CN114445099A - Returned freight insurance pricing method, pricing system and construction method thereof - Google Patents
Returned freight insurance pricing method, pricing system and construction method thereof Download PDFInfo
- Publication number
- CN114445099A CN114445099A CN202011190847.2A CN202011190847A CN114445099A CN 114445099 A CN114445099 A CN 114445099A CN 202011190847 A CN202011190847 A CN 202011190847A CN 114445099 A CN114445099 A CN 114445099A
- Authority
- CN
- China
- Prior art keywords
- return
- pricing
- data
- price
- customer
- 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
- 238000000034 method Methods 0.000 title claims abstract description 62
- 238000010276 construction Methods 0.000 title abstract description 9
- 230000006399 behavior Effects 0.000 claims description 34
- 238000011156 evaluation Methods 0.000 claims description 9
- 238000004590 computer program Methods 0.000 claims description 6
- 230000035945 sensitivity Effects 0.000 claims description 6
- 238000007477 logistic regression Methods 0.000 claims description 3
- 238000007637 random forest analysis Methods 0.000 claims description 3
- 230000003542 behavioural effect Effects 0.000 claims 1
- 238000005406 washing Methods 0.000 claims 1
- 238000004364 calculation method Methods 0.000 abstract description 4
- 238000007418 data mining Methods 0.000 description 6
- 230000009286 beneficial effect Effects 0.000 description 4
- 238000004422 calculation algorithm Methods 0.000 description 4
- 238000007781 pre-processing Methods 0.000 description 4
- 238000004140 cleaning Methods 0.000 description 3
- 230000002159 abnormal effect Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 238000012502 risk assessment Methods 0.000 description 1
- 238000007619 statistical method Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
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
- G06Q30/0206—Price or cost determination based on market factors
-
- 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
-
- 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
- G06Q40/00—Finance; Insurance; Tax strategies; Processing of corporate or income taxes
- G06Q40/08—Insurance
Landscapes
- Business, Economics & Management (AREA)
- Engineering & Computer Science (AREA)
- Accounting & Taxation (AREA)
- Finance (AREA)
- Strategic Management (AREA)
- Development Economics (AREA)
- Entrepreneurship & Innovation (AREA)
- General Business, Economics & Management (AREA)
- Economics (AREA)
- Marketing (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Game Theory and Decision Science (AREA)
- Data Mining & Analysis (AREA)
- Technology Law (AREA)
- Financial Or Insurance-Related Operations Such As Payment And Settlement (AREA)
Abstract
The invention belongs to the field of return freight insurance pricing, and particularly relates to a return freight insurance pricing method, a pricing system and a construction method thereof, wherein the return freight insurance pricing method comprises the following steps: predicting the return probability of the current commodity for the customer by adopting a return probability prediction model based on the behavior data and the purchase data of the current commodity for the customer; and (5) bringing the return probability into a profit maximization objective function, and calculating the return freight insurance price. Secondly, the optimal price obtained by the pricing method is used as a soft price target, the behavior data and the purchase data are used, the return probability prediction model takes the return freight insurance price as a prediction target, the error between the model prediction price and the soft price target is calculated, and the model parameters are optimized to obtain the pricing system of each customer, wherein the pricing system is used for pricing the return freight insurance corresponding to the customer. The method fully utilizes the abundant and large amount of customer behavior data and historical data owned by the business enterprises, can obtain the optimal pricing decision step by step, does not need manual participation, and has high calculation efficiency.
Description
Technical Field
The invention belongs to the field of return freight insurance pricing, and particularly relates to a return freight insurance pricing method, a pricing system and a construction method of the return freight insurance pricing system.
Background
With the increasing popularity of online shopping, online orders of e-commerce enterprises are increasing, and statistical surveys show that on average, one return order is generated from three orders. There are many reasons why customers choose to return goods, quality problems of goods, regret after the customer impulse to buy, goods not in line with the customer expectations, etc. The returned freight insurance is a novel insurance type proposed by insurance enterprises and E-commerce enterprises for solving the loss caused by returned goods. The consumer can voluntarily purchase the return freight insurance when purchasing the product and placing the order online, and if the insurance is purchased, the order is returned for any reason, and the return freight will be borne by the insurance company. The partial online retailers of the partial platforms give return freight insurance to the consumers, thereby improving the service level and increasing the sales volume.
