WO2015052851A1 - Système d'analyse de données de clients - Google Patents

Système d'analyse de données de clients Download PDF

Info

Publication number
WO2015052851A1
WO2015052851A1 PCT/JP2013/081284 JP2013081284W WO2015052851A1 WO 2015052851 A1 WO2015052851 A1 WO 2015052851A1 JP 2013081284 W JP2013081284 W JP 2013081284W WO 2015052851 A1 WO2015052851 A1 WO 2015052851A1
Authority
WO
WIPO (PCT)
Prior art keywords
data
customer
prediction
analysis system
probability value
Prior art date
Application number
PCT/JP2013/081284
Other languages
English (en)
Japanese (ja)
Inventor
剛太郎 毛谷村
Original Assignee
カルチュア・コンビニエンス・クラブ株式会社
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by カルチュア・コンビニエンス・クラブ株式会社 filed Critical カルチュア・コンビニエンス・クラブ株式会社
Priority to KR1020147022254A priority Critical patent/KR20150053256A/ko
Priority to CN201380013637.8A priority patent/CN104718547A/zh
Publication of WO2015052851A1 publication Critical patent/WO2015052851A1/fr
Priority to HK15110464.9A priority patent/HK1209867A1/xx

Links

Images

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
    • G06Q30/0281—Customer communication at a business location, e.g. providing product or service information, consulting
    • 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
    • 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
    • G06Q30/0241—Advertisements

