CN107346502A - A kind of iteration product marketing forecast method based on big data - Google Patents
A kind of iteration product marketing forecast method based on big data Download PDFInfo
- Publication number
- CN107346502A CN107346502A CN201710737231.4A CN201710737231A CN107346502A CN 107346502 A CN107346502 A CN 107346502A CN 201710737231 A CN201710737231 A CN 201710737231A CN 107346502 A CN107346502 A CN 107346502A
- Authority
- CN
- China
- Prior art keywords
- data
- module
- prediction
- model algorithm
- 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
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
- G06Q30/0201—Market modelling; Market analysis; Collecting market data
- G06Q30/0202—Market predictions or forecasting for commercial activities
Abstract
The invention discloses a kind of iteration product marketing forecast method based on big data, including data processing module, model algorithm module and prediction output visualize module, the data processing module is used for each operation system data of the bottom, third party website data and part manual data introduce mysql database purchases and propose that data demand carries out ETL work according to the model of model algorithm module, model algorithm module is used to make modeling work according to the data being already prepared to and obtain final mask, the final mask finds law forecasting future sales volume by learning, the prediction output visualizes module for obtaining the prediction data progress visualized graphs displaying of model algorithm module output and supporting product type and the monthly prediction of the product type.The present invention improves the predictablity rate of iteration product, instructs supply chain high-efficiency operation, improves customer satisfaction with services, product is timely and effectively supplied market, reduces stock and improves inventory turnover ratio, while avoids the out of stock appearance of product.
Description
Technical field
The present invention relates to big data applied technical field, more particularly to a kind of iteration product marketing forecast based on big data
Method.
Background technology
With the continuous development of big data, solve the problems, such as that supply chain is more and more using big data at present, made in China
2025 proposition, the proposition of industrial 4.0 intelligence manufactures, all it is intelligent solution supply chain, sale is the source of supply chain, first
First big data technology is used to solve sales forecast, (enterprise marketing prediction is substantially at present so as to substitute artificial subjectivity to estimate
Expert assesses, and is rule of thumb carried out with history with ring ratio data), the particularity of wherein iteration product is also to be difficult to use certainly at present
Body data solve.Iteration household appliances refer to：The new household appliances model of product line substitutes old household appliances model, core work(
Can be consistent, performance or other factors etc. have certain lifting with meet to improve market the needs of, iteration product does not have when releasing market
Itself historic sales data.Sales forecast core has three types of technology：Expert's assessment, time series analysis, machine learning；Expert comments
Estimate and belong to subjective forecast, human factor, accuracy rate is unstable；Time series analysis and machine learning are based on algorithm model
Computer big data calculate, the objective prediction accurate stable of data, premise needs itself substantial amounts of historical data to carry out model training.
The content of the invention
Part in view of the shortcomings of the prior art, it is an object of the invention to provide a kind of iteration production based on big data
Product sales forecasting method, in the case where not influenceing historical product sale, utilize big data technological prediction iteration type product
Sales volume is estimated, and is reached new old product and is seamlessly transitted, the buying of product factory and production quantity precision.
The purpose of the present invention is achieved through the following technical solutions：
A kind of iteration product marketing forecast method based on big data, including data processing module, model algorithm module and
Prediction output visualizes module, and the data processing module is used for each operation system data of the bottom, third party website number
According to and part manual data introduce mysql database purchases and according to model algorithm module model propose data demand carry out
ETL works, and model algorithm module is used to make modeling work according to the data that are already prepared to and obtain final mask, it is described most
Final cast finds law forecasting future sales volume by learning, and the prediction output visualizes module and is used to obtain model algorithm
The prediction data of module output carries out visualized graphs displaying and supports product type and the monthly prediction of the product type；Its side
Method step is as follows：
A, the data handling procedure of data processing module：
A1, each operation system are entered in mysql databases by script interface；Third party website data pass through java programs
Form reads and write in mysql databases；State Statistics Bureau's industry data customizes crawl page info simultaneously by crawler technology
The page info got is write in mysql databases；
The data demand that A2, data processing module are proposed according to model algorithm module is directed to the number in mysql databases
According to ETL work is carried out, result data continues to be stored in mysql databases to be used for model algorithm module；
B, prediction output visualizes module and visualized for obtaining the prediction data of model algorithm module output
Figure shows and supports product type and the monthly prediction of the product type, the prediction data result of model algorithm module are stored in
Data are read in mysql databases and from mysql databases and carry out Visual Chart and trend displaying.
