CN111222915A - Public number ROI (region of interest) estimation method and device based on linear regression model - Google Patents

Public number ROI (region of interest) estimation method and device based on linear regression model Download PDF

Info

Publication number
CN111222915A
CN111222915A CN201911417542.8A CN201911417542A CN111222915A CN 111222915 A CN111222915 A CN 111222915A CN 201911417542 A CN201911417542 A CN 201911417542A CN 111222915 A CN111222915 A CN 111222915A
Authority
CN
China
Prior art keywords
linear regression
regression model
roi
data
user activity
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
Application number
CN201911417542.8A
Other languages
Chinese (zh)
Inventor
翟永佳
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Shanghai Changtou Network Technology Co Ltd
Original Assignee
Shanghai Changtou Network Technology Co Ltd
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 Shanghai Changtou Network Technology Co Ltd filed Critical Shanghai Changtou Network Technology Co Ltd
Priority to CN201911417542.8A priority Critical patent/CN111222915A/en
Publication of CN111222915A publication Critical patent/CN111222915A/en
Pending legal-status Critical Current

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
    • G06Q30/0241—Advertisements
    • G06Q30/0251—Targeted advertisements
    • G06Q30/0255—Targeted advertisements based on user history
    • 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
    • G06Q30/00—Commerce
    • G06Q30/02—Marketing; Price estimation or determination; Fundraising
    • G06Q30/0201—Market modelling; Market analysis; Collecting market data
    • G06Q30/0202—Market predictions or forecasting for commercial activities
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q30/00—Commerce
    • G06Q30/02—Marketing; Price estimation or determination; Fundraising
    • G06Q30/0241—Advertisements
    • G06Q30/0242—Determining effectiveness of advertisements
    • 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
    • G06Q30/0277—Online advertisement

Landscapes

  • Business, Economics & Management (AREA)
  • Engineering & Computer Science (AREA)
  • Strategic Management (AREA)
  • Development Economics (AREA)
  • Accounting & Taxation (AREA)
  • Finance (AREA)
  • Economics (AREA)
  • Entrepreneurship & Innovation (AREA)
  • Physics & Mathematics (AREA)
  • Marketing (AREA)
  • Game Theory and Decision Science (AREA)
  • General Business, Economics & Management (AREA)
  • General Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Human Resources & Organizations (AREA)
  • Operations Research (AREA)
  • Quality & Reliability (AREA)
  • Tourism & Hospitality (AREA)
  • Data Mining & Analysis (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)

Abstract

The invention is suitable for the technical field of micro-letter public number advertisement putting, and provides a public number ROI estimation method and a device based on a linear regression model, which can provide data reference for advertisement putting by sequentially extracting user activity data of a micro-letter public number in preset days, inputting the obtained user activity data as a prediction variable, inputting sales of a large class of the micro-letter public number in preset days after advertisement putting as a predicted variable, training the linear regression model, inputting an estimation sample comprising the user activity data of the micro-letter public number to be estimated when estimating the ROI, obtaining the estimated sales through the trained linear regression model, dividing the estimated sales by putting cost to obtain the estimated ROI value, thereby effectively estimating the advertisement investment rate of the micro-letter public number by using the existing data, and providing data reference for the advertisement putting, the public number with better putting effect is intelligently locked in advance, and the investment cost is saved.