Definitions

  • the present invention relates to a system for collecting and analyzing data relating to customers.
  • data collected from customers includes analysis for extracting optimal customers for recommendations such as advertisements to customers as described above, research for product and service development, and research on product and service sales trends. It can be used as data that is the basis of various analyzes represented by analysis for market research. Conventionally, as an analysis method for generating data that is the basis of such analysis, how much influence is the data associated with one item on the data associated with one item? In order to know whether or not to give, a model is created for each objective variable, and scoring is performed for one or more objective variables.
  • the present invention provides a system that can efficiently analyze collected data and generate data that is the basis of analysis that can be used in various aspects of analysis such as advertising and market research in a short time.
  • the purpose is to do.
  • the customer data analysis system of the present invention is a system for analyzing detailed data collected and stored in an operating company system, wherein a plurality of items of arbitrary detailed data are used as explanatory variables, and a plurality of other items are used as target variables. And a prediction processing means for calculating probability values of a plurality of items by probability inference.
  • a plurality of items of arbitrary detailed data are used as explanatory variables, a plurality of other items are used as objective variables, and the objective variable is used as an explanatory variable for a next-generation objective variable.
  • a prediction processing means for calculating probability values of a plurality of other items by probability inference.
  • It is characterized by having a data mart generation processing means for generating a data mart composed of detailed data suitable for analysis by summarizing detailed data.
  • It is characterized by having a correction means for correcting the prediction test model of the prediction process until the difference between the probability value and the prior probability value is determined to be equal to or less than an arbitrary value by the verification means.
  • a prediction test model determined to be a difference equal to or less than an arbitrary value by the verification unit is used as a prediction model for the prediction process, and a scoring unit that predicts the detailed data of all customers by the prediction model and calculates a probability value is provided. It is characterized by.
  • Threshold value is determined for the calculated probability value, and a map estimated value is calculated.
  • the prediction model creation process and the scoring process can be performed at one time regardless of the number of objective variables.
  • a customer data analysis system 1 (hereinafter simply referred to as a system 1) includes an operation company system 2 and an operation company system 2 that are composed of arithmetic devices, database groups, etc. under the jurisdiction of the operation company.
  • the network alliance system 3 such as an EC site composed of computing devices and input / output terminals, etc.
  • the operating company system 2 so as to be able to communicate information. It has a real alliance system 4 installed in the store and a questionnaire means 5.
  • the system 1 is a system for accumulating and analyzing various data collected from customers who use the system 1 via the net alliance system 3, the real alliance system 4, the questionnaire means 5, and the like.
  • the data accumulated from the customer in the operating company system 2 includes, firstly, the customer ID given to each customer at the time of system usage registration, the gender, age, etc. provided by the customer at the time of system 1 usage registration. There are attribute data such as basic customer attributes. Second, every time a customer purchases a product / service (hereinafter referred to as a product, etc.) at an alliance company, the items such as the product and product name, product name, time of visit, and store used are collected and transmitted.
  • a product / service hereinafter referred to as a product, etc.
  • the attribute data is accumulated in the member master database and updated when there is a change in the customer attribute data. Further, the detailed data is provided to the operating company system 2 as needed and stored in the analysis database.
  • Each data collected in this way is managed by customer ID.
  • An example of a customer ID is a number or character string with an arbitrary number of digits that differs for each customer. If the customer has a loyalty card, the customer ID is stored on the card magnetically, It is recorded by various methods such as electrical, customer ID is read by input means such as POS terminal of Real Alliance System 4, and can be transmitted to operating company system 2 in a state where customer ID and customer data are linked. Yes.
  • the customer ID is input by the input means of the customer terminal such as a portable terminal or a computer owned by the customer, and the operating company system is linked to the customer ID and the customer data. 2 can be transmitted.
  • the service point addition / subtraction process which is an incidental function in the system 1, is performed by the point system of the operation company system 2, and when a customer purchases a product etc. at an alliance company or at various other occasions.
  • service points are accumulated using service points, that is, whenever service point addition / subtraction data is transmitted, the service point addition / subtraction process corresponding to the customer's customer ID is performed. It has become.
  • the orthodox flow of the system 1 is a detailed data accumulation process (S1) for collecting detailed data transmitted to the operating company system 2 every time a customer purchases a product or the like at an alliance company, and accumulating the acquired detailed data (Detailed data collection and accumulation stage consisting of two steps, data mart generation processing (S3), sampling processing (S4), modeling processing (S5), verification processing (S6), scoring processing (S7)
  • the detailed data analysis stage includes analysis result calculation processing (S8).
  • the detailed data transmitted to the operating company system 2 through the real alliance system 4 and the net alliance system 3 through the detailed data storage process (S2) is stored in the analysis data database. In this way, collection and accumulation of detailed data is performed every time detailed data is transmitted.
  • the data summarization process (S3) as the first step in the detailed data analysis stage will be described.
  • the attribute data and / or the detail data are discretized as necessary, and the attribute data and / or the detail data are collected into the category data, the upper hierarchy, or the large / middle classification item group.
  • attribute data and / or detailed data can be collected into data items that are easy to analyze.
  • An example of the data mart generation process will be described with reference to FIG. For example, an item that is not a continuous quantity such as “gender” of attribute data is processed into categorical data.
  • the novel prediction processing of the present invention shown in FIGS. 3 and 5 to 11 uses, for example, probability inference represented by a Bayesian network, a plurality of items of arbitrary detailed data as objective variables, The probability value of a plurality of items is calculated by probability inference from the degree of correlation between items using a plurality of items as explanatory variables.
  • the probability value (1.0) of the item with side dish purchases is entered, and prediction processing is performed. Then, the probability value of unmarried, the objective variable, rises from 0.4252 (about 43%) to about 0.63 (63%).
  • the probability value of handmade orientation is the research-related data when there is no detailed data of customer A.
  • Prior probability values high 0.4809, low 0.5191
  • Prior probability values Married 0.5748, unmarried 0.4252 are assigned.