A kind of iteration product marketing forecast method based on big data, specific method of the invention are as follows：
The first step, data prepare：Each operation system is entered in mysql databases by script interface；Third party's data
Excel is read and write in mysql databases by java program forms；State Statistics Bureau's industry data grasps at page by customization
The mode of face information reptile is obtained in write-in mysql databases.
Second step, data processing：Data demand is proposed by model group, ETL works are carried out for the data in mysql databases
Make, result data continues to be stored in database to be used for model algorithm.
3rd step, model algorithm
1., index system establish：Index system content foundation to iteration new product model includes：New iteration product rule
Draw, match and associate with historical product system；Data are investigated, with marketing center, branch company, business department, client；Operation system data are adjusted
Grind；Data target combs, classification；According to Mass adjust- ment data target proportion；Index system is established, carries out model training, according to
As a result index proportion, optimizing index system are adjusted.Index system content includes：The data classification related to sale, including production and marketing
Deposit：Sales histories data, inventory history data, production production capacity historical data, inventory turnover ratio etc.；The number relevant with cost price
According to classification, including price data, cost data etc.；Consumer's related data, including consumer behaviour：Navigation patterns data, consult
Ask behavioral data, collection behavioral data, shopping cart behavioral data, lower single behavioral data, payment behavior data, user's evaluation number
According to, usage behavior data etc.；Macroscopic Factors relevant classification, including population structure data, industry market data, economic level, state
Family's policy data etc.；Internal operation relevant classification, including marketing activity data, client promote mainly day, client's shop-establishment celebration day, festivals or holidays work
Dynamic data etc.；Wherein sell related data and the data of consumer behaviour aggregation of data iteration historical product are predicted, it is new and old
The product iteration transitional period is analyzed, the comprehensive Sale Forecasting Model index system established as iteration new product.
2., model learning：Model obtains sales data and third party's data, industry data, system from mysql databases
Parameter, and result is inputted in mysql databases.
3., model evaluation analysis：By being continued to optimize to index, the continuous training to model, commented according to prediction result
The sales forecast algorithm model that valency analysis selection is reliably adapted to.
4th step, prediction output visualize：The result of model prediction is stored in mysql databases, it is necessary to show
The web or other-end system of result data read data from mysql databases and carry out Visual Chart and trend displaying.
The present invention compared with the prior art, has advantages below and beneficial effect：
The present invention improves the predictablity rate of iteration product, instructs supply chain high-efficiency operation, improves customer satisfaction with services,
Product is timely and effectively supplied market, reduce stock and improve inventory turnover ratio, while avoid the out of stock appearance of product.
Brief description of the drawings
Fig. 1 is the structural representation of the present invention；
Fig. 2 new product model forecast model index systems of the present invention establish schematic diagram；
The iteration product marketing forecast result of Fig. 3 present invention.
Embodiment
The present invention is described in further detail with reference to embodiment：
Embodiment one
A kind of iteration product marketing forecast method based on big data, including data processing module, model algorithm module and
Prediction output visualizes module, and the data processing module is used for each operation system data of the bottom, third party website number
According to and part manual data introduce mysql database purchases and according to model algorithm module model propose data demand carry out
ETL works, and model algorithm module is used to make modeling work according to the data that are already prepared to and obtain final mask, it is described most
Final cast finds law forecasting future sales volume by learning, and the prediction output visualizes module and is used to obtain model algorithm
The prediction data of module output carries out visualized graphs displaying and supports product type and the monthly prediction of the product type；Its side
Method step is as follows：
A, the data handling procedure of data processing module：
A1, each operation system are entered in mysql databases by script interface；Third party website data pass through java programs
Form reads and write in mysql databases；State Statistics Bureau's industry data customizes crawl page info simultaneously by crawler technology
The page info got is write in mysql databases；
The data demand that A2, data processing module are proposed according to model algorithm module is directed to the number in mysql databases
According to ETL work is carried out, result data continues to be stored in mysql databases to be used for model algorithm module；
B, prediction output visualizes module and visualized for obtaining the prediction data of model algorithm module output
Figure shows and supports product type and the monthly prediction of the product type, the prediction data result of model algorithm module are stored in
Data are read in mysql databases and from mysql databases and carry out Visual Chart and trend displaying.
