CN110930184A - Potential customer mining and customer type selection method based on mixed recommendation algorithm - Google Patents
Potential customer mining and customer type selection method based on mixed recommendation algorithm Download PDFInfo
- Publication number
- CN110930184A CN110930184A CN201911113155.5A CN201911113155A CN110930184A CN 110930184 A CN110930184 A CN 110930184A CN 201911113155 A CN201911113155 A CN 201911113155A CN 110930184 A CN110930184 A CN 110930184A
- Authority
- CN
- China
- Prior art keywords
- algorithm
- user
- customer
- product
- data
- 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
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
- G06Q30/0201—Market modelling; Market analysis; Collecting market data
Landscapes
- Business, Economics & Management (AREA)
- Strategic Management (AREA)
- Engineering & Computer Science (AREA)
- Accounting & Taxation (AREA)
- Development Economics (AREA)
- Finance (AREA)
- Entrepreneurship & Innovation (AREA)
- Game Theory and Decision Science (AREA)
- Data Mining & Analysis (AREA)
- Economics (AREA)
- Marketing (AREA)
- Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The invention discloses a potential customer mining and customer type selection method based on a hybrid recommendation algorithm, which comprises the following steps of: s1: collecting user data and extracting data characteristics to build a data model; s2: selecting different algorithms for algorithm analysis and taking specific gravity values of the labels for algorithm integration aiming at different data characteristic labels; judging whether the users have interest in the product before the point by using a jacard formula according to the similarity between the users and searching a similarity algorithm between individual users; calculating the probability of the interest of the user in the product by using a Euclidean algorithm according to the scores of the user on different products; s3: and outputting an algorithm result. The method has the beneficial effects that a mixed recommendation algorithm is adopted, and various recommendation technologies are adopted to provide various recommendation results for providing recommendation reference for sales and integrating final recommendation so as to realize scientific and intelligent sales.
Description
Technical Field
The invention relates to a potential customer mining and customer type selection method based on a hybrid recommendation algorithm.
Background
The sales promotion staff roughly still is in a relatively original mode in the selection of the customers, the consumption type and the consumption potential of one user are judged through subjective consciousness, the demand direction of the user is not clearly known, and the type of the user is not clearly labeled.
The main defects of the existing method are as follows: (1) blind sale, and carrying out ineffective work on users without consumption potential and capacity; (2) the sales efficiency is low, and no needed sales client is found; (3) the sales probability is low, and the customers do not well know the products which are not needed by the sales customers in consumption; (4) the algorithm is not systematic, has no perfect scientific algorithm basis and is completely defined by subjective judgment and experience of the user.
Disclosure of Invention
In order to overcome the defects of the prior art, the invention provides a potential customer mining and customer type selection method based on a hybrid recommendation algorithm, which adopts the hybrid recommendation algorithm, namely, the customer mining is carried out on the basis of data acquisition and feature extraction, so that the sales efficiency is improved, and the single sales rate is improved to realize the improvement of the sales amount.
In order to achieve the above object, the present invention adopts the following technical solutions:
a potential customer mining and customer type selection method based on a hybrid recommendation algorithm comprises the following steps:
s1: collecting user data and extracting data characteristics to build a data model;
s2: selecting different algorithms for algorithm analysis and taking specific gravity values of the labels for algorithm integration aiming at different data characteristic labels; wherein the content of the first and second substances,
judging whether the user is interested in the product before the point by using a jacard formula according to the similarity between the users and searching a similarity algorithm between individual users;
calculating the probability of the interest of the user in the product by using a Euclidean algorithm according to the scores of the user on different products;
aiming at a user with the same hobbies and purchasing tendency as the user, judging whether the product has a purchasing tendency by using a CF algorithm based on the user;
a product-based CF algorithm is used to determine whether a user is inclined to purchase a product for the type of user for which the product was purchased.
S3: and outputting an algorithm result.
Further, algorithm analysis is carried out aiming at user group characteristics, support vector machine algorithm processing is carried out on the behavior data, and association rule algorithm processing is carried out on the identity and industry characteristics of the user.
And further, carrying out score comparison processing on different features and algorithms.
A potential customer mining and customer type selection method based on a hybrid recommendation algorithm comprises the following steps:
s1: collecting user data and extracting data characteristics to build a data model;
s2: selecting different algorithms for algorithm analysis and taking specific gravity values of the labels for algorithm integration aiming at different data characteristic labels;
s3: and outputting an algorithm result.
Further, the algorithms used include jacard's formula, euclidean algorithm, customer-based CF algorithm, and product-based CF algorithm.
The invention has the advantages that
A mixed recommendation algorithm is adopted, and various recommendation technologies are adopted to provide various recommendation results for sales, so that recommendation reference and final recommendation are integrated to achieve scientific and intelligent sales.