  • the probability value (1.0) without the vegetable purchase is entered, and the marriage probability value of the presence or absence of marriage as the first objective variable. Increases from 0.5748 (about 57%) to 0.685 (about 68%). Furthermore, since the presence or absence of marriage as the first objective variable is also an explanatory variable for handmade orientation as the second objective variable, the presence or absence of marriage of the first objective variable due to the fluctuation of the probability value (1.0) without the side dish purchase. The fluctuation of the first objective variable is propagated to the fluctuation of the second objective variable, and the handmade orientation probability value as the second objective variable is further increased from 0.715 (about 71%) to 0.737. (Approx. 74%).
  • the prediction process is a process in which the fluctuation of the probability value of the explanatory variable (parent) changes the probability value of the first objective variable (child), and the first objective variable (child) is updated. Is the process of changing the probability value of the second objective variable (child (grandchild for the first explanatory variable)).
  • one objective variable is also an explanatory variable for objective variables of the next generation and below, and all objective variables linked (the nth generation objective variable) can be set as necessary.
  • the prediction process of the present invention performs the prediction process for calculating the probability value of each item linked to the detailed data of an arbitrary explanatory variable, and affects the probability values of all linked objective variables. give.
  • the actual value of the explanatory variable of the parent generation is entered, and the influence is propagated to the linked (child, grandchild, nth generation objective variable) fluctuation, and the probability of each item
  • a prediction process for calculating a value is performed. This is the prediction process that calculates the probability value in the prediction model creation process and the scoring process, but here, the propagation model of the prediction process is shown in relation to the parent, child, and grandchild. It is not limited to the one-way type.
  • the sampling process creates a predictive test model as a pre-stage for creating a highly accurate prediction model for predicting detailed data for all customers, that is, a calculation system for probability reasoning. This is an operation to extract customers.
  • the sampling processing means performs processing for extracting a data mart (for example, a data mart of 3000 items) after summarizing an arbitrary number of customers (for example, one million people).
  • Customers who can be extracted for the purpose of creating a predictive test model in the sampling process can be extracted at random, but in order to enable accurate verification in the verification process described later, a customer who has an answer to the probability value In other words, it is appropriate to extract an arbitrary number of customers from customers in which detailed data of actual values exceeding a predetermined item is accumulated.
  • the detailed data sampled by the sampling means described above is subjected to the prediction process, that is, the probability inference using the prediction test model, and the probability value is calculated.
  • This is a process of creating a prediction model for scoring by verifying the answer obtained from the probability value and the detailed data actually collected and accumulated, that is, the prior probability value.
  • the modeling processing means performs prediction processing on the sampled customer detail data using the prediction test model.
  • the verification processing means determines the difference between the probability value obtained by the prediction process using the prediction test model and the prior probability value obtained for each objective variable collected in advance as the actual value for all items or arbitrarily.
  • the verification process calculated with the item is performed.
  • the correction processing means replaces the item of the objective variable or the explanatory variable or discretizes the item so that the difference between the probability value calculated as a result of the verification process and the prior probability value is equal to or less than an arbitrary value. Modify the prediction test model, such as changing.
  • the scoring process is a process for expanding the prediction process to the detailed data of the data marts of all customers using the prediction model created by the modeling process. Thereby, probability values are calculated for all items of the data mart of all customers.
  • the actual value is assigned only to the items of attribute data and detailed data that are actually collected.
  • the probability values after probability inference are assigned to all items, which is also referred to as a customer DNA (customer profiling) table shown in FIG.
  • FIG. 14 it is also possible to obtain a map estimated value by adding a process indicating the result of determining the input probability value with a threshold based on the tendency of the result table.
  • the waveform generation means performs a plot process for plotting the probability value of each item corresponding to the category taken along the vertical axis (S1), A waveform generation process (S2) for graphing is performed. For example, when generating the waveform of customer A, as shown in FIG.
  • the horizontal axis represents items
  • the vertical axis represents customer data (%)
  • each item of customer A for example, annual income level, smoking rate, car
  • the probability value against (retention ratio) is plotted, and this is converted into a waveform.
  • the property of customer A is represented by the waveform.
  • the waveform of customer B can also be represented.
  • the waveform generation means of another form calculates the average value of the probability values of each item, with the horizontal axis as the item and the vertical axis as the probability value (%), and the averaged probability value Is plotted, and a waveform generation process for generating a line graph is performed.
  • a waveform generation process for generating a line graph is performed.
  • FIG. 12 when generating a waveform of a product G, each item of customers who have history data that purchased the product G, with the horizontal axis as the item and the vertical axis as the probability value (%) An average value of other probability values is calculated, and an averaged probability value for each item (for example, annual income level, smoking rate, car ownership rate) of the product G is plotted, and this is converted into a waveform.
  • the waveform of the store A and the waveform of the store B can be generated.
  • the probability difference is a value indicating a distance between corresponding plotted points by a difference of probability values taken on the vertical axis, as shown in FIG.
  • the probability of the item X 1 for example, the annual income level
  • the probability of the item X 1 the annual income level of the item of the destination data B is X
  • X 1 A% the probability of the item of the destination data B is X
  • a threshold for example, ⁇ 3 degrees
  • the threshold value described above can be a variable condition.
  • the approximation degree between the same categories such as customer-to-customer, company-to-company, store-to-store, etc., or customer-to-company, customer-to-store, customer-to-product
  • this system can be used as a recommendation work for customers.
  • this system can be used to conduct survey analysis for various purposes, such as analysis of product lineups of companies and stores, analysis of store openings, and the like.
  • market research such as picking up customers who have not purchased product A but have a high probability of purchasing it. It can also be used. Furthermore, it can also be used for market research, such as analyzing products that are likely to be purchased by a group of customers.
  • the prediction model creation process and the scoring process can be performed at one time regardless of the number of objective variables.

