CN109214587A - A kind of demand for commodity prediction based on three decisions divides storehouse planing method with logistics - Google Patents
A kind of demand for commodity prediction based on three decisions divides storehouse planing method with logistics Download PDFInfo
- Publication number
- CN109214587A CN109214587A CN201811133436.2A CN201811133436A CN109214587A CN 109214587 A CN109214587 A CN 109214587A CN 201811133436 A CN201811133436 A CN 201811133436A CN 109214587 A CN109214587 A CN 109214587A
- Authority
- CN
- China
- Prior art keywords
- commodity
- value
- feature
- prediction result
- window
- 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.)
- Withdrawn
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
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- 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
- G06Q10/08—Logistics, e.g. warehousing, loading or distribution; Inventory or stock management
- G06Q10/087—Inventory or stock management, e.g. order filling, procurement or balancing against orders
Landscapes
- Business, Economics & Management (AREA)
- Engineering & Computer Science (AREA)
- Economics (AREA)
- Strategic Management (AREA)
- Human Resources & Organizations (AREA)
- Marketing (AREA)
- Tourism & Hospitality (AREA)
- Development Economics (AREA)
- Theoretical Computer Science (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- General Physics & Mathematics (AREA)
- Entrepreneurship & Innovation (AREA)
- Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- Accounting & Taxation (AREA)
- Finance (AREA)
- Game Theory and Decision Science (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The present invention provides a kind of, and the demand for commodity prediction based on three decisions divides storehouse planing method with logistics, include the following steps: Q1, data prediction, Q2, feature construction, Q3, characteristic value selection, Q4, model selection, Q5, model prediction result are merged with regular prediction result, and fusion coefficients 0.75model+0.25rule the present invention is based on the prediction of the smart home demand for commodity of three decisions and divides storehouse planing method.It can effectively help smart home businessman that operation cost is greatly reduced, reduce timeliness of receiving, promote the experience of user, be more in line with the practical commercial scene of data volume rapid growth.
Description
Technical field
The present invention relates to big data analysis applied technical fields, are related in e-commerce, produce more particularly, to smart home
In product e-commerce, meets the prediction of electric business demand for commodity with logistics point storehouse and plan a kind of used commodity based on three decisions
Requirement forecasting and logistics divide storehouse planing method.
Background technique
With the fast development of science and technology, internet has brought various convenient services, and e-commerce is more next
More complicated, smart home is the embodiment of the instrumentation under the influence of internet, and smart home will be in family by technology of Internet of things
Various equipment (such as audio & video equipment, lighting system, curtain control, airconditioning control, security system, Digital Theater Systems, audio-visual clothes
Business device, shadow cabinet system, network home appliance etc.) it connects together, home wiring control, Lighting control, remote control using telephone, indoor and outdoor are provided
The multiple functions such as remote control, burglar alarm, environmental monitoring, HVAC control, infrared forwarding and programmable Timer control and means.With
Common household is compared, and smart home not only has traditional inhabitation function, has both building, network communication, information household appliances, equipment certainly
Dynamicization provides comprehensive information exchange function, and even various energy expenditures save fund.
For smart home E-commerce market, time limit and two key factors that price is that user considers, one
As in the case of, the promotion in time limit and the reduction of price are constantly present rigid outer limit, and therefore, it is necessary to seek in deeper time
Solution is sought, a point storehouse stock service refers to by smart home businessman according to sales forecast, is got ready the goods in advance to warehouse, realizes nearest
It is dispensed in delivery, area, smart home businessman also can easily possess the object of a line electric business of cost 10,000,000,000 easily without self-built warehouse
Fluid system realizes very fast be sent to.With adding fuel to the flames for various red-letter days and electric business platform, the various forms online shopping such as quick-fried money, special selling
Advertising campaign will become normality.If smart home businessman is delivered with traditional single storehouse mode, it is difficult to avoid transprovincially that outbox amount is big, object
It flows at high cost, the problems such as delivering and sending time long, customer complaint with charge free, therefore the product that standardization level is higher, inventory's depth is deeper
Board should consider that a point storehouse is got ready the goods in advance.
