CN104616180A - Method for predicting hot sellers - Google Patents
Method for predicting hot sellers Download PDFInfo
- Publication number
- CN104616180A CN104616180A CN201510101656.7A CN201510101656A CN104616180A CN 104616180 A CN104616180 A CN 104616180A CN 201510101656 A CN201510101656 A CN 201510101656A CN 104616180 A CN104616180 A CN 104616180A
- Authority
- CN
- China
- Prior art keywords
- data
- analysis
- technology
- prediction
- hot item
- 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
Abstract
The invention discloses a method for predicting hot sellers. The method is achieved by three steps, namely data acquisition, data preprocessing and data analysis, wherein during the data acquisition, through Internet and by a vertical search engine technology, structured and unstructured network electronic business data can be acquired from the network; during the data preprocessing, by a noise-reducing and normalizing technology, the data is processed to remove interfering data so as to prepare for the following data analysis; during the data analysis, the preprocessed data is modeled and analyzed to obtain prediction of the hot sellers and the prediction is displayed in a graphical form. Compared with the prior art, the method for predicting hot sellers has the following advantages: by the method, the data can be fully utilized; through processing and analysis on the electronic business data, an electronic business user is helped to purposefully analyze hot-selling trends of goods so as to achieve a purpose of effectively predicting the shelf goods to earn more profits.
Description
Technical field
The present invention relates to computer network technical field of electronic commerce, specifically a kind of hot item Forecasting Methodology.
Background technology
Along with the fast development of ecommerce, people more and more get used to using e-commerce website to buy commodity.But seller, while earning profit by Internet channel, but cannot be undertaken predicting later hot item by existing internet information, reach the object of the more profits of earning.How to help by a kind of effective mechanism the tendency that seller analyzes merchandise sales fast, to hold the type of added commodity accurately, be focus and the difficult point of current ecommerce research.
Data mining refers to the process excavating effective knowledge from the mass data leaving database, data warehouse or other information banks in.Data mining extracts implicit, valuable and intelligible information from mass data, to instruct the activity of people.Data mining technology mainly contains correlation rule, classifying rules, cluster analysis and sequence pattern etc.
Data mining is a kind of new business information treatment technology, and its principal feature extracts a large number of services data in business database, changes, analyzes and other modelling process, therefrom extracts the critical data of auxiliary commerce decision-making.In brief, data mining is the data analysing method of a class profound level in fact.
Data mining from a large amount of, incomplete, noisy, fuzzy, random real application data, extract lie in wherein, people are ignorant in advance but be the information of potentially useful and the process of knowledge.The synonym close with data mining has data to melt platform, data analysis and decision support etc.This definition comprises several layers implication: data source must be real, a large amount of, Noise; The found out that interested knowledge of user; The knowledge found will can accept, can understand, can use; Do not require the knowledge that the four seas that find to put are all accurate, only support specifically to pinpoint the problems.
Current e-commerce website is generally adopt the conventional art such as statistical technique and multidimensional analysis, with the experience of website design personnel, carries out prediction recommend the fast-selling trend of commodity.This commodity projection mode lacks accuracy, is difficult to reach remarkable result.These conventional arts are technology of checking type, are difficult to obtain be hidden in data knowledge behind.At present, also do not utilize data mining technology, carry out the fast-selling trend of commodity predicting the method for recommending.
Summary of the invention
Technical assignment of the present invention is to provide a kind of hot item Forecasting Methodology.
Technical assignment of the present invention realizes in the following manner, and the method realizes through data acquisition, data prediction and data analysis three step:
Data acquisition: utilize vertical search engine technology by internet, from network collection structuring and non-structured network electricity quotient data;
Data prediction: by noise reduction, normalization technology processes data, removes interfering data, for next step data analysis is prepared;
Data analysis: pretreated data are carried out modeling analysis, draws the prediction of hot item and shows with patterned form.
In described data acquisition, search for all inside and outside data messages relevant with business object, and therefrom select the data being applicable to data mining application.
Described noise reduction: filtered out the noise in data by data analysis algorithm, the data that analytical work is adopted are more accurate;
Normalization: when calculating the fancy grade of user to article, need to be weighted different behavioral datas; The data of each behavior are unified in an identical span, more accurate by being normalized the general trend making weighted sum obtain.
The technology that described Modeling analysis adopts is: Bayesian network technology, correlation rule, cluster analysis, Horting diagram technology and collaborative filtering.
A kind of hot item Forecasting Methodology of the present invention compared to the prior art, data can be made to be fully utilized, carry out the fast-selling trend of the commercial family of auxiliary electrical to commodity by the process to electric quotient data, analysis and carry out autotelic analysis, reach the effective prediction to added commodity, earn the object of more profits.
Accompanying drawing explanation
Accompanying drawing 1 is a kind of FB(flow block) of hot item Forecasting Methodology.
Embodiment
Embodiment 1:
The method realizes through data acquisition, data prediction and data analysis three step:
Data acquisition: utilize vertical search engine technology by internet, from network collection structuring and non-structured network electricity quotient data; In data acquisition, search for all inside and outside data messages relevant with business object, and therefrom select the data being applicable to data mining application.