Abstract

Un objectif de la présente invention est de proposer un système d'analyse grâce auquel l'analyse de données de clients qui sont collectées et accumulées dans un système d'entreprise de gestion est réalisée en un délai court et avec une grande précision. Pour atteindre cet objectif, l'invention propose un système d'analyse de données de clients (1) pour analyser des données détaillées qui sont collectées et accumulées dans un système d'entreprise de gestion (2), ledit système d'analyse de données de clients (1) comprenant un moyen de traitement de prédictions pour traiter une pluralité d'éléments arbitraires des données détaillées comme des variables explicatives, traiter une autre pluralité d'éléments comme des variables cibles, et calculer des valeurs de probabilité de la pluralité d'éléments à partir de corrélations entre les éléments par des inférences probabilistes.
PCT/JP2013/081284 2013-10-11 2013-11-20 Système d'analyse de données de clients WO2015052851A1 (fr)

Priority Applications (3)

Application Number Priority Date Filing Date Title
KR1020147022254A KR20150053256A (ko) 2013-10-11 2013-11-20 고객 데이터 해석 시스템
CN201380013637.8A CN104718547A (zh) 2013-10-11 2013-11-20 顾客数据解析系统
HK15110464.9A HK1209867A1 (en) 2013-10-11 2015-10-23 Customer data analysis system

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
JP2013-214213 2013-10-11
JP2013214213A JP6059122B2 (ja) 2013-10-11 2013-10-11 顧客データ解析システム

Publications (1)

Publication Number Publication Date
WO2015052851A1 true WO2015052851A1 (fr) 2015-04-16

Family

ID=52812694

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/JP2013/081284 WO2015052851A1 (fr) 2013-10-11 2013-11-20 Système d'analyse de données de clients

Country Status (6)

Country Link
JP (1) JP6059122B2 (fr)
KR (1) KR20150053256A (fr)
CN (1) CN104718547A (fr)
HK (1) HK1209867A1 (fr)
TW (1) TWI597679B (fr)
WO (1) WO2015052851A1 (fr)

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2017054487A (ja) * 2015-07-04 2017-03-16 タタ コンサルタンシー サービシズ リミテッドＴＡＴＡ Ｃｏｎｓｕｌｔａｎｃｙ Ｓｅｒｖｉｃｅｓ Ｌｉｍｉｔｅｄ 分布クエリに対してビジネスデータを融合するための方法及びシステム
EP4120147A4 (fr) * 2020-06-12 2023-04-26 ASICS Corporation Dispositif d'estimation de données, procédé et programme