Embodiment two
As shown in FIG. 1 to 3, a kind of iteration product marketing forecast method based on big data, including data processing module,
Model algorithm module and prediction output visualize module, and the data processing module is used for each operation system number of the bottom
Mysql database purchases are introduced according to, third party website data and part manual data and are carried according to the model of model algorithm module
Go out data demand and carry out ETL work, model algorithm module is used to make modeling work according to the data being already prepared to and obtain
Final mask, the final mask find law forecasting future sales volume by learning, and the prediction output visualizes module
Prediction data for obtaining model algorithm module output carries out visualized graphs displaying and supports product type and the product type
Number monthly prediction；Its method and step is as follows：
Step A, prediction target is determined：It is determined that prediction object is the sales forecast of household electrical appliances iteration product；Predetermined period is monthly,
M+3；Model needs precision high, and possesses certain interpretation；Wherein forecast demand investigation includes new iteration product type rule
Draw, match and associate with historical product system；Data are investigated, with marketing center, branch company, business department, client；Operation system data are adjusted
Grind；To ensure prediction effect, predict that the needs of object data set a little filter conditions, this phase rules：A upper product type
History sales volume data moon sales volume of at least 8 months in complete 12 months months in past is more than 10, and identical product system iteration
At least above the 1 month transitional time (i.e. the sales data of the first two iteration product type is simultaneously greater than 10).
Step B, data processing：
Step B1, retail data, history model iteration mistake under data-interface access system inside production and marketing deposit data, line are prepared
Cross analyze data deposit mysql databases；Reptile obtains outside macro-data, consumer behaviour data, and extra day destiny
According to, deposit mysql databases such as longitude and latitude degrees of data, festivals or holidays data；Data excel is introduced directly into mysql databases and (also known as counted
According to storehouse mysql)；
Step B2, the exploration of data is to data inspection and understanding, for example quantity in stock is that negative value, number of weeks are more than 8 etc.；To knot
The analysis of fruit variable, including sale and inventory distribution, sale size trend, sale are the same as ring periodicity etc.；To predictive variable
Analysis, including Variable Selection, multicollinearity, correlation；
Step B3, data prediction：
Step B31, in order to ensure different indexs have comparativity while can remove the influence of extremum, in data analysis
Before, it usually needs a pair index relevant with sales volume is standardized (normalization), conventional standardized method
Have following two：
Min-max standardizes (min-max normalization)
It is the linear change to initial data, falls result as follows in [0,100] section, transfer function：
Wherein max is the maximum of sample data, and min is the minimum value of sample data.
Z-score standardizes (z-score normalization)
Treated data fit normal distribution, i.e. average are 0, standard deviation 1, and its conversion function is：
Wherein it is the average of all sample datas, for the standard deviation of all sample datas.
Step B32, missing values are handled:The initial data of Method for Sales Forecast is all with time correlation, has tandem, category
In time series, take the neighbouring interpolation related to time series to carry out interpolation to the missing Value Data of Method for Sales Forecast, that is, use
Value that missing values close on replaces missing values.
Step C, index feature selects, and establishes index system：
Step C1, feature selection approach:Red pond information criterion (Akaike information criterion, AIC) is
A kind of standard of measure statistical models fitting Optimality, it is built upon on the conceptual foundation of entropy, can weigh estimation model
The Optimality of complexity and this models fitting data, AIC calculation formula are:
Wherein ln (L) is the maximum likelihood ratio of subset A drags, and k is subset A variable number, and n is independent variable sum.
Bayesian information criterion (Bayesian information criterion, BIC) be under incomplete information, it is right
The unknown state in part is estimated with subjective probability, and then probability of happening is modified with Bayesian formula, finally recycles the phase
Prestige value and amendment probability make optimizing decision, and BIC calculation formula is：
Wherein ln (L) is the maximum likelihood ratio of subset B drags, and k is subset B variable number, and n is the total of all independents variable
Number.
Feature selection approach：Mechanism is evaluated by subset of AIC/BIC information criterions, with sweep forward, successive Regression (repeatedly
Iteration, each iteration, which is only done, once to be returned) subset search mechanism is characterized, k (k are filtered out from n feature<N) individual feature.
