mining there is provided the visibility solution of man-machine interaction, and for enterprise
CRM provide management level decision support.
As shown in figure 3, the seller shopping at network return of goods prediction algorithm that the present invention is used is NB Algorithm.Its
In, XiThe reason for being returned goods for seller, transporter and consumer influence.Although the return of goods are initiated by consumer, it is influenceed to move back
The factor of goods rate is main to be produced by three aspects:Consumer, seller, transporter.It is related to different heterogeneous database systems.
For consumer, the principal element of the return of goods is mainly listed below:(1) impulse purchases, such as businessman concentrate the pin that gives a discount
Sell activity etc.;(2) legal provisions are unconditionally returned goods in seven days, and return of goods cost is smaller;(3) self-operation platform in part is returned goods conveniently, and zero
Cost is returned goods;(4) in a organized way, premeditated malice return goods.These return of goods are likely to be centralization, it is also possible to be distributed
Cooperative mode.In addition, consumer returns goods also is influenceed by season, personal unpredictable other factorses.
For seller, the principal element of the return of goods is mainly listed below:(1) commercial quality problem;(2) businessman marks
There is problem in size, the commodity of purchase are bigger than normal or less than normal;(3) false propaganda of businessman, it is in kind not to be inconsistent with picture description;(4) business
The wrong goods of family's hair;
For transporter, mainly transport goods midway and occur:(1) loss of goods;(2) cargo damage;(3) logistics is matched somebody with somebody
Send slow etc..Wherein, commercial quality problem is completed by seller and manufacturer's cooperation.
Certainly, above-mentioned reason can't summarize all return of goods reasons completely.
Give some user and the return of goods rate of some commodity is bought in some time for C.Because simple pattra leaves algorithm assumes each
Characteristic condition is independent, in the present system, and both assuming to return goods, characteristic condition is only each other by the seller being related to, transporter and consumer
It is vertical, also assume that each characteristic condition that seller internal influence is returned goods is independent of one another.
Learnt by above-mentioned discussion, for all Xi、XjFor, there is Xi⊥Xj|C.Calculate the return of goods probability of certain shopping
Calculation formula is:
Wherein P (C) and P (Xi| C) existing data are calculated in database.
The seller shopping at network return of goods forecasting system of the present invention is described above, the present invention is disclosing the same of said system
When, further disclose the optimization method of said system;As shown in figure 4, methods described comprises the following steps:
The optimization method uses integrated learning approach.
Ballot method is used in this improved method.Assuming that prediction classification is { C1,C2, wherein C1Represent this purchase row of customer
For that can return goods, and C2Represent that this buying behavior of customer will not return goods.For any one forecast sample X, T is suppose there is in system
Individual learner h1~hT, typical learner includes NB Algorithm, decision Tree algorithms etc..It is assumed that the individual weak learners of T is pre-
It is (h respectively to survey result1(X),h2(X)...hT(X))。
Fig. 4 ballot method using relative majority vote method, i.e. T weak learners in the predicting the outcome of sample X, quantity
Most classification CiFor final class categories.If more than one classification obtains highest ticket, one conduct of random selection is most
Whole classification.
In summary, seller shopping at network return of goods forecasting system proposed by the present invention and its optimization method, can be achieved certainly
The dynamic return of goods probabilistic forecasting to certain shopping of some consumer;Corresponding data are provided for enterprise CRM to support.Enterprise can pass through
The sales situation of certain commodity is studied and judged in data analysis, increases or decreases the species of network selling goods.The entirety of enterprise efficiency
Optimization.
It is of the invention main by collection network shopping history data warehouse, extract sale shopping platform data warehouse and express delivery
Historical data in corporate data warehouse, it is pre- by data to obtain seller, consumer and the tripartite of express company data
Processing, application data method for digging obtains result, and providing data for business decision supports.The invention has:(1) solid number
Learn basis;(2) stable classification effectiveness;(3) parameter of estimation is seldom, less sensitive to missing data needed for;(4) algorithm is simpler
It is single.Optimized algorithm solves same problem using multiple learners, can significantly increase the generalization ability of learning system.Institute
The technological means taken is main in data mining phases, and it includes:Returned goods using NB Algorithm prediction shopping at network general
Rate;Optimization method uses integrated learning approach.
The present invention is not limited to above-mentioned embodiment, using the architecture identical or approximate with the above embodiment of the present invention
And algorithm, and other obtained design of hardware and software, within protection scope of the present invention.
Claims (5)
1. a kind of shopping at network return of goods forecasting system based on seller, it is characterised in that:Deposited comprising shopping at network historical data
Store up module, data integration module, data preprocessing module, data-mining module, human-computer interaction interface;
Wherein, shopping at network history data store module, for collect and store seller during shopping at network, transporter and
The historical rudiment data of consumer;
Data integration module, for extracting required data from heterogeneous database;
Data preprocessing module, for being pre-processed to the result that data integration module is obtained;
Data-mining module, the result for being obtained to data preprocessing module carries out data mining, and then obtains system prediction
As a result.