Families Citing this family (12)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP6603600B2 (ja) * 2015-06-30 2019-11-06 パナソニック インテレクチュアル プロパティ コーポレーション オブ アメリカ 需要予測方法、需要予測装置及び需要予測プログラムを記録したコンピュータ読み取り可能な記録媒体
US11593817B2 (en) 2015-06-30 2023-02-28 Panasonic Intellectual Property Corporation Of America Demand prediction method, demand prediction apparatus, and non-transitory computer-readable recording medium
JP6320353B2 (ja) * 2015-08-27 2018-05-09 株式会社アクシバル デジタルマーケティングシステム
CN106651409A (zh) * 2015-10-29 2017-05-10 北京京东尚科信息技术有限公司 预测用户婚姻状态的方法和装置
JP6058104B1 (ja) * 2015-11-06 2017-01-11 株式会社南山デイリーサービス 顧客情報更新装置及びコンピュータプログラム
JP6784000B2 (ja) * 2015-12-25 2020-11-11 インターナショナル・ビジネス・マシーンズ・コーポレーションＩｎｔｅｒｎａｔｉｏｎａｌ Ｂｕｓｉｎｅｓｓ Ｍａｃｈｉｎｅｓ Ｃｏｒｐｏｒａｔｉｏｎ 情報処理装置、情報処理方法、及び、プログラム
CN105701498B (zh) * 2015-12-31 2021-09-07 腾讯科技（深圳）有限公司 一种用户分类方法及服务器
WO2019188102A1 (fr) 2018-03-27 2019-10-03 カルチュア・コンビニエンス・クラブ株式会社 Dispositif, procédé et programme de réalisation de recommandations sur la base d'informations d'attribut de client
JP6598321B1 (ja) * 2018-05-21 2019-10-30 Ｎｅｃプラットフォームズ株式会社 情報処理装置、制御方法、及びプログラム
JP7197391B2 (ja) * 2019-02-01 2022-12-27 株式会社オービック データ分析装置、データ分析方法およびデータ分析プログラム
CN113177643A (zh) * 2021-05-24 2021-07-27 北京融七牛信息技术有限公司 一种基于大数据的自动建模系统
CN113177642A (zh) * 2021-05-24 2021-07-27 北京融七牛信息技术有限公司 一种针对数据不平衡的自动建模系统

Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2002366401A (ja) * 2001-06-06 2002-12-20 Nippon Yunishisu Kk 統合的データマート構築及び運用支援システム
JP2010044518A (ja) * 2008-08-11 2010-02-25 Kddi Corp 嗜好推定装置、嗜好推定方法及びコンピュータプログラム
JP2012155427A (ja) * 2011-01-25 2012-08-16 Hitachi Ltd 用役設備の最適運転システム

Family Cites Families (10)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2001229150A (ja) * 2000-02-14 2001-08-24 Hitachi Ltd データ分析方法
CA2481485A1 (fr) * 2002-04-04 2003-10-16 Ishihara Sangyo Kaisha, Ltd. Dispositif et procede d'analyse de donnees
US20040064357A1 (en) * 2002-09-26 2004-04-01 Hunter Jeffrey D. System and method for increasing the accuracy of forecasted consumer interest in products and services
JP4847916B2 (ja) * 2007-05-18 2011-12-28 日本電信電話株式会社 購買順序を考慮したリコメンド装置、リコメンド方法、リコメンドプログラムおよびそのプログラムを記録した記録媒体
CN101354757B (zh) * 2008-09-08 2010-08-18 中国科学院地理科学与资源研究所 一种精细尺度下的动态风险及易损性预测方法
US20100203876A1 (en) * 2009-02-11 2010-08-12 Qualcomm Incorporated Inferring user profile properties based upon mobile device usage
JP2012190061A (ja) * 2011-03-08 2012-10-04 Sony Corp 情報処理装置、端末装置、情報提示システム、評価スコアの算出方法、及びプログラム
CN102360386A (zh) * 2011-10-12 2012-02-22 朱一超 电子商务网站智能导购系统和方法
CN102662832A (zh) * 2012-03-20 2012-09-12 浙江大学 一种生产过程数据校正软件的评测方法
CN103235981B (zh) * 2013-04-10 2016-03-09 东南大学 一种风电电能质量趋势预测方法