Step C2, feature selecting flow
Given characteristic set { X1, X2..., Xn, the flow of feature selecting is specific as follows：
Using the model not comprising any variable as starting point, each feature is regarded as a candidate subset, it is single to this n candidate
Character subset, by building regression model with Y, compare AIC/BIC values and evaluated, it is assumed that { X2Optimal, then by { X2Conduct
The selected collection of the first round；
A feature is added in last round of selected concentration, forms the candidate subset for including two features, it is assumed that in this n-1
{ X in the individual character subset of candidate two2, X4Optimal, and it is better than { X2, then by { X2, X4Selected collection as epicycle；
The rest may be inferred, adds feature one by one, and selected collection is selected by wheel；
It is assumed that when kth+1 is taken turns, optimal candidate (k+1) character subset is not so good as last round of selected collection, then stops generation
Candidate subset, and using last round of selected k characteristic sets as feature selecting result.
Step D, Sale Forecasting Model is established, learnt, evaluation analysis：
Mainly relevant with the time, this patent mainly selects to be trained using time series as main models algorithm and in advance
Survey.
Hierachical Time Series Methods：After Attribute decomposition (disaggregate), have hierarchical structure when
Between sequence.
Or it is designated as yt=SyK, t
Wherein, ytReferring to the variable of all observation compositions in t, level, S refers to summation matrix as defined above,
Refer to yK,tThe variable of all observations composition of the bottom in t, level.
In Hierachical Time Series Forecasting Methods, this project preferably selects top-down methods.Top-down methods
Refer to, be primarily based on top " Total " sequence of Hierachical time serieses, generation base prediction (base
Forecasts), it is successively then decomposed to (diaggregate), successively predicted.Here it is a proportion set to make, the proportion set
(revised is predicted in the revision for each sequence for determining how the base prediction of " Total " sequence distributing to hierarchical structure bottom
forecasts).Once generating level forecasts, then it can carry out the pre- of remainder in generation layer time structure using summation matrix
Survey.Pay attention to, for top-down methods, top revision prediction is equal to top base and predicted, i.e.,
The advantage of Top-down methods is dependable with function.Due to based on the higher of Hierachical time serieses
Level sequence is modeled and generated prediction, and in general, prediction result is more reliable；And for low enumeration data, Top-
Down methods are especially useful.On the other hand, inferior position is can not to catch and utilize single sequence signature.
Most common historical proportion of the top-down methods based on data, give proportion set.Most common two methods are such as
Under：
Averaged historical ratio (Average historical proportions)
For j=1 ..., nK, each ratio pj, reflect in t=1 the ..., T phases, relative to " Total " sequences yt, bottom
Sequence of layer yJ, tHistory proportion is averaged.
The average ratio of history (Proportions of the historacal averages)
For j=1 ..., nK, each ratio pj, capture in t=1 the ..., T phases, relative to the y of " Total " sequencet
History average, bottom sequences yJ, tRatio shared by history average.
Step E, prediction result visualizes, including sales forecast value and the displaying of sales forecast trend.Web terminals, app
Or large-size screen monitors displaying.
The foregoing is merely illustrative of the preferred embodiments of the present invention, is not intended to limit the invention, all essences in the present invention
All any modification, equivalent and improvement made within refreshing and principle etc., should be included in the scope of the protection.
Claims (1)
- A kind of 1. iteration product marketing forecast method based on big data, it is characterised in that：Calculated including data processing module, model Method module and prediction output visualize module, and the data processing module is used for each operation system data of the bottom, the 3rd Square website data and part manual data introduce mysql database purchases and propose that data will according to the model of model algorithm module To ask and carry out ETL work, model algorithm module is used to make modeling work according to the data being already prepared to and obtain final mask, The final mask finds law forecasting future sales volume by learning, and the prediction output visualizes module and is used to obtain mould The prediction data of type algoritic module output carries out visualized graphs displaying and supports the monthly pre- of product type and the product