2. a kind of shopping at network return of goods forecasting system based on seller according to claim 1, it is characterised in that:Network
Shopping history data memory module includes sale shopping platform data memory module and express company's data memory module, the pin
Selling shopping platform data memory module is used to store seller and the interaction data of consumer, express company's data storage mould
Block is used to store seller and purchase and the fast delivery data of returning goods of consumer.
3. a kind of shopping at network return of goods forecasting system based on seller according to claim 1, it is characterised in that:It is described
Data integration module is used to obtain seller data, consumer data and fast delivery data.
4. a kind of shopping at network return of goods forecasting system based on seller according to claim 1, it is characterised in that:It is described
Data preprocessing module includes data regularization module, data cleansing module, data transformation module;
Wherein, data regularization module, the reduction for obtaining data set is represented;
Data cleansing module, for carrying out data scrubbing:Complete, correct, consistent data message is stored in shopping at network history
In data memory module;
Data transformation module, is applied to the form of data mining for converting the data into.
5. a kind of shopping at network return of goods forecasting system based on seller according to claim 1, it is characterised in that:Pass through
The result that NB Algorithm and Ensemble Learning Algorithms are obtained to data preprocessing module.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710334392.9A CN107274191A (en) | 2017-05-12 | 2017-05-12 | A kind of shopping at network return of goods forecasting system based on seller |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710334392.9A CN107274191A (en) | 2017-05-12 | 2017-05-12 | A kind of shopping at network return of goods forecasting system based on seller |
Publications (1)
Publication Number | Publication Date |
---|---|
CN107274191A true CN107274191A (en) | 2017-10-20 |
Family
ID=60074219
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201710334392.9A Pending CN107274191A (en) | 2017-05-12 | 2017-05-12 | A kind of shopping at network return of goods forecasting system based on seller |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN107274191A (en) |
Cited By (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108764532A (en) * | 2018-05-04 | 2018-11-06 | 四川斐讯信息技术有限公司 | A kind of logistics flux forecasting system and method based on router |
CN110009154A (en) * | 2019-04-03 | 2019-07-12 | 深圳威狮物流网络科技有限公司 | A kind of reimbursement prediction technique, device, terminal device and storage medium |
CN110874745A (en) * | 2018-08-24 | 2020-03-10 | 堆糖信息科技(上海)有限公司 | Bill return management system |
CN111008871A (en) * | 2019-12-10 | 2020-04-14 | 重庆锐云科技有限公司 | Real estate repurchase customer follow-up quantity calculation method, device and storage medium |
CN112596647A (en) * | 2020-12-21 | 2021-04-02 | 百度在线网络技术(北京)有限公司 | Method, apparatus, device, storage medium, and program for outputting information |
US11113741B2 (en) | 2018-11-04 | 2021-09-07 | International Business Machines Corporation | Arranging content on a user interface of a computing device |
US11164229B2 (en) | 2018-11-19 | 2021-11-02 | International Business Machines Corporation | Hypergraph structure and truncation method that reduces computer processor execution time in predicting product returns based on large scale data |
CN114445089A (en) * | 2022-01-20 | 2022-05-06 | 荃豆数字科技有限公司 | Method and device for pre-estimating after-sale service cost of traditional Chinese medicine decoction pieces and computer equipment |
CN116433145A (en) * | 2023-03-10 | 2023-07-14 | 广州手拉手互联网股份有限公司 | E-commerce data monitoring and order management method and system |
Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN105574599A (en) * | 2014-10-09 | 2016-05-11 | 阿里巴巴集团控股有限公司 | Method and apparatus for estimating sales return rate of order |
CN106127634A (en) * | 2016-06-20 | 2016-11-16 | 山东师范大学 | A kind of Forecasting The Scores method and system based on model-naive Bayesian |
US20170032400A1 (en) * | 2015-07-27 | 2017-02-02 | Truecar, Inc. | Vehicle data system for distribution of vehicle data in an online networked environment |
CN106504015A (en) * | 2016-10-17 | 2017-03-15 | 鞍钢集团矿业有限公司 | A kind of field supplier of enterprise of combination BP neural network recommends method |
-
2017
- 2017-05-12 CN CN201710334392.9A patent/CN107274191A/en active Pending
Patent Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN105574599A (en) * | 2014-10-09 | 2016-05-11 | 阿里巴巴集团控股有限公司 | Method and apparatus for estimating sales return rate of order |