Insurance companies that provide return freight insurance services as third parties need risk assessment and management to develop pricing strategies for return freight insurance, including premium and reimbursement costs. The price setting method of the freight insurance provided by the current online platform is single, the compensation cost is generally 8-12 RMB, and the premium is simply determined according to the return rate of the consumer in the previous period. Although the current freight return insurance pricing method is effective to some extent, it does not take into account the background of e-commerce and its characteristics sufficiently, nor does it satisfy the needs of consumers (especially their psychological needs) nor maximize the profit of insurance companies.
Disclosure of Invention
The invention provides a return freight insurance pricing method, a pricing system and a construction method thereof, which are used for solving the technical problem that the existing return freight insurance pricing cannot effectively take the demands of consumers and insurance profits into consideration.
The technical scheme for solving the technical problems is as follows: a method of return freight insurance pricing, comprising:
predicting the return probability of the current commodity for the customer by adopting a return probability prediction model based on the behavior data and the purchase data of the current commodity for the customer; bringing the return probability into an objective function with the profit maximization as the target, and calculating the return freight insurance price;
the behavior data comprises data formed by current commodity information and behavior information generated by behaviors of clicking commodities, collecting commodities and adding the commodities into a shopping cart; the purchase data includes the order quantity, order amount, quantity of returned orders, returned merchandise information and returned amount paid by the customer on the online platform.
The invention has the beneficial effects that: the method is a pricing method based on a big data mining algorithm, and the method fully utilizes abundant and mass customer behavior data and historical data of the merchant and enterprise, evaluates the return probability of customers through a prediction model, meets the requirements of consumers, can also maximize the profits of insurance companies, and is a novel and effective return freight risk pricing method.
On the basis of the technical scheme, the invention can be further improved as follows.
Further, the construction method of the return probability prediction model comprises the following steps:
adopting the behavior data and the purchasing data of a plurality of customers for each commodity to construct a training set and a prediction set; training a plurality of models by adopting the training set, and selecting a model with the highest prediction precision as a return probability prediction model by adopting the prediction set;
the plurality of models includes: multilayer perceptrons, random forests, and logistic regression.
The invention has the further beneficial effects that: a training set and a prediction set are constructed in advance, a plurality of models are trained through the training set, and a model with better prediction performance is selected by the prediction set to serve as a return probability prediction model, so that the objectivity of return freight insurance pricing is improved.
Further, before the behavior data and the purchase data are adopted, cleaning, duplicate removal and null removal preprocessing are carried out on the behavior data and the purchase data.
Further, the objective function is: pi ═ pD (P, r) -PrC；
Wherein P represents the return freight price of the commodity, C is the compensation fee, PrAnd D (p, r) ═ alpha-beta p-gamma r represents the purchase intention of the customer when the goods evaluation index is r under the condition that the return freight risk price is p, wherein alpha is the basic purchase probability, and beta and gamma are sensitivity indexes.
The invention also provides a construction method of the return freight insurance pricing system, which comprises the following steps:
acquiring a plurality of data samples corresponding to orders placed by target customers, wherein each data sample comprises behavior data and purchase data of the target customers for corresponding commodities in the return freight insurance pricing method;
based on each data sample, adopting the return freight insurance pricing method to obtain the return freight insurance price of the commodity corresponding to the data sample;
and (3) forming a training sample data by each data sample and the corresponding return freight insurance price to obtain a training sample set, inputting the training sample set into the return probability prediction model in the return freight insurance pricing method, and training to obtain the return freight insurance pricing model as a return freight insurance pricing system of the target customer by taking the return freight insurance price as a prediction target.
The invention has the beneficial effects that: the optimal price obtained by the pricing method is the most expensive soft target, the selected data mining model takes the return freight insurance price as a prediction target, and the error between the price predicted by the model and the price soft target is calculated to minimize an error function, so that model parameters are optimized, a final pricing system is obtained, the construction efficiency of the pricing system is improved, and meanwhile, a pricing system is established for each customer, so that the method is strong in pertinence and reasonable in pricing.
The invention also provides a return freight insurance pricing method, which is used for obtaining the behavior data and the purchase data of the current commodity of the target customer, inputting the return freight insurance pricing system of the target customer obtained by the method, obtaining the return freight insurance price of the current commodity of the target customer and finishing the return freight insurance pricing of the current commodity of the target customer.
The invention has the beneficial effects that: by adopting the pricing system of each client, the optimal pricing decision can be obtained step by step without manual participation, the system automatically gives the optimal return freight insurance price for each client, and the calculation efficiency is high.
The present invention also provides a computer-readable storage medium, characterized in that the computer-readable storage medium comprises a stored computer program, wherein the computer program, when executed by a processor, controls a device on which the storage medium is located to perform a return freight risk pricing method as described above, a method of constructing a return freight risk pricing system as described above, and/or a return freight risk pricing method as described above.