type Survey；Its method and step is as follows：A, the data handling procedure of data processing module：A1, each operation system are entered in mysql databases by script interface；Third party website data pass through java program forms Read and write in mysql databases；State Statistics Bureau's industry data customizes crawl page info by crawler technology and will obtained In the page info write-in mysql databases got；The data that the data demand that A2, data processing module are proposed according to model algorithm module is directed in mysql databases are entered Row ETL is worked, and result data continues to be stored in mysql databases to be used for model algorithm module；B, prediction output visualizes the prediction data progress visualized graphs that module is used to obtain model algorithm module output Show and support product type and the monthly prediction of the product type, the prediction data result of model algorithm module are stored in Data are read in mysql databases and from mysql databases and carry out Visual Chart and trend displaying.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710737231.4A CN107346502A (en) | 2017-08-24 | 2017-08-24 | A kind of iteration product marketing forecast method based on big data |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710737231.4A CN107346502A (en) | 2017-08-24 | 2017-08-24 | A kind of iteration product marketing forecast method based on big data |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN107346502A true CN107346502A (en) | 2017-11-14 |
Family
ID=60257531
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710737231.4A Pending CN107346502A (en) | 2017-08-24 | 2017-08-24 | A kind of iteration product marketing forecast method based on big data |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107346502A (en) |
Cited By (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107967624A (en) * | 2017-11-24 | 2018-04-27 | 四川长虹电器股份有限公司 | A kind of evaluation method of business activity Sale Forecasting Model |
| CN108182595A (en) * | 2017-12-19 | 2018-06-19 | 山东浪潮云服务信息科技有限公司 | A kind of formulation migration efficiency method and device |
| CN108446771A (en) * | 2018-04-02 | 2018-08-24 | 四川长虹电器股份有限公司 | A method of preventing Sale Forecasting Model over-fitting |
| WO2018170595A1 (en) * | 2017-03-23 | 2018-09-27 | Rubikloud Technologies Inc. | Method and system for generation of adjustable automated forecasts for a promotion |
| CN109214601A (en) * | 2018-10-31 | 2019-01-15 | 四川长虹电器股份有限公司 | Household electric appliances big data Method for Sales Forecast method |
| CN109472648A (en) * | 2018-11-20 | 2019-03-15 | 四川长虹电器股份有限公司 | Method for Sales Forecast method and server |
| CN109472518A (en) * | 2018-12-10 | 2019-03-15 | 泰康保险集团股份有限公司 | Sales behavior evaluation method and device, medium and electronic equipment based on block chain |
| CN109949079A (en) * | 2019-03-04 | 2019-06-28 | 王汝平 | Product market report generation method based on Bayesian network model, device |
| CN110322263A (en) * | 2018-03-30 | 2019-10-11 | 香港纺织及成衣研发中心有限公司 | The prediction technique and prediction meanss of garment marketing based on machine learning |
| CN110378510A (en) * | 2019-05-30 | 2019-10-25 | 国网浙江绍兴市上虞区供电有限公司 | A kind of distribution material requirements prediction technique being polymerize based on time series and level |
| CN111242698A (en) * | 2020-01-20 | 2020-06-05 | 金华航大北斗应用技术有限公司 | Method and system for neural network model of commodity demand prediction |
| TWI755035B (en) * | 2020-08-19 | 2022-02-11 | 國立勤益科技大學 | Big data product value model and product active index for method and system of analyzing consumption patterns |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20050102175A1 (en) * | 2003-11-07 | 2005-05-12 | Dudat Olaf S. | Systems and methods for automatic selection of a forecast model |
| CN106779859A (en) * | 2016-12-27 | 2017-05-31 | 南京安讯科技有限责任公司 | A kind of real-time Method for Sales Forecast method of mobile terminal product |
-
2017
- 2017-08-24 CN CN201710737231.4A patent/CN107346502A/en active Pending
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20050102175A1 (en) * | 2003-11-07 | 2005-05-12 | Dudat Olaf S. | Systems and methods for automatic selection of a forecast model |
| CN106779859A (en) * | 2016-12-27 | 2017-05-31 | 南京安讯科技有限责任公司 | A kind of real-time Method for Sales Forecast method of mobile terminal product |
Non-Patent Citations (2)
| Title |
|---|
| 李敏波等: "工业大数据分析技术与轮胎销售数据预测", 《计算机工程与应用》 * |
| 赵红艳: "基于大数据技术的小微企业信息采集技术研究", 《科技展望》 * |
Cited By (15)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2018170595A1 (en) * | 2017-03-23 | 2018-09-27 | Rubikloud Technologies Inc. | Method and system for generation of adjustable automated forecasts for a promotion |
| CN107967624A (en) * | 2017-11-24 | 2018-04-27 | 四川长虹电器股份有限公司 | A kind of evaluation method of business activity Sale Forecasting Model |