Promote whenever big, consumer is most concerned with when express delivery is sent to.Most effective method be by big data and
Algorithm allows cargo to be placed directly on the warehouse nearest from consumer；Businessman can be helped substantially to drop with the supply chain that big data drives
Low running cost promotes the experience of user, plays an important role to the improved efficiency of entire smart home electric business industry.High quality
Smart home demand for commodity prediction be supply chain management basis and core function.Realizing the demand for commodity prediction of high quality is
It is more stepped towards intelligentized supply platform chain direction further.Therefore how to realize more accurate requirement forecasting, make cargo direct
Be put into the warehouse nearest from consumer, at the same again can greatly optimizing management cost, be it is essential that being to be badly in need of solving
The problem of.
Three decision theories are Yao Yiyu in the rough set that studies for a long period of time, especially probability rough set and decision rough set mistake
Cheng Zhong, a kind of decision-making mode for meeting the practical cognitive ability of the mankind summarized and extract are a kind of new decision theories.Three
Branch decision thought is the semantic interpretation to three domains of rough set originally, and the positive domain representation of the positive corresponding rough set of rule, which determines, to be received；
The boundary domain representation that boundary rule corresponds to rough set is uncertain, and delay makes a decision；The negative domain of the negative corresponding rough set of rule indicates true
Fixed refusal.But with further going deep into for research, three decision theories have become the fusion of rough set theory and decision theory,
A kind of effective tactful and method is provided for the solution of challenge.Three decision theories are since proposition, just by many
The favor of person.
The theory is a kind of method that decision is carried out under the conditions of information is uncertain or incomplete.Yao gives related three
The formal definitions of branch decision problem, it is specific as follows.
Defining 1 and setting U is a nonempty finite The Analects of Confucius, and C is a limited conditions collection.Three decision problems are based on decision item
U is divided into three regions, is indicated respectively with POS, NEG and BND, successively referred to as positive domain by part collection C, negative domain and Boundary Region,
Meet the following conditions:
POS ∪ BND ∪ NEG=U
To positive domain, the object in negative domain and Boundary Region makes receiving respectively, refuses and does not promise to undertake decision.
Define 2: the nonempty finite sample set on given real number space, objective function f (x) is given, then neighborhood three
Decision is as follows:
(P) if f (x) >=α, x ∈ POS (X)
(B) if β < f (x) < α, x ∈ BND (X)
(N) if f (x)≤β, x ∈ NEG (X)
Three decision thoughts are applied in the prediction of smart home demand for commodity in point storehouse planning, fully considers and mends more costs
It can be that commodity demand volume accurately be predicted to future time section with few influence of the cost to objective function of benefit, it can be maximum
The reduction totle drilling cost of limit helps smart home businessman that operation cost is greatly reduced, and reduces timeliness of receiving, promotes the body of user
It tests, plays an important role to the improved efficiency of entire electric business industry.
Summary of the invention
Aiming at the problem that above-mentioned background technique is illustrated, it is an object of the present invention to provide a kind of commodity based on three decisions to need
Prediction and logistics point storehouse planing method are asked, existing smart home demand for commodity prediction and information efficiency in the planning of logistics point storehouse are solved
Problem low, at high cost can effectively help smart home businessman that operation cost is greatly reduced, and reduce timeliness of receiving, and promoted and used
The experience at family.
In order to achieve the above object, the invention provides the following technical scheme:
A kind of demand for commodity prediction based on three decisions divides storehouse planing method with logistics, includes the following steps:
Q1, data prediction obtain associated data files, including commodity granularity correlated characteristic dependent merchandise from database
User behavior characteristics, commodity and the region Fen Cang granularity correlated characteristic, the region Fen Cang benefit few to mend the relevant informations such as more costs right
Afterwards, by database because recent restocking or undercarriage cause the commodity of no sales volume record to carry out filling out 0 processing, to guarantee that data connect
Continuous property；
Q2, feature construction, using slip window sampling construction feature, select after each specific time point N days as one
Window, each commodity of the window, the total sales volume of warehouse inventory slide M window, to the specific time as label characteristic value
It is used as a window at N days before point, carries out feature construction, count the peaceful with value sum of N days various classification characteristic values before the window
Mean value avg counts commodity in the characteristic value of nearest N days numbers of deals, including maximum value, minimum value, standard deviation, counts its classification
Characteristic value of the id in nearest N days numbers of deals, including maximum value, minimum value, standard deviation and rank value and meet more accounting
Item formula cross feature value.