Description

Public number ROI (region of interest) estimation method and device based on linear regression model
Technical Field
The invention belongs to the technical field of WeChat public number advertisement delivery, and particularly relates to a public number ROI estimation method and device based on a linear regression model.
Background
The WeChat public platform is mainly used for cooperative popularization business brought by organizations such as celebrities, governments, media, enterprises and the like. Branding can be promoted to the online platform function through channels. Advertising on WeChat public numbers is a common advertising promotion method.
However, the return on investment that needs to be considered when an enterprise puts an advertisement is needed, which is the value to be returned by investment, that is, the economic return that the enterprise receives from one investment activity, and therefore, a technology capable of estimating the return on investment for the WeChat public account is needed.
Disclosure of Invention
The invention provides a public number ROI (region of interest) estimation method and device based on a linear regression model, and aims to solve the problem that the return on investment of WeChat advertisements cannot be estimated.
The invention is realized in this way, a public number ROI estimation method and device based on linear regression model, comprising the following steps:
s1, extracting user activity data of the WeChat public number in preset days;
s2, inputting the obtained user activity data as a prediction variable, inputting the sales of the WeChat public class in a preset number of days after advertisement putting as a predicted variable, and training a linear regression model;
s3, when the ROI is estimated, inputting an estimation sample of user activity data including the WeChat public number to be estimated, obtaining estimated sales through a trained linear regression model, and dividing by the delivery cost to obtain a numerical value of the estimated ROI.
Preferably, the user activity data includes historical reading number, praise number and comment number, and the weighted coefficient of the historical reading number is 0.2, the weighted coefficient of the praise number is 0.4, and the weighted coefficient of the comment number is 0.4, and the weighted historical reading number, praise number and comment number are added to calculate the user activity data value.
Preferably, in step S2, the preset number of days is 3 to 5 days.
A public number ROI estimation device based on a linear regression model comprises:
the data acquisition module is used for extracting user activity data of the WeChat public number in preset days;
the sales amount pre-estimation module comprises a linear regression model, and the sales amount pre-estimation module is used for training the linear regression model by taking the user activity data as a prediction variable and taking the sales amount of the WeChat public class in a preset number of days after the advertisement is released as a predicted variable;
and the ROI estimation module is used for obtaining estimated sales through a trained linear regression model according to an estimation sample of user activity data including the WeChat public number to be estimated, and obtaining a value of the estimated ROI after dividing by the delivery cost.
Preferably, when the data acquisition module extracts the user activity data, the historical reading number, the like number and the comment number of the WeChat public number are calculated, and the weighted historical reading number, the like number and the comment number are added to calculate the user activity data value, wherein the weighting coefficient of the historical reading number is 0.2, the weighting coefficient of the like number is 0.4 and the weighting coefficient of the comment number is 0.4.
Preferably, the preset number of days is 3-5 days.
Preferably, a plurality of liquid leakage holes are formed in the grab bucket.
Compared with the prior art, the invention has the beneficial effects that: according to the method and the device for estimating the ROI of the public number based on the linear regression model, the user activity data of the WeChat public number in the preset days are sequentially extracted, the obtained user activity data are used as the prediction variables to be input, the sales of the WeChat public number in the preset days after the advertisement is released are used as the predicted variables to be input, the linear regression model is trained, when the ROI is estimated, the estimation sample comprising the user activity data of the WeChat public number to be estimated is input, the estimated sales is obtained through the trained linear regression model, and the estimated ROI value is obtained after the cost of the release is divided by the estimated sales, so that the advertisement investment return rate of the WeChat public number can be effectively estimated by using the existing data.
Drawings
FIG. 1 is a flow chart of the public number ROI estimation method based on a linear regression model according to the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, the present invention is described in further detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.
Referring to fig. 1, the present invention provides a technical solution: a public number ROI estimation method and a device based on a linear regression model are disclosed, wherein the public number ROI estimation method comprises the following steps:
and S1, extracting the user activity data of the WeChat public number in the preset days.
The user activity data comprises historical reading data, praise data and comment data, the weighting coefficient of the historical reading data is 0.2, the weighting coefficient of the praise data is 0.4, the weighting coefficient of the comment data is 0.4, and the weighted historical reading data, the praise data and the comment data are added to calculate a user activity data value.
And S2, inputting the obtained user activity data as a prediction variable, and inputting the sales of the WeChat public class in 3 days after the advertisement is delivered as a predicted variable, and training a linear regression model. Sales amounts of 4 or 5 days after ad placement may be employed in other embodiments.
Linear regression is a statistical analysis method that utilizes regression analysis in mathematical statistics to determine the interdependent quantitative relationships between two or more variables, and is widely used. The regression analysis, which includes only one independent variable and one dependent variable and the relationship between them can be approximately expressed by a straight line, is called unitary linear regression analysis, i.e. the linear regression analysis method adopted by the present invention.
S3, when the ROI is estimated, inputting an estimation sample of user activity data including the WeChat public number to be estimated, obtaining estimated sales through a trained linear regression model, and dividing by the delivery cost to obtain a numerical value of the estimated ROI.
The invention discloses a public number ROI estimation device based on a linear regression model, which comprises: the system comprises a data acquisition module, a sales amount pre-estimation module and an ROI pre-estimation module. The data acquisition module is used for extracting user activity data of the WeChat public account within preset days. The sales amount estimation module comprises a linear regression model, and the sales amount estimation module is used for training the linear regression model by taking the user activity data as a prediction variable and taking the sales amount of the WeChat public account class in a preset number of days after the advertisement is released as a predicted variable. The preset number of days is 3-5 days, and 3 days are adopted as the sales amount 3 days after the advertisement is delivered in the embodiment. And the ROI estimation module is used for obtaining estimated sales through a trained linear regression model according to an estimation sample of user activity data including the WeChat public number to be estimated, and obtaining a value of the estimated ROI after dividing by the delivery cost.
When the data acquisition module extracts user activity data, historical reading numbers, praise numbers and comment numbers of the WeChat public numbers are calculated, the weighting coefficient of the historical reading numbers is 0.2, the weighting coefficient of the praise numbers is 0.4, the weighting coefficient of the comment numbers is 0.4, and the weighted historical reading numbers, the praise numbers and the comment numbers are added to calculate a user activity data value.
According to the method and the device for estimating the ROI of the public number based on the linear regression model, the user activity data of the WeChat public number in the preset days are sequentially extracted, the obtained user activity data are used as the prediction variables to be input, the sales of the WeChat public number in the preset days after the advertisement is released are used as the predicted variables to be input, the linear regression model is trained, when the ROI is estimated, the estimation sample comprising the user activity data of the WeChat public number to be estimated is input, the estimated sales is obtained through the trained linear regression model, and the estimated ROI value is obtained after the cost of the release is divided by the estimated sales, so that the advertisement investment return rate of the WeChat public number can be effectively estimated by using the existing data. The public number ROI estimation method and the public number ROI estimation device can provide data reference for advertisement putting, and intelligently lock public numbers with good putting effect in advance.
The above description is only for the purpose of illustrating the preferred embodiments of the present invention and is not to be construed as limiting the invention, and any modifications, equivalents and improvements made within the spirit and principle of the present invention are intended to be included within the scope of the present invention.