Drawings
FIG. 1 is a schematic diagram of a potential customer mining and customer typing method based on a hybrid recommendation algorithm;
FIG. 2 is a schematic diagram of a table of the user-based CF algorithm of the hybrid recommendation algorithm based potential customer mining and customer typing method of FIG. 1;
FIG. 3 is a schematic diagram of the user-based CF algorithm of FIG. 2;
FIG. 4 is a schematic diagram of a table of the product-based CF algorithm of the hybrid recommendation algorithm based potential customer mining and customer model selection method of FIG. 1;
fig. 5 is a schematic diagram of the product-based CF algorithm of fig. 4.
Detailed Description
The invention is described in detail below with reference to the figures and the embodiments.
As shown in fig. 1 to 5, a potential customer mining and customer type selection method based on a hybrid recommendation algorithm includes the following steps:
s1: user data acquisition and data feature extraction and data model building and feature training are carried out;
s2: selecting different algorithms for algorithm analysis and taking specific gravity values of the labels for algorithm integration aiming at different data characteristic labels;
judging whether the users have interest in the product before the point by using a jacard formula according to the similarity between the users and searching a similarity algorithm between individual users;
calculating the probability of the interest of the user in the product by using a Euclidean algorithm according to the scores of the user on different products;
aiming at a user with the same hobbies and purchasing tendency as the user, judging whether the product has a purchasing tendency by using a CF algorithm based on the user;
a product-based CF algorithm is used to determine whether a user is inclined to purchase a product for the type of user for which the product was purchased.
S3: and outputting an algorithm result. And outputting an algorithm result for user sales judgment and leadership decision.
Specifically, the jacard algorithm:
a euclidean algorithm;
user-based CF algorithm see fig. 2 and 3; the product-based CF algorithm is shown in fig. 4 and 5.
The main tasks of the customer mining and model selection method are customer data acquisition, feature processing and a mixed recommendation algorithm based on the same, and the core idea is to utilize a recommendation system from commodity recommendation to customer selection and leadership decision based on the mixed recommendation algorithm collaborative filtering.
Based on collaborative filtering; searching for similarity of jaccard, Euclidean algorithm, CF algorithm based on user and CF algorithm based on product, and the like. The collected and processed user data includes user identity, behavior, assets, and social circle preference. And performing algorithm analysis aiming at the user group characteristics, performing SVM (support vector machine) algorithm processing on the behavior data, and performing association rule algorithm processing on the identity and the industry characteristics of the user. Performing coordination filtering and other processing based on hobby social circles, and finally performing score comparison processing on different characteristics and algorithms; and the recommendation system is utilized from commodity recommendation to leader decision. The basic process is as follows: firstly, collecting data and extracting characteristics; selecting an algorithm and analyzing the algorithm; and then obtaining the user type and the potential consumption value to complete the pre-decision calculation process.
The foregoing illustrates and describes the principles, general features, and advantages of the present invention. It should be understood by those skilled in the art that the above embodiments do not limit the present invention in any way, and all technical solutions obtained by using equivalent alternatives or equivalent variations fall within the scope of the present invention.
Claims (5)
1. A potential customer mining and customer type selection method based on a hybrid recommendation algorithm is characterized by comprising the following steps:
s1: collecting user data and extracting data characteristics to build a data model;
s2: selecting different algorithms for algorithm analysis and taking specific gravity values of the labels for algorithm integration aiming at different data characteristic labels; wherein the content of the first and second substances,
judging whether the user is interested in the product before the point by using a jacard formula according to the similarity between the users and searching a similarity algorithm between individual users;
calculating the probability of the interest of the user in the product by using a Euclidean algorithm according to the scores of the user on different products;
aiming at a user with the same hobbies and purchasing tendency as the user, judging whether the product has a purchasing tendency by using a CF algorithm based on the user;
judging whether the user has a purchasing tendency to the product or not by using a CF algorithm based on the product aiming at the type of the user who purchases the product;
s3: and outputting an algorithm result.
2. The hybrid recommendation algorithm-based potential customer mining and customer typing method according to claim 1,
and performing algorithm analysis aiming at the user group characteristics, performing support vector machine algorithm processing on the behavior data, and performing association rule algorithm processing on the identity and the industry characteristics of the user.
3. The hybrid recommendation algorithm-based potential customer mining and customer typing method according to claim 2,
and carrying out score comparison processing on different characteristics and algorithms.
4. A potential customer mining and customer type selection method based on a hybrid recommendation algorithm is characterized by comprising the following steps:
s1: collecting user data and extracting data characteristics to build a data model;
s2: selecting different algorithms for algorithm analysis and taking specific gravity values of the labels for algorithm integration aiming at different data characteristic labels;
s3: and outputting an algorithm result.