Q3, characteristic value selection select the feature of ranking topk using xgboost, calculate similarity, remove redundancy feature,
The associated eigenvalue for selecting construction feature in Q2, then goes to learn, most obtains the importance ranking of feature with xgboost model,
It chooses topk important feature and calculates similarity, weed out those unessential features；
Q4, model selection, the multiple regression models of training use Logic Regression Models (Logistic first
Regression, LR), Support vector regression model (Support Vector Regression, SVR), Random Forest model
(Random Forest, RF), gradient promotion decision tree (Gradient Boosting Decision Tree, GBRT),
The multiple models of XGBOOST method training；Be defined as follows secondly, defining α, β and f (x): it is more that f (x)=benefit lacks cost/benefit
Cost, α, β are to connect a threshold value to define different values according to α, β and f (x) value of definition three decisions pair of realization according to scene
Single model prediction result obtains model value model,
Be implemented as follows: if f (x) > α, then the prediction result of the commodity takes the maximum value in single model prediction result again
Multiplied by 1.1；If f (x) < β, the prediction result of the commodity takes the minimum value in single model prediction result multiplied by 0.9；If β≤f
(x) >=α, then the prediction result of the commodity takes the minimum value in single model prediction result；
Q5, model prediction result are merged with regular prediction result, fusion coefficients 0.75model+0.25rule,
Wherein rule rule learning is defined as: N days sales volumes are denoted as day1, day2 ... dayN respectively before prediction window, to each quotient
Product mend more costs if mending few cost and being greater than, are predicted as N*max (day1, day2 ... dayN), otherwise are predicted as N* min
(day1,day2,…dayN)。
The present invention is based on the prediction of the smart home demand for commodity of three decisions and divide storehouse planing method.Intelligence can effectively be helped
Operation cost is greatly reduced in energy household businessman, reduces timeliness of receiving, promotes the experience of user, be more in line with data volume rapid growth
Practical commercial scene.
Detailed description of the invention
Flow diagram Fig. 1 of the invention.
Specific embodiment
Below in conjunction with drawings and examples of the invention, technical solution of the present invention is clearly and completely described,
Obviously, described embodiments are only a part of the embodiments of the present invention, instead of all the embodiments.Based in the present invention
Embodiment, every other embodiment obtained by those of ordinary skill in the art without making creative efforts, all
Belong to the scope of protection of the invention.
According to Fig. 1, the present invention saves as embodiment, explanation with the e-commerce product and logistic warehouse of smart home product
A kind of demand for commodity prediction based on three decisions divides storehouse planing method with logistics, includes the following steps:
Q1, data preprocessing phase:
Related data information is obtained from related smart home product database, and multilist data are carried out after integrating conveniently
It is continuous to use, then carry out pretreatment operation, by data record because recent restocking or undercarriage lead to the quotient of no sales volume record
Product carry out filling out 0 processing, to guarantee data continuity；Secondly it chooses whether that operation is normalized as needed.Finally, according to wanting
Predicted time length divides data, will integrally be divided into training set, verifying collection and test set.Wherein data structure such as the following table 1,
Shown in table 2:
1 commodity granularity correlated characteristic of table
The cost of the benefit in 2 region commodity Fen Cang of table less, more than benefit
| Field | Type | Meaning | Example |
| item_id | bigint | Commodity ID | 333442 |
| store_code | String | Warehouse CODE | 1 |
| money_a | String | Commodity benefit mends more cost less | 10.44 |
| money_b | String | Commodity benefit mends more cost less | 20.88 |
Q2, feature construction:
Using slip window sampling construction feature, a window is used as within N days after choosing each specific time point, the window is each
A commodity, the total sales volume of warehouse inventory slide M window as characteristic value label, were used as one to N days before specific time point
A window carries out feature construction:
/ sum and avg of N days various classification features are counted 1/2/3/5/7/9/ before the window ..., the window is counted
First N days various classification characteristic values and value sum and average value avg, count commodity nearest N days numbers of deals characteristic value,
Including maximum value, minimum value, standard deviation, its classification id is counted in the characteristic value of nearest N days numbers of deals, including maximum value, most
Small value, standard deviation and rank value, accounting and meet multinomial cross feature value.