Drawings
Fig. 1 is a block diagram of a flow chart of a return freight insurance pricing method according to an embodiment of the present invention;
FIG. 2 is a flow chart of a return freight insurance pricing system according to an embodiment of the present invention;
fig. 3 is a flowchart of an implementation of a return freight insurance pricing system according to an embodiment of 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. In addition, the technical features involved in the embodiments of the present invention described below may be combined with each other as long as they do not conflict with each other.
Example one
A method for pricing return shipping insurance, as shown in fig. 1, comprising:
predicting the return probability of the current commodity for the customer by adopting a return probability prediction model based on the behavior data and the purchase data of the current commodity for the customer; and (4) bringing the return probability into an objective function with the goal of maximizing profits, and calculating the return freight insurance price.
The behavior data comprises data formed by current commodity information and behavior information generated by behaviors of clicking commodities, collecting commodities and adding the commodities into a shopping cart; the purchase data includes the number of orders, the amount of the orders, the number of return orders, return merchandise information, and the amount of the returns paid by the customer on the online platform.
The method is a pricing method based on a big data mining algorithm, and the method fully utilizes abundant and mass customer behavior data and historical data of the merchant and enterprise, evaluates the return probability of customers through a prediction model, meets the requirements of consumers, can also maximize the profits of insurance companies, and is a novel and effective return freight risk pricing method.
Preferably, the method for constructing the return probability prediction model includes:
adopting behavior data and purchase data of a plurality of customers for each commodity to construct a training set and a prediction set; training a plurality of models by adopting a training set, and selecting a model with the highest prediction precision by adopting a prediction set as a return probability prediction model; the plurality of models includes: multilayer perceptrons, random forests, and logistic regression.
A training set and a prediction set are constructed in advance, a plurality of models are trained through the training set, and a model with better prediction performance is selected by the prediction set to serve as a return probability prediction model, so that the objectivity of return freight insurance pricing is improved.
Preferably, the behavior data and the purchase data are preprocessed by cleaning, deduplication and null before being used.
Preferably, the objective function is: pi ═ pD (P, r) -PrC；
Wherein P represents the return freight price of the commodity, C is the compensation fee, PrAnd D (p, r) ═ alpha-beta p-gamma r represents the purchase intention of the customer when the goods evaluation index is r under the condition that the return freight risk price is p, wherein alpha is the basic purchase probability, and beta and gamma are sensitivity indexes. The commodity evaluation index can be obtained by statistically analyzing the evaluation information of the commodity, and the sensitivity index can be obtained by statistically analyzing the customer history data.
Example two
A method for constructing a return freight insurance pricing system comprises the following steps:
obtaining a plurality of data samples corresponding to orders placed by target customers, wherein each data sample comprises behavior data and purchase data of the target customers for corresponding commodities in the return freight insurance pricing method in the embodiment I;
based on each data sample, adopting the return freight insurance pricing method as described in the first embodiment to obtain the return freight insurance price of the commodity corresponding to the data sample;
each data sample and the corresponding return freight insurance price form a training sample data to obtain a training sample set, and the training sample set is input into the return probability prediction model in the return freight insurance pricing method in the embodiment one, and the return freight insurance pricing model is trained to obtain the return freight insurance pricing model as a return freight insurance pricing system of the target customer by taking the return freight insurance price as a prediction target.
The optimal price obtained by the pricing method in the first embodiment is the most expensive soft target, the selected data mining model takes the return freight risk price as a prediction target, and the error between the price predicted by the model and the price soft target is calculated to minimize an error function, so that model parameters are optimized, and a final pricing system is obtained.
For example, fig. 2 is a schematic flow chart of the construction of a return freight insurance pricing system based on big data technology according to the present embodiment, and as shown in fig. 2, the method includes the following steps:
step 1, extracting and preprocessing customer behavior data and historical data.
A large amount of customer behavior data and historical data are stored in a network log of a platform on an e-commerce enterprise line, and are data left by corresponding operations of consumers on an e-commerce website. The data are extracted from the weblog for preprocessing, including cleaning, duplicate removal and null removal of the data, and non-universal data, abnormal data and the like are removed through preliminary statistics.
And 2, predicting the return probability of the customer and constructing a pricing model to obtain the optimal price suitable for the customer, and taking the optimal price as a soft target for training a pricing system.
In particular, the upper part of fig. 3 depicts a flow chart of a specific implementation of this step. Taking the processed data as input, selecting a prediction model which can be a certain data mining algorithm, taking a multilayer perceptron prediction model as an example, predicting whether a consumer returns goods or not as a prediction target by the prediction model, predicting the goods return probability of the consumer, applying the predicted goods return probability to price decision modelization to obtain an optimal price decision, and using the optimal price decision as a price soft target to guide the training of a pricing prediction model.