5. The hybrid recommendation algorithm-based potential customer mining and customer typing method according to claim 4,
algorithms used include jacard's formula, euclidean algorithm, customer-based CF algorithm, and product-based CF algorithm.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911113155.5A CN110930184A (en) | 2019-11-14 | 2019-11-14 | Potential customer mining and customer type selection method based on mixed recommendation algorithm |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911113155.5A CN110930184A (en) | 2019-11-14 | 2019-11-14 | Potential customer mining and customer type selection method based on mixed recommendation algorithm |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110930184A true CN110930184A (en) | 2020-03-27 |
Family
ID=69853032
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911113155.5A Pending CN110930184A (en) | 2019-11-14 | 2019-11-14 | Potential customer mining and customer type selection method based on mixed recommendation algorithm |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110930184A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107451748A (en) * | 2017-08-10 | 2017-12-08 | 北京奇鱼时代科技有限公司 | Client high sea management method in a kind of CRM system |
| CN114387064A (en) * | 2022-01-13 | 2022-04-22 | 福州大学 | E-commerce platform potential customer recommendation method and system based on comprehensive similarity |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104809243A (en) * | 2015-05-15 | 2015-07-29 | 东南大学 | Mixed recommendation method based on excavation of user behavior compositing factor |
| US20160162974A1 (en) * | 2014-12-08 | 2016-06-09 | Lg Cns Co., Ltd. | Personalized recommendation method and system, and computer-readable record medium |
| CN108876537A (en) * | 2018-06-15 | 2018-11-23 | 重庆知遨科技有限公司 | A kind of mixed recommendation method for on-line mall system |
| CN109615466A (en) * | 2018-11-27 | 2019-04-12 | 浙江工商大学 | The mixed method of commending contents and collaborative filtering recommending towards mobile ordering system |
-
2019
- 2019-11-14 CN CN201911113155.5A patent/CN110930184A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20160162974A1 (en) * | 2014-12-08 | 2016-06-09 | Lg Cns Co., Ltd. | Personalized recommendation method and system, and computer-readable record medium |
| CN104809243A (en) * | 2015-05-15 | 2015-07-29 | 东南大学 | Mixed recommendation method based on excavation of user behavior compositing factor |
| CN108876537A (en) * | 2018-06-15 | 2018-11-23 | 重庆知遨科技有限公司 | A kind of mixed recommendation method for on-line mall system |
| CN109615466A (en) * | 2018-11-27 | 2019-04-12 | 浙江工商大学 | The mixed method of commending contents and collaborative filtering recommending towards mobile ordering system |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107451748A (en) * | 2017-08-10 | 2017-12-08 | 北京奇鱼时代科技有限公司 | Client high sea management method in a kind of CRM system |
| CN114387064A (en) * | 2022-01-13 | 2022-04-22 | 福州大学 | E-commerce platform potential customer recommendation method and system based on comprehensive similarity |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109299370B (en) | Multi-pair level personalized recommendation method | |
| CN107944911B (en) | Recommendation method of recommendation system based on text analysis | |
| CN108805598B (en) | Similarity information determination method, server and computer-readable storage medium | |
| CN106959966A (en) | A kind of information recommendation method and system | |
| CN112102029B (en) | Knowledge graph-based long-tail recommendation calculation method | |
| CN106408377A (en) | Shopping recommended method and system | |
| CN110147483A (en) | A kind of title method for reconstructing and device | |
| CN110956210B (en) | Semi-supervised network water force identification method and system based on AP clustering | |
| CN103970801B (en) | Microblogging advertisement blog article recognition methods and device | |
| CN110930184A (en) | Potential customer mining and customer type selection method based on mixed recommendation algorithm | |
| CN103577472B (en) | Personal information acquisition, presumption, the classification of commodity, search method and system | |
| CN105279148A (en) | User review consistency judgment method of APP (Application) software | |
| CN116596570A (en) | Information comparison system of same product in different E-commerce platforms based on big data analysis algorithm | |
| CN115115435A (en) | E-commerce recommendation algorithm based on diversity | |
| CN111274492A (en) | Information recommendation method, information recommendation device and computer readable storage medium | |
| CN106980613B (en) | Search navigation method and device | |
| CN111026976A (en) | Identification method for microblog specific event attention group | |
| CN104268214B (en) | A kind of user's gender identification method and system based on microblog users relation | |
| CN111368131B (en) | User relationship identification method and device, electronic equipment and storage medium | |
| RU2014150563A (en) | SYSTEM AND METHOD FOR FORMING A CIRCLE OF COMMUNICATION AND A COMPUTER MEDIA | |
| CN110634051B (en) | Fresh agricultural product recommendation method based on multi-granularity fuzzy data | |
| CN105512914B (en) | Information processing method and electronic equipment | |
| CN110555210A (en) | product feature analysis method based on user viewpoint and emotion score | |
| CN103793504B (en) | A kind of cluster initial point system of selection based on user preference and item attribute | |
| Meida et al. | Pattern of E-marketplace customer shopping behavior using Tabu search and FP-growth algorithm |
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 |
Application publication date: 20200327 |
|
| RJ01 | Rejection of invention patent application after publication |