| CN108182595A (en) * | 2017-12-19 | 2018-06-19 | 山东浪潮云服务信息科技有限公司 | A kind of formulation migration efficiency method and device |
| CN110322263A (en) * | 2018-03-30 | 2019-10-11 | 香港纺织及成衣研发中心有限公司 | The prediction technique and prediction meanss of garment marketing based on machine learning |
| CN110322263B (en) * | 2018-03-30 | 2023-11-03 | 香港纺织及成衣研发中心有限公司 | Clothes sales prediction method and device based on machine learning |
| CN108446771A (en) * | 2018-04-02 | 2018-08-24 | 四川长虹电器股份有限公司 | A method of preventing Sale Forecasting Model over-fitting |
| CN109214601A (en) * | 2018-10-31 | 2019-01-15 | 四川长虹电器股份有限公司 | Household electric appliances big data Method for Sales Forecast method |
| CN109472648A (en) * | 2018-11-20 | 2019-03-15 | 四川长虹电器股份有限公司 | Method for Sales Forecast method and server |
| CN109472518A (en) * | 2018-12-10 | 2019-03-15 | 泰康保险集团股份有限公司 | Sales behavior evaluation method and device, medium and electronic equipment based on block chain |
| CN109472518B (en) * | 2018-12-10 | 2021-06-29 | 泰康保险集团股份有限公司 | Block chain-based sales behavior evaluation method and device, medium and electronic equipment |
| CN109949079A (en) * | 2019-03-04 | 2019-06-28 | 王汝平 | Product market report generation method based on Bayesian network model, device |
| CN110378510A (en) * | 2019-05-30 | 2019-10-25 | 国网浙江绍兴市上虞区供电有限公司 | A kind of distribution material requirements prediction technique being polymerize based on time series and level |
| CN110378510B (en) * | 2019-05-30 | 2023-08-18 | 国网浙江绍兴市上虞区供电有限公司 | Distribution network material demand prediction method based on time sequence and hierarchical aggregation |
| CN111242698A (en) * | 2020-01-20 | 2020-06-05 | 金华航大北斗应用技术有限公司 | Method and system for neural network model of commodity demand prediction |
| TWI755035B (en) * | 2020-08-19 | 2022-02-11 | 國立勤益科技大學 | Big data product value model and product active index for method and system of analyzing consumption patterns |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107346502A (en) | A kind of iteration product marketing forecast method based on big data | |
| Sadeghi et al. | A fuzzy grey goal programming approach for aggregate production planning | |
| CN109214601A (en) | Household electric appliances big data Method for Sales Forecast method | |
| Sadeghieh et al. | A genetic algorithm based grey goal programming (G3) approach for parts supplier evaluation and selection | |
| CN111882278A (en) | Intelligent replenishment method and system | |
| CN108280541A (en) | Customer service strategies formulating method, device based on random forest and decision tree | |
| WO2013102932A2 (en) | System and method facilitating forecasting, optimization and visualization of energy data for an industry | |
| CN109767032A (en) | A kind of business finance operation digital management optimization system based on data analysis | |
| CN108388974A (en) | Top-tier customer Optimum Identification Method and device based on random forest and decision tree | |
| Kaboli et al. | An expression-driven approach for long-term electric power consumption forecasting | |
| Chen et al. | Sales forecasting using deep neural network and SHAP techniques | |
| Jung et al. | Managing demand uncertainty through fuzzy inference in supply chain planning | |
| CN114782065A (en) | Commodity sales volume prediction method and device based on model combination and storage medium | |
| Singha et al. | Application of different machine learning models for supply chain demand forecasting: comparative analysis | |
| Zhou et al. | Research on intelligent solution of service industry supply chain network optimization based on genetic algorithm | |
| JP2020112847A (en) | Water demand prediction method and system | |
| CN116308494A (en) | Supply chain demand prediction method | |
| Xie et al. | Cross-border e-commerce logistics collaboration model based on supply chain theory | |
| Monge et al. | Water prices: persistence, mean reversion and trends | |
| Sun et al. | Hybrid evolutionary algorithm for integrated supply chain network design with assembly line balancing | |
| Kharkyanen et al. | Development of information technology for supporting the process of adjustment of the food enterprise assortment | |
| Che | Pricing strategy and reserved capacity plan based on product life cycle and production function on LCD TV manufacturer | |
| Li | A feature engineering approach for tree-based machine learning sales forecast, optimized by a genetic algorithm based sales feature framework | |
| Liang | Forecasting International Tourism Demand Using the Recurrent Neural Network Model with Genetic Algorithms and ARIMAX Model in Tourism Supply Chains | |
| De Nicolao et al. | Short-term load forecasting: A power-regression approach |
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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20171114 |