Claims (6)

1. A public number ROI estimation method and a device based on a linear regression model are characterized in that: the method comprises the following steps:
s1, extracting user activity data of the WeChat public number in preset days;
s2, inputting the obtained user activity data as a prediction variable, inputting the sales of the WeChat public class in a preset number of days after advertisement putting as a predicted variable, and training a linear regression model;
s3, when the ROI is estimated, inputting an estimation sample of user activity data including the WeChat public number to be estimated, obtaining estimated sales through a trained linear regression model, and dividing by the delivery cost to obtain a numerical value of the estimated ROI.
2. The linear regression model-based public account ROI estimation method of claim 1, wherein: the user activity data comprises historical reading data, praise data and comment data, the weighting coefficient of the historical reading data is 0.2, the weighting coefficient of the praise data is 0.4, the weighting coefficient of the comment data is 0.4, and the weighted historical reading data, the praise data and the comment data are added to calculate a user activity data value.
3. The linear regression model-based public account ROI estimation method of claim 1, wherein: in step S2, the preset number of days is 3 to 5 days.
4. A public number ROI estimation device based on a linear regression model is characterized in that: the method comprises the following steps:
the data acquisition module is used for extracting user activity data of the WeChat public number in preset days;
the sales amount pre-estimation module comprises a linear regression model, and the sales amount pre-estimation module is used for training the linear regression model by taking the user activity data as a prediction variable and taking the sales amount of the WeChat public class in a preset number of days after the advertisement is released as a predicted variable;
and the ROI estimation module is used for obtaining estimated sales through a trained linear regression model according to an estimation sample of user activity data including the WeChat public number to be estimated, and obtaining a value of the estimated ROI after dividing by the delivery cost.
5. The linear regression model-based public address ROI estimation device of claim 4, wherein: when the data acquisition module extracts user activity data, historical reading numbers, praise numbers and comment numbers of the WeChat public numbers are calculated, the weighting coefficient of the historical reading numbers is 0.2, the weighting coefficient of the praise numbers is 0.4, the weighting coefficient of the comment numbers is 0.4, and the weighted historical reading numbers, the praise numbers and the comment numbers are added to calculate a user activity data value.
6. The linear regression model-based public account ROI estimation method and device as claimed in claim 1, wherein: the preset days are 3-5 days.
CN201911417542.8A 2019-12-31 2019-12-31 Public number ROI (region of interest) estimation method and device based on linear regression model Pending CN111222915A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201911417542.8A CN111222915A (en) 2019-12-31 2019-12-31 Public number ROI (region of interest) estimation method and device based on linear regression model

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201911417542.8A CN111222915A (en) 2019-12-31 2019-12-31 Public number ROI (region of interest) estimation method and device based on linear regression model

Publications (1)

Publication Number Publication Date
CN111222915A true CN111222915A (en) 2020-06-02

Family

ID=70808316

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201911417542.8A Pending CN111222915A (en) 2019-12-31 2019-12-31 Public number ROI (region of interest) estimation method and device based on linear regression model

Country Status (1)

Country Link
CN (1) CN111222915A (en)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113344642A (en) * 2021-07-05 2021-09-03 上海明略人工智能(集团)有限公司 Method, device, electronic equipment and readable storage medium for predicting return on investment of advertisement