Data prediction: by noise reduction, normalization technology processes data, removes interfering data, for next step data analysis is prepared;
Noise reduction: filtered out the noise in data by data analysis algorithm, the data that analytical work is adopted are more accurate;
Normalization: when calculating the fancy grade of user to article, need to be weighted different behavioral datas; The data of each behavior are unified in an identical span, more accurate by being normalized the general trend making weighted sum obtain.
Data analysis: pretreated data are carried out modeling analysis, draws the prediction of hot item and shows with patterned form.
The each system of last mode, makes system run all right.
Embodiment 2:
The method realizes through data acquisition, data prediction and data analysis three step:
Data acquisition: utilize vertical search engine technology by internet, from network collection structuring and non-structured network electricity quotient data; In data acquisition, search for all inside and outside data messages relevant with business object, and therefrom select the data being applicable to data mining application, after collection, unification is stored in raw data warehouse.
Data prediction: by noise reduction, normalization technology processes data, removes interfering data, for next step data analysis is prepared;
Noise reduction: filtered out the noise in data by data analysis algorithm, the data that analytical work is adopted are more accurate;
Normalization: when calculating the fancy grade of user to article, need to be weighted different behavioral datas; The data of each behavior are unified in an identical span, more accurate by being normalized the general trend making weighted sum obtain.
Data analysis: pretreated data acquisition Bayesian network technology, correlation rule, cluster analysis, Horting diagram technology and collaborative filtering are carried out modeling analysis, draw the prediction of hot item and show with patterned form, being presented to user.
The each system of last mode, makes system run all right.
By embodiment above, described those skilled in the art can be easy to realize the present invention.But should be appreciated that the present invention is not limited to above-mentioned several embodiments.On the basis of disclosed embodiment, described those skilled in the art can the different technical characteristic of combination in any, thus realizes different technical schemes.
Claims (4)
1. a hot item Forecasting Methodology, is characterized in that, the method realizes through data acquisition, data prediction and data analysis three step:
Data acquisition: utilize vertical search engine technology by internet, from network collection structuring and non-structured network electricity quotient data;
Data prediction: by noise reduction, normalization technology processes data, removes interfering data, for next step data analysis is prepared;
Data analysis: pretreated data are carried out modeling analysis, draws the prediction of hot item and shows with patterned form.
2. a kind of hot item Forecasting Methodology according to claim 1, is characterized in that, in described data acquisition, searches for all inside and outside data messages relevant with business object, and therefrom selects the data being applicable to data mining application.
3. a kind of hot item Forecasting Methodology according to claim 1, it is characterized in that, described noise reduction: filtered out the noise in data by data analysis algorithm, the data that analytical work is adopted are more accurate;
Normalization: when calculating the fancy grade of user to article, need to be weighted different behavioral datas; The data of each behavior are unified in an identical span, more accurate by being normalized the general trend making weighted sum obtain.
4. a kind of hot item Forecasting Methodology according to claim 1, is characterized in that, the technology that described Modeling analysis adopts is: Bayesian network technology, correlation rule, cluster analysis, Horting diagram technology and collaborative filtering.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201510101656.7A CN104616180A (en) | 2015-03-09 | 2015-03-09 | Method for predicting hot sellers |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201510101656.7A CN104616180A (en) | 2015-03-09 | 2015-03-09 | Method for predicting hot sellers |
Publications (1)
Publication Number | Publication Date |
---|---|
CN104616180A true CN104616180A (en) | 2015-05-13 |
Family
ID=53150614
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201510101656.7A Pending CN104616180A (en) | 2015-03-09 | 2015-03-09 | Method for predicting hot sellers |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN104616180A (en) |
Cited By (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN104915734A (en) * | 2015-06-25 | 2015-09-16 | 深圳市腾讯计算机系统有限公司 | Commodity popularity prediction method based on time sequence and system thereof |
CN105956015A (en) * | 2016-04-22 | 2016-09-21 | 四川中软科技有限公司 | Service platform integration method based on big data |
CN107016571A (en) * | 2017-03-31 | 2017-08-04 | 北京百分点信息科技有限公司 | Data predication method and its system |
WO2018165962A1 (en) * | 2017-03-17 | 2018-09-20 | 深圳市秀趣品牌文化传播有限公司 | E-commerce data migration system and method |
WO2018165964A1 (en) * | 2017-03-17 | 2018-09-20 | 深圳市秀趣品牌文化传播有限公司 | Cluster architecture-based e-commerce data migration system and method |