The objective function of the price decision model in this step is the profit function of each insurance company bill, and the formula is as follows:
π＝pD(p,r)-PrC
wherein P represents the premium of the single insurance, C is the reimbursement fee, PrAnd D (p, r) ═ alpha-beta p-gamma r represents the purchase intention of the customer when the return freight risk price is p and the product evaluation index is r, wherein alpha is the basic purchase probability, and beta and gamma are sensitivity indexes. Here, we can set the basic purchase probability α of the customer to 0.5, the commodity evaluation index can be obtained by calculating the good evaluation rate of the commodity, and the sensitivity index can be set to [0,1 ] by performing statistical analysis on the historical data of the customer]The numerical values within the interval.
Through the formula, the profit maximization is taken as an optimization target, the optimal pricing is obtained, and the optimal pricing is used as a price soft target for guiding and training a pricing system.
And 3, constructing a pricing system by using the obtained price soft target training price prediction model.
In particular, the lower half of fig. 3 depicts a flow chart of a specific implementation of this step. And (3) taking the data obtained in the step (1) as input, taking the return freight risk price as a prediction template, performing model training by using the price soft target obtained in the step (2), and optimizing model parameters by calculating the cross entropy between the price predicted by the model and the price soft target and minimizing an error function to obtain a final pricing system.
Therefore, the method is a pricing method based on a big data mining algorithm, and provides a one-step pricing system based on customer data. The method fully utilizes abundant and large amount of customer behavior data and historical data of the merchant and enterprise, evaluates the return probability of the customer through a prediction model after preprocessing the customer behavior data and the historical data, takes profit maximization as a target, brings the return probability value of the customer into a target function, calculates to obtain the optimal return freight insurance price, finally takes the obtained optimal price as a price soft target, guides and trains a selected prediction model to take the return freight insurance price as the prediction target, and optimizes model parameters to obtain the final pricing system. The embodiment of the invention can effectively utilize the customer behavior data and the historical data, mine effective information from the data, optimize the return freight insurance price and construct an accurate and effective pricing system.
EXAMPLE III
A return freight insurance pricing method obtains behavior data and purchase data of a current commodity of a target client, inputs the behavior data and the purchase data into a return freight insurance pricing system of the target client obtained by the method in the second embodiment, obtains a return freight insurance price of the current commodity of the target client, and completes the return freight insurance pricing of the current commodity of the target client.
The system of the second embodiment can obtain the optimal pricing decision step by step without manual participation, has high calculation efficiency, and automatically gives the personalized optimal return freight insurance price for the client.
The pricing method and the system for the return freight insurance designed by the embodiment can effectively utilize the customer behavior data and the historical data, mine effective information from the data, and convert the effective information into the optimal price information through the price decision model so as to guide the training of the price prediction model and construct an accurate and effective pricing system. The pricing system constructed by the technical scheme can take the preprocessed customer behavior data and the historical data as input, so that the optimal return freight insurance pricing for each individual customer is obtained, and the profit of the insurance business is maximized. Different from the prior art, the pricing method provided by the document considers the influence of the evaluation index of the commodity on the return freight insurance purchase and digs the potential return willingness information of the customer from the big data to formulate a pricing scheme individualized for the individual customer. Meanwhile, the pricing system constructed by the method can acquire the optimal pricing decision step by step without manual participation, automatically gives the optimal return freight insurance price for individual customers, and is high in calculation efficiency.
Example four
A computer-readable storage medium comprising a stored computer program, wherein the computer program, when executed by a processor, controls a device on which the storage medium resides to perform a method for pricing return freight insurance according to embodiment one, a method for constructing a system for pricing return freight insurance according to embodiment two, and/or a method for pricing return freight insurance according to embodiment three.
The related technical solutions are the same as those in the first to third embodiments, and are not described herein again.
It will be understood by those skilled in the art that the foregoing is only an exemplary embodiment of the present invention, and is not intended to limit the invention to the particular forms disclosed, since various modifications, substitutions and improvements within the spirit and scope of the invention are possible and within the scope of the appended claims.
Claims (7)
1. A method for pricing return freight insurance, comprising:
predicting the return probability of the current commodity for the customer by adopting a return probability prediction model based on the behavior data and the purchase data of the current commodity for the customer; bringing the return probability into an objective function with the profit maximization as the target, and calculating the return freight insurance price;
the behavior data comprises data formed by current commodity information and behavior information generated by behaviors of clicking commodities, collecting commodities and adding the commodities into a shopping cart; the purchase data includes the order quantity, order amount, quantity of returned orders, returned merchandise information and returned amount paid by the customer on the online platform.