Patent Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2002366401A (ja) * 2001-06-06 2002-12-20 Nippon Yunishisu Kk 統合的データマート構築及び運用支援システム
JP2010044518A (ja) * 2008-08-11 2010-02-25 Kddi Corp 嗜好推定装置、嗜好推定方法及びコンピュータプログラム
JP2012155427A (ja) * 2011-01-25 2012-08-16 Hitachi Ltd 用役設備の最適運転システム

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
TSUKASA ISHIGAKI ET AL.: "Computational Customer Modeling by Using the Bayesian Network and the Double-latent Class Model in a Retail Service", IEICE TECHNICAL REPORT, vol. 110, no. 76, 7 June 2010 (2010-06-07), pages 165 - 171 *

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2017054487A (ja) * 2015-07-04 2017-03-16 タタ コンサルタンシー サービシズ リミテッドＴＡＴＡ Ｃｏｎｓｕｌｔａｎｃｙ Ｓｅｒｖｉｃｅｓ Ｌｉｍｉｔｅｄ 分布クエリに対してビジネスデータを融合するための方法及びシステム
EP4120147A4 (fr) * 2020-06-12 2023-04-26 ASICS Corporation Dispositif d'estimation de données, procédé et programme

Also Published As

Publication number Publication date
TWI597679B (zh) 2017-09-01
JP2015076076A (ja) 2015-04-20
HK1209867A1 (en) 2016-04-08
JP6059122B2 (ja) 2017-01-11
CN104718547A (zh) 2015-06-17
KR20150053256A (ko) 2015-05-15
TW201514889A (zh) 2015-04-16

Similar Documents

Publication Publication Date Title
JP6059122B2 (ja) 顧客データ解析システム
CN110135876A (zh) 销量预测的方法及装置
US20160267503A1 (en) System and method for predicting sales
KR20160071990A (ko) 고객 데이터 분석·검증 시스템
US20210264448A1 (en) Privacy preserving ai derived simulated world
WO2021025926A1 (fr) Priorisation de contenu numérique pour accélérer un hyper-ciblage
Catal et al. Benchmarking of regression algorithms and time series analysis techniques for sales forecasting
KR102091529B1 (ko) 사용자의 시계열적 행동 데이터를 이용하여 인공지능 모델을 학습시키는 방법 및 장치
US11017330B2 (en) Method and system for analysing data
JP5693649B2 (ja) 市場調査・分析システム
JP5914549B2 (ja) 情報処理装置および情報分析方法
US11762819B2 (en) Clustering model analysis for big data environments
Ismail et al. Data mining in electronic commerce: benefits and challenges
US20170316442A1 (en) Increase choice shares with personalized incentives using social media data
Wang et al. Infrastructure deployment under uncertainties and competition: the biofuel industry case
US10846352B1 (en) System and method for identifying potential clients from aggregate sources
JP2019082865A (ja) 販売促進装置、販売促進方法及び販売促進プログラム
JP6287280B2 (ja) 情報処理方法、プログラム、及び情報処理装置
Houshmand et al. Improve the classification and Sales management of products using multi-relational data mining
Al-Basha Forecasting Retail Sales Using Google Trends and Machine Learning
Wikamulia et al. Predictive business intelligence dashboard for food and beverage business
Ouamani et al. A Hybrid Model for Demand Forecasting Based on the Combination of Statistical and Machine Learning Methods
Chan Predictive models for determining if and when to display online lead forms
César et al. Customer Success Analysis and Modeling in Digital Marketing.
Inamoto et al. An approach of vectorizing shopping paths sensed by RFID tags to classify retail customers and its application with principal component regression

Legal Events

Date Code Title Description
ENP Entry into the national phase

Ref document number: 20147022254

Country of ref document: KR

Kind code of ref document: A

121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 13895177

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 13895177

Country of ref document: EP

Kind code of ref document: A1