WO2018165966A1 (en) * | 2017-03-17 | 2018-09-20 | 深圳市秀趣品牌文化传播有限公司 | Discrete e-commerce data migration processing system and method |
Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101141456A (en) * | 2007-10-09 | 2008-03-12 | 南京财经大学 | Vertical search based network data excavation method |
US7664693B1 (en) * | 2005-06-13 | 2010-02-16 | CommEq Ltd. | Financial methodology for the examination and explanation of spread between analyst targets and market share prices |
CN101996213A (en) * | 2009-08-27 | 2011-03-30 | 顾海松 | Real-time customer shopping behavior analysis system and method |
CN102693498A (en) * | 2012-05-16 | 2012-09-26 | 上海卓达信息技术有限公司 | Accurate recommendation method based on incomplete data |
CN104063429A (en) * | 2014-06-11 | 2014-09-24 | 深圳德协保税电子商务有限公司 | Predicting method for user behavior in e-commerce |
CN104318459A (en) * | 2014-11-11 | 2015-01-28 | 苏州晨川通信科技有限公司 | Automatic market analysis method based on multi-mode learning |
-
2015
- 2015-03-09 CN CN201510101656.7A patent/CN104616180A/en active Pending
Patent Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US7664693B1 (en) * | 2005-06-13 | 2010-02-16 | CommEq Ltd. | Financial methodology for the examination and explanation of spread between analyst targets and market share prices |
CN101141456A (en) * | 2007-10-09 | 2008-03-12 | 南京财经大学 | Vertical search based network data excavation method |
CN101996213A (en) * | 2009-08-27 | 2011-03-30 | 顾海松 | Real-time customer shopping behavior analysis system and method |
CN102693498A (en) * | 2012-05-16 | 2012-09-26 | 上海卓达信息技术有限公司 | Accurate recommendation method based on incomplete data |
CN104063429A (en) * | 2014-06-11 | 2014-09-24 | 深圳德协保税电子商务有限公司 | Predicting method for user behavior in e-commerce |
CN104318459A (en) * | 2014-11-11 | 2015-01-28 | 苏州晨川通信科技有限公司 | Automatic market analysis method based on multi-mode learning |
Cited By (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN104915734A (en) * | 2015-06-25 | 2015-09-16 | 深圳市腾讯计算机系统有限公司 | Commodity popularity prediction method based on time sequence and system thereof |
CN104915734B (en) * | 2015-06-25 | 2017-03-22 | 深圳市腾讯计算机系统有限公司 | Commodity popularity prediction method based on time sequence and system thereof |
CN105956015A (en) * | 2016-04-22 | 2016-09-21 | 四川中软科技有限公司 | Service platform integration method based on big data |
WO2018165962A1 (en) * | 2017-03-17 | 2018-09-20 | 深圳市秀趣品牌文化传播有限公司 | E-commerce data migration system and method |
WO2018165964A1 (en) * | 2017-03-17 | 2018-09-20 | 深圳市秀趣品牌文化传播有限公司 | Cluster architecture-based e-commerce data migration system and method |
WO2018165966A1 (en) * | 2017-03-17 | 2018-09-20 | 深圳市秀趣品牌文化传播有限公司 | Discrete e-commerce data migration processing system and method |
CN107016571A (en) * | 2017-03-31 | 2017-08-04 | 北京百分点信息科技有限公司 | Data predication method and its system |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
Liu | Analyzing the impact of user-generated content on B2B Firms' stock performance: Big data analysis with machine learning methods | |
US20210027146A1 (en) | Method and apparatus for determining interest of user for information item | |
Kurnia | Business intelligence model to analyze social media information | |
He et al. | A novel social media competitive analytics framework with sentiment benchmarks | |
Moro et al. | Business intelligence in banking: A literature analysis from 2002 to 2013 using text mining and latent Dirichlet allocation | |
CN104616180A (en) | Method for predicting hot sellers | |
Sun et al. | iCARE: A framework for big data-based banking customer analytics | |
Ernawati et al. | A review of data mining methods in RFM-based customer segmentation | |
WO2021025926A1 (en) | Digital content prioritization to accelerate hyper-targeting | |
Qu et al. | Matchmaking in reward-based crowdfunding platforms: A hybrid machine learning approach | |
JP6059122B2 (en) | Customer data analysis system | |
CN107077486A (en) | Affective Evaluation system and method | |
KR101566616B1 (en) | Advertisement decision supporting system using big data-processing and method thereof | |
Vanani et al. | A comparative analysis of emerging scientific themes in business analytics | |
CN105069036A (en) | Information recommendation method and apparatus | |
KR102458510B1 (en) | Real-time complementary marketing system | |
Werle et al. | Competitor identification: A review of use cases, data sources, and algorithms | |
Bhargavi et al. | Comparative study of consumer purchasing and decision pattern analysis using pincer search based data mining method | |
Son et al. | Topic diversity of online consumer reviews and its effect on review helpfulness | |
Cho et al. | Clustering method using weighted preference based on RFM score for personalized recommendation system in u-commerce | |
Zhao | The review of web mining in e-commerce | |
Seeliger et al. | Process explorer: an interactive visual recommendation system for process mining | |
CN114065063A (en) | Information processing method, information processing apparatus, storage medium, and electronic device | |
Hong et al. | ClustPTF: Clustering-based parallel tensor factorization for the diverse multi-criteria recommendation | |
Midhunchakkaravarthy et al. | Evaluation of product usability using improved FP-growth frequent itemset algorithm and DSLC–FOA algorithm for alleviating feature fatigue |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C06 | Publication | ||
PB01 | Publication | ||
C10 | Entry into substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20150513 |
|
WD01 | Invention patent application deemed withdrawn after publication |