For example, being trained in selection 13 Time of Day section in December 10 to 2015 years July in 2015,11 windows, window are slided
Mouthful length selects progress feature extraction in 14 days two weeks, feature includes 1/2/3/5/7/9/ before the window .../14 days various classifications
Characteristic value and value sum and average value avg, count commodity in the characteristic value of nearest 14 days numbers of deals, including maximum value, minimum
Value, standard deviation count its classification id in the characteristic value of nearest 14 days numbers of deals, including maximum value, minimum value, standard deviation and
Rank value, accounting and meets multinomial cross feature value.Each length of window last day counts the sale in 14 days backward
Total number of packages summation is used as characteristic value label.
Q3, characteristic value selection:
Using the feature of xgboost selection ranking topk, similarity is calculated, removes redundancy feature.Select the correlation of building
Feature, then goes to learn with xgboost model, most obtains the importance ranking of feature, and finally according to this sequence, we are rejected
Falling those unessential features, so far mining process is completed.
Such as: 400 correlated characteristics are constructed, then xgboost model is selected to go to learn, then can export each feature
Important coefficient, we select tok40 here, that is, importance has been selected to come preceding 40 feature；However this 40 features may
There are redundancies.Therefore by calculating the similarity between feature, common similarity calculating method includes Pearson correlation coefficients, remaining
String similarity etc..Such as feature 1 and 10 similarity of feature are up to 0.999 in this 40 features, then may be selected removal feature 1 or
Feature 10 only retains one of feature, and in removal characteristic procedure, preferential removal is larger with the sum of the similarity of other features
Feature.For example, calculating the similarity between feature using Pearson correlation coefficients, feature 1 is similar to other 39 features
The sum of degree is 20, and the sum of feature 40 and the similarity of other 39 features are 18, then should remove feature 1.
That is specifically removed also with the relationship for considering itself and other features.
Q4, model selection:
First using the multiple models of the methods of LR, SVR, RF, GBRT, XGBOOST training；Secondly, defining α, β and f (x)
Be defined as follows: f (x)=benefit lacks the more costs of cost/benefit, and α, β are that even a threshold value defines different values according to scene.Finally
Single model prediction result is merged according to three decision models.It is implemented as follows: if f (x) > α, then the prediction of the commodity
As a result take the maximum value in single model prediction result multiplied by 1.1；If f (x) < β, the prediction result of the commodity takes single model pre-
The minimum value in result is surveyed multiplied by 0.9；If β≤f (x) >=α, the prediction result of the commodity is taken in single model prediction result
Minimum value.
Such as: define the few more costs of cost/benefit of f (x)=benefit；α=3；β=1；Commodity a, b, c LR, SVR, RF,
Predicted value is as shown in table 3 under the models such as GBRT, XGBOOST:
Each model predication value of table 3
| Commodity | Position in storehouse | LR | SVR | RF | GBRT | XGBOOST |
| a | 0001 | 20 | 45 | 56 | 10 | 30 |
| b | 0002 | 30 | 45 | 54 | 100 | 10 |
| c | 0003 | 40 | 60 | 70 | 20 | 10 |
If it is 20 yuan that commodity a, which mends more costs, mending few cost is 30 yuan, then f (x)=1.5, then the commodity are in 0001 warehouse
Inventory forecasts end value be 10；
If it is 10 yuan that commodity b, which mends more costs, mending few cost is 100 yuan, then f (x)=5, then the commodity are in 0002 warehouse
Prediction result value be 100*1.1=110；
If it is 80 yuan that commodity c, which mends more costs, mending few cost is 40 yuan, then f (x)=0.5, then the commodity are in 0003 warehouse
Prediction result value be 10*0.9=9
Q5, model prediction result are merged with regular prediction result:
N days sales volumes are denoted as day1, day2 ... dayN respectively before prediction window, to each commodity, if it is big to mend few cost
In mending more costs, then it is predicted as N*max (day1, day2 ... dayN), otherwise is predicted as N*min (day1, day2 ... dayN)；
Such as: the sales volume of prediction window the last fortnight is denoted as sale1, sale2 respectively, to each (commodity, position in storehouse), if mended
Few cost, which is greater than, mends more costs, then is predicted as 2* max (sale1, sale2), otherwise is predicted as 2*min (sale1, sale2).