Citations (9)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2014041566A (en) * 2012-08-23 2014-03-06 Nippon Telegr & Teleph Corp <Ntt> Device, method, and program for linear regression model estimation
CN105022825A (en) * 2015-07-22 2015-11-04 中国人民解放军国防科学技术大学 Financial variety price prediction method capable of combining financial news mining and financial historical data
CN106803190A (en) * 2017-01-03 2017-06-06 北京掌阔移动传媒科技有限公司 A kind of ad personalization supplying system and method
CN106980909A (en) * 2017-03-30 2017-07-25 重庆大学 A kind of box office receipts Forecasting Methodology based on Fuzzy Linear Regression
CN107292664A (en) * 2017-06-10 2017-10-24 星联互动文化传播（天津）有限公司 A kind of microblogging marketing temperature prediction model method
CN107862547A (en) * 2017-11-03 2018-03-30 网易乐得科技有限公司 Launch appraisal procedure, medium, device and the computing device of channel
CN108564404A (en) * 2018-04-09 2018-09-21 北京搜狐新媒体信息技术有限公司 A kind of method and device of prediction investment in advertising return rate
CN108665310A (en) * 2018-05-08 2018-10-16 多盟睿达科技（中国）有限公司 A kind of advertisement placement method and system based on detection pre-estimating technology
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

Patent Citations (9)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2014041566A (en) * 2012-08-23 2014-03-06 Nippon Telegr & Teleph Corp <Ntt> Device, method, and program for linear regression model estimation
CN105022825A (en) * 2015-07-22 2015-11-04 中国人民解放军国防科学技术大学 Financial variety price prediction method capable of combining financial news mining and financial historical data
CN106803190A (en) * 2017-01-03 2017-06-06 北京掌阔移动传媒科技有限公司 A kind of ad personalization supplying system and method
CN106980909A (en) * 2017-03-30 2017-07-25 重庆大学 A kind of box office receipts Forecasting Methodology based on Fuzzy Linear Regression
CN107292664A (en) * 2017-06-10 2017-10-24 星联互动文化传播（天津）有限公司 A kind of microblogging marketing temperature prediction model method
CN107862547A (en) * 2017-11-03 2018-03-30 网易乐得科技有限公司 Launch appraisal procedure, medium, device and the computing device of channel
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
CN108564404A (en) * 2018-04-09 2018-09-21 北京搜狐新媒体信息技术有限公司 A kind of method and device of prediction investment in advertising return rate
CN108665310A (en) * 2018-05-08 2018-10-16 多盟睿达科技（中国）有限公司 A kind of advertisement placement method and system based on detection pre-estimating technology

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113344642A (en) * 2021-07-05 2021-09-03 上海明略人工智能(集团)有限公司 Method, device, electronic equipment and readable storage medium for predicting return on investment of advertisement

Similar Documents

Publication Publication Date Title
US20230161968A1 (en) System and Method for Monitoring a Sentiment Score
US11954577B2 (en) Deep neural network based user segmentation
CN110310163A (en) A kind of accurate method, equipment and readable medium for formulating marketing strategy
US20100205103A1 (en) Real-time customer service assistance using collected customer life cycle data
CN107872593A (en) Attend a banquet the method and device of distribution
CN106997549A (en) The method for pushing and system of a kind of advertising message
CN105989074A (en) Method and device for recommending cold start through mobile equipment information
Olugbode et al. The Effect of Information Systems on Firm Performance and Profitability Using a Case‑Study Approach
US20200202361A1 (en) System and method for analysing and evaluating customer effort
CN107864301A (en) Client&#39;s label management method, system, computer equipment and storage medium
CN108133390A (en) For predicting the method and apparatus of user behavior and computing device
CN108053322A (en) The customer investment return evaluation method and system of vehicle
CN109783726A (en) A kind of real estate big data computation processing method and its system
CN110955690A (en) Self-service data labeling platform and self-service data labeling method based on big data technology
US8375038B2 (en) Method to send a short message service (SMS) campaign to a related object by selecting the base object
CN115545516A (en) Performance data processing method, device and system based on process engine
CN110716774B (en) Data driving method, system and storage medium for brain of financial business data
CN111159429B (en) Knowledge graph-based data analysis method and device, equipment and storage medium
CN110147286B (en) Custom information sending method, device and system based on message queue and recording medium
CN111222915A (en) Public number ROI (region of interest) estimation method and device based on linear regression model
CN113452852B (en) Method and device for regulating and controlling number of outbound calls of machine, electronic equipment and storage medium
CN108021584A (en) A kind of method and apparatus of pushed information
Moth et al. From Doctor to Nurse Triage in the Danish Out‐of‐Hours Primary Care Service: Simulated Effects on Costs
CN111199426B (en) WeChat public signal ROI estimation method and device based on random forest model
CN114429362A (en) Advertisement product delivery method and device, electronic device and readable storage medium

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: 20200602