US20170032400A1 (en) * | 2015-07-27 | 2017-02-02 | Truecar, Inc. | Vehicle data system for distribution of vehicle data in an online networked environment |
CN106127634A (en) * | 2016-06-20 | 2016-11-16 | 山东师范大学 | A kind of Forecasting The Scores method and system based on model-naive Bayesian |
CN106504015A (en) * | 2016-10-17 | 2017-03-15 | 鞍钢集团矿业有限公司 | A kind of field supplier of enterprise of combination BP neural network recommends method |
Non-Patent Citations (2)
Title |
---|
施彦: "《群体智能预测与优化》", 31 August 2012, 国防工业出版社 * |
王丹: "基于信息不对称的退货运费险的定价模型研究", 《中国优秀硕士学位论文全文数据库 经济与管理科学辑》 * |
Cited By (10)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108764532A (en) * | 2018-05-04 | 2018-11-06 | 四川斐讯信息技术有限公司 | A kind of logistics flux forecasting system and method based on router |
CN110874745A (en) * | 2018-08-24 | 2020-03-10 | 堆糖信息科技(上海)有限公司 | Bill return management system |
US11113741B2 (en) | 2018-11-04 | 2021-09-07 | International Business Machines Corporation | Arranging content on a user interface of a computing device |
US11164229B2 (en) | 2018-11-19 | 2021-11-02 | International Business Machines Corporation | Hypergraph structure and truncation method that reduces computer processor execution time in predicting product returns based on large scale data |
CN110009154A (en) * | 2019-04-03 | 2019-07-12 | 深圳威狮物流网络科技有限公司 | A kind of reimbursement prediction technique, device, terminal device and storage medium |
CN111008871A (en) * | 2019-12-10 | 2020-04-14 | 重庆锐云科技有限公司 | Real estate repurchase customer follow-up quantity calculation method, device and storage medium |
CN112596647A (en) * | 2020-12-21 | 2021-04-02 | 百度在线网络技术(北京)有限公司 | Method, apparatus, device, storage medium, and program for outputting information |
CN114445089A (en) * | 2022-01-20 | 2022-05-06 | 荃豆数字科技有限公司 | Method and device for pre-estimating after-sale service cost of traditional Chinese medicine decoction pieces and computer equipment |
CN116433145A (en) * | 2023-03-10 | 2023-07-14 | 广州手拉手互联网股份有限公司 | E-commerce data monitoring and order management method and system |
CN116433145B (en) * | 2023-03-10 | 2023-12-19 | 广州手拉手互联网股份有限公司 | E-commerce data monitoring and order management method and system |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN107274191A (en) | A kind of shopping at network return of goods forecasting system based on seller | |
Smith et al. | Neural networks in business: techniques and applications | |
Chen et al. | Logistics provider selection for omni-channel environment with fuzzy axiomatic design and extended regret theory | |
Jana et al. | Multi-item partial backlogging inventory models over random planninghorizon in random fuzzy environment | |
KR102578114B1 (en) | Computerized systems and methods for using artificial intelligence to optimize database parameters | |
Xu et al. | Data-driven decision and analytics of collection and delivery point location problems for online retailers | |
WO2020034044A1 (en) | System and method for predicting delivery parameters in an intermodal logistics network | |
CN107527451A (en) | Box for material circulation good selling method, device and box for material circulation | |
Gangurde et al. | Building prediction model using market basket analysis | |
Mamoudan et al. | Food products pricing theory with application of machine learning and game theory approach | |
CN115619571A (en) | Financing planning method, system and device | |
Dharshini et al. | Survey of machine learning and deep learning approaches on sales forecasting | |
Pal et al. | On optimal partially integrated production and marketing policy with variable demand under flexibility and reliability considerations via Genetic Algorithm | |
Yan et al. | Integrated data mining and TOPSIS entropy weight method to evaluate logistics supply and demand efficiency of a 3PL company | |
CN116228403A (en) | Personal bad asset valuation method and system based on machine learning algorithm | |
Kumar et al. | Big Mart Sales Prediction Using Machine Learning | |
Aktas | Big data applications in supply chain management | |
Turken et al. | Research on Creating a Data Warehouse Based on E-Commerce | |
CN109754265B (en) | Data processing method and device | |
Al-Basha | Forecasting Retail Sales Using Google Trends and Machine Learning | |
Li | Evaluation of Artificial Intelligence models and wireless network applications for enterprise sales management innovation under the new retail format | |
Akaydin | Benefits of Using Information Technology in Supply Chain Management | |
Indira et al. | Indian Agriculture Supply Chain Management using Blockchain Technology and CNN | |
Stanelytė | Inventory Optimization in Retail Network by Creating a Demand Prediction Model | |
Putra et al. | Descriptive And Predictive Analysis Of Mail Order Pharmacy |
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: 20171020 |
|
RJ01 | Rejection of invention patent application after publication |