Fusion forecasting is as a result, model prediction result is merged with regular prediction result, fusion coefficients 0.75model
+0.25rule；Model Fusion result is M1, is then merged with rule, fusion results M2.The fused model M 2,
It is exactly a rule set, can be used for the prediction of smart home demand for commodity, is i.e. M2 is the prediction model of final output.Utilize model
M2, according to the historical data (as shown in table 1, table 2) of different smart home products, future can be predicted, and they are required in warehouse
Quantity in stock (as shown in table 3).It compares for table 3, table 3 is the output of single model as a result, M2 is multi-model and rule
Fusion results, effect can be more preferably.
The above description is merely a specific embodiment, but scope of protection of the present invention is not limited thereto, any
Those familiar with the art in the technical scope disclosed by the present invention, can easily think of the change or the replacement, and should all contain
Lid is within protection scope of the present invention.Therefore, the protection scope of the present invention shall be subject to the protection scope of the claims.
Claims (1)
1. a kind of demand for commodity prediction based on three decisions divides storehouse planing method with logistics, it is characterised in that:, including walk as follows
It is rapid:
Q1, data prediction obtain associated data files, including commodity granularity correlated characteristic dependent merchandise user from database
Then behavioural characteristic, commodity and the region Fen Cang granularity correlated characteristic, mending for the region Fen Cang mend the relevant informations such as more costs less, will
Because recent restocking or undercarriage cause the commodity of no sales volume record to carry out filling out 0 processing in database, to guarantee data continuity；
Q2, feature construction, using slip window sampling construction feature, select after each specific time point N days as a window,
The each commodity of the window, the total sales volume of warehouse inventory slide M window, to N before specific time point as label characteristic value
It is used as a window, carries out feature construction, count N days various classification characteristic values before the window with value sum and average value
Avg counts commodity in the characteristic value of nearest N days numbers of deals, including maximum value, minimum value, standard deviation, counts its classification id and exist
The characteristic value of N days numbers of deals recently, including maximum value, minimum value, standard deviation and rank value and meet multinomial at accounting
Cross feature value；
Q3, characteristic value selection select the feature of ranking topk using xgboost, calculate similarity, remove redundancy feature, selection
The associated eigenvalue of construction feature in Q2, then goes to learn with xgboost model, most obtains the importance ranking of feature, chooses
Topk important feature calculates similarity, weeds out those unessential features；
Q4, model selection, the multiple regression models of training, first using the multiple moulds of LR, SVR, RF, GBRT, XGBOOST method training
Type；Be defined as follows secondly, defining α, β and f (x): f (x)=benefits lack the more costs of cost/benefit, α, β be a threshold value of company according to
Scene defines different values and realizes that three decisions to single model prediction result, obtain mould according to α, β and f (x) value of definition
Offset model,
Be implemented as follows: if f (x) > α, then the prediction result of the commodity take the maximum value in single model prediction result multiplied by
1.1；If f (x) < β, the prediction result of the commodity takes the minimum value in single model prediction result multiplied by 0.9；If β≤f (x)
>=α, then the prediction result of the commodity takes the minimum value in single model prediction result；
Q5, model prediction result are merged with regular prediction result, fusion coefficients 0.75model+0.25rule, wherein
Rule rule learning is defined as: N days sales volumes are denoted as day1, day2 ... dayN respectively before prediction window, to each commodity, such as
Fruit, which mends few cost and is greater than, mends more costs, then is predicted as N*max (day1, day2 ... dayN), on the contrary be predicted as N*min (day1,
day2,…dayN)。
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811133436.2A CN109214587A (en) | 2018-09-27 | 2018-09-27 | A kind of demand for commodity prediction based on three decisions divides storehouse planing method with logistics |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811133436.2A CN109214587A (en) | 2018-09-27 | 2018-09-27 | A kind of demand for commodity prediction based on three decisions divides storehouse planing method with logistics |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109214587A true CN109214587A (en) | 2019-01-15 |
Family
ID=64981803
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811133436.2A Withdrawn CN109214587A (en) | 2018-09-27 | 2018-09-27 | A kind of demand for commodity prediction based on three decisions divides storehouse planing method with logistics |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109214587A (en) |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110598798A (en) * | 2019-09-20 | 2019-12-20 | 胡燕祝 | Data classification method based on VFDT-Boosting-3WD |
| CN111856954A (en) * | 2020-07-20 | 2020-10-30 | 桂林电子科技大学 | Smart home data completion method based on combination of rough set theory and rules |
| CN112184304A (en) * | 2020-09-25 | 2021-01-05 | 中国建设银行股份有限公司 | Method, system, server and storage medium for assisting decision |
| CN113327131A (en) * | 2021-06-03 | 2021-08-31 | 太原理工大学 | Click rate estimation model for feature interactive selection based on three-branch decision theory |
| CN113673866A (en) * | 2021-08-20 | 2021-11-19 | 上海寻梦信息技术有限公司 | Crop decision method, model training method and related equipment |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20160350703A1 (en) * | 2015-05-27 | 2016-12-01 | Mariella Labels Oy | Electronic price, inventory management and label system |
| CN106599935A (en) * | 2016-12-29 | 2017-04-26 | 重庆邮电大学 | Three-decision unbalanced data oversampling method based on Spark big data platform |
| WO2017163278A1 (en) * | 2016-03-25 | 2017-09-28 | 日本電気株式会社 | Product demand forecasting system, product demand forecasting method, and product demand forecasting program |
| CN107909433A (en) * | 2017-11-14 | 2018-04-13 | 重庆邮电大学 | A kind of Method of Commodity Recommendation based on big data mobile e-business |
| CN108320171A (en) * | 2017-01-17 | 2018-07-24 | 北京京东尚科信息技术有限公司 | Hot item prediction technique, system and device |
-
2018
- 2018-09-27 CN CN201811133436.2A patent/CN109214587A/en not_active Withdrawn
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20160350703A1 (en) * | 2015-05-27 | 2016-12-01 | Mariella Labels Oy | Electronic price, inventory management and label system |
| WO2017163278A1 (en) * | 2016-03-25 | 2017-09-28 | 日本電気株式会社 | Product demand forecasting system, product demand forecasting method, and product demand forecasting program |
| CN106599935A (en) * | 2016-12-29 | 2017-04-26 | 重庆邮电大学 | Three-decision unbalanced data oversampling method based on Spark big data platform |
| CN108320171A (en) * | 2017-01-17 | 2018-07-24 | 北京京东尚科信息技术有限公司 | Hot item prediction technique, system and device |
| CN107909433A (en) * | 2017-11-14 | 2018-04-13 | 重庆邮电大学 | A kind of Method of Commodity Recommendation based on big data mobile e-business |
Non-Patent Citations (3)
| Title |
|---|
| LIMEIYANG: "菜鸟-需求预测与分仓规划解决", 《HTTPS://GITHUB.COM/LIMEIYANG/CAINIAO》 * |
| 朱振峰 等: ""基于GBDT的商品分配层次化预测模型"", 《北京交通大学学报》 * |
| 菜鸟网络: "菜鸟-需求预测与分仓规划：赛题与数据", 《HTTPS://TIANCHI.ALIYUN.COM/COMPETITION/ENTRANCE/231530/INFORMATION?FROM=OLDURL》 * |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110598798A (en) * | 2019-09-20 | 2019-12-20 | 胡燕祝 | Data classification method based on VFDT-Boosting-3WD |
| CN111856954A (en) * | 2020-07-20 | 2020-10-30 | 桂林电子科技大学 | Smart home data completion method based on combination of rough set theory and rules |
| CN111856954B (en) * | 2020-07-20 | 2022-08-02 | 桂林电子科技大学 | Smart home data completion method based on combination of rough set theory and rules |
| CN112184304A (en) * | 2020-09-25 | 2021-01-05 | 中国建设银行股份有限公司 | Method, system, server and storage medium for assisting decision |
| CN113327131A (en) * | 2021-06-03 | 2021-08-31 | 太原理工大学 | Click rate estimation model for feature interactive selection based on three-branch decision theory |
| CN113673866A (en) * | 2021-08-20 | 2021-11-19 | 上海寻梦信息技术有限公司 | Crop decision method, model training method and related equipment |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109214587A (en) | A kind of demand for commodity prediction based on three decisions divides storehouse planing method with logistics | |
| CN109325808A (en) | Demand for commodity prediction based on Spark big data platform divides storehouse planing method with logistics | |
| CN105303444A (en) | Automatic adaption system for financial products | |
| CN104866474A (en) | Personalized data searching method and device | |
| CN109300039A (en) | The method and system of intellectual product recommendation are carried out based on artificial intelligence and big data | |
| Tanaka | A sales forecasting model for new-released and nonlinear sales trend products | |
| Modrák et al. | Impacts of RFID implementation on cost structure in networked manufacturing | |
| Zhu et al. | Investigating remanufacturing competition with yield uncertainty on market share, profit, and consumer surplus | |
| Behera et al. | Grid search optimization (GSO) based future sales prediction for big mart | |
| Saha et al. | Multi-item fuzzy-stochastic supply chain models for long-term contracts with a profit sharing scheme | |
| Kumar et al. | Multi-objective linear fractional inventory model of multi-products with price-dependant demand rate in fuzzy environment | |
| Alonso-Garcia et al. | Omnichannel Management in a B2B context: Concept, research agenda and bibliometric review | |
| Haq et al. | Analysis of agile supply chain enablers for Indian food processing industries using analytical hierarchy process | |
| Alizadeh et al. | Suitable delivery system in small e-commerce companies | |
| Apichottanakul et al. | Customer behaviour analysis based on buying-data sparsity for multi-category products in pork industry: A hybrid approach | |
| Andrade et al. | Disaggregated retail forecasting: A gradient boosting approach | |
| CN111353794A (en) | Data processing method, supply chain scheduling method and device | |
| CN110490682B (en) | Method and device for analyzing commodity attributes | |
| CN108629656B (en) | Intelligent shop pushing system and method based on mobile terminal positioning | |
| CN111127072A (en) | Multi-stage real-time prediction method for new product requirements | |
| US20210073840A1 (en) | Multi-layered system for heterogeneous pricing decisions by continuously learning market and hotel dynamics | |
| CN111768139B (en) | Stock processing method, apparatus, device and storage medium | |
| CN110533206A (en) | The method and apparatus for determining restocking opportunity | |
| Ishigaki et al. | Computational customer behavior modeling for knowledge management with an automatic categorization using retail service's datasets | |
| Alfawaer | Design of a forecasting Inventory Classification Model for ABC Analysis |
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 | ||
| TA01 | Transfer of patent application right |
Effective date of registration: 20190415 Address after: 400000 Chongqing Nanan District Photoelectric Road 26 10 7-1 Applicant after: Shu Haidong Address before: 400010 9 buildings 13-8, 168 Caiyuan Road, Yuzhong District, Chongqing Applicant before: Chongqing Zhiwanjia Technology Co., Ltd. |
|
| TA01 | Transfer of patent application right | ||
| WW01 | Invention patent application withdrawn after publication |
Application publication date: 20190115 |
|
| WW01 | Invention patent application withdrawn after publication |