2. A return freight risk pricing method according to claim 1, wherein the return probability prediction model is constructed by:
adopting the behavior data and the purchasing data of a plurality of customers for each commodity to construct a training set and a prediction set; training a plurality of models by adopting the training set, and selecting a model with the highest prediction precision as a return probability prediction model by adopting the prediction set;
the plurality of models includes: multilayer perceptrons, random forests, and logistic regression.
3. A method for pricing return freight insurance according to claim 2, characterized in that the behavioural data and the purchase data are preprocessed by washing, deduplication and emptying before they are used.
4. A method for pricing return freight insurance according to claim 1, wherein the objective function is: pi ═ pD (P, r) -PrC；
Wherein P represents the return freight price of the goods, C is the compensation cost, PrAnd D (p, r) ═ alpha-beta p-gamma r represents the purchase intention of the customer when the goods evaluation index is r under the condition that the return freight risk price is p, wherein alpha is the basic purchase probability, and beta and gamma are sensitivity indexes.
5. A method for constructing a return freight insurance pricing system is characterized by comprising the following steps:
obtaining a plurality of data samples corresponding to orders placed by target customers, wherein each data sample comprises behavior data and purchase data of the target customers for corresponding commodities in the return freight insurance pricing method according to any one of claims 1 to 4;
obtaining a return freight insurance price of the commodity corresponding to each data sample by adopting a return freight insurance pricing method according to any one of claims 1 to 4 on the basis of each data sample;
each data sample and the corresponding return freight insurance price form a training sample data to obtain a training sample set, and the training sample set is input into the return probability prediction model in the return freight insurance pricing method according to any one of claims 1 to 4, and the return freight insurance pricing model is trained to obtain as a return freight insurance pricing system of the target customer by taking the return freight insurance price as a prediction target.
6. A return freight insurance pricing method is characterized in that the behavior data and the purchase data of the current goods of a target customer are obtained, the return freight insurance pricing system of the target customer obtained by the method of claim 5 is input, the return freight insurance price of the current goods of the target customer is obtained, and the return freight insurance pricing of the current goods of the target customer is completed.
7. A computer-readable storage medium, comprising a stored computer program, wherein the computer program, when executed by a processor, controls a device on which the storage medium resides to perform a method of pricing return shipping costs according to any of claims 1 to 4, a method of constructing a system of pricing return shipping costs according to claim 5, and/or a method of pricing return shipping costs according to claim 6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011190847.2A CN114445099A (en) | 2020-10-30 | 2020-10-30 | Returned freight insurance pricing method, pricing system and construction method thereof |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011190847.2A CN114445099A (en) | 2020-10-30 | 2020-10-30 | Returned freight insurance pricing method, pricing system and construction method thereof |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114445099A true CN114445099A (en) | 2022-05-06 |
Family
ID=81358014
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011190847.2A Pending CN114445099A (en) | 2020-10-30 | 2020-10-30 | Returned freight insurance pricing method, pricing system and construction method thereof |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114445099A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116433145A (en) * | 2023-03-10 | 2023-07-14 | 广州手拉手互联网股份有限公司 | E-commerce data monitoring and order management method and system |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR20000054642A (en) * | 2000-06-15 | 2000-09-05 | 임성식 | Business Protection System for E-Commerce |
| CN104866540A (en) * | 2015-05-04 | 2015-08-26 | 华中科技大学 | Personalized recommendation method based on group user behavior analysis |
| CN105574599A (en) * | 2014-10-09 | 2016-05-11 | 阿里巴巴集团控股有限公司 | Method and apparatus for estimating sales return rate of order |
| CN107274191A (en) * | 2017-05-12 | 2017-10-20 | 南京邮电大学 | A kind of shopping at network return of goods forecasting system based on seller |
| CN110009154A (en) * | 2019-04-03 | 2019-07-12 | 深圳威狮物流网络科技有限公司 | A kind of reimbursement prediction technique, device, terminal device and storage medium |
-
2020
- 2020-10-30 CN CN202011190847.2A patent/CN114445099A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR20000054642A (en) * | 2000-06-15 | 2000-09-05 | 임성식 | Business Protection System for E-Commerce |
| CN105574599A (en) * | 2014-10-09 | 2016-05-11 | 阿里巴巴集团控股有限公司 | Method and apparatus for estimating sales return rate of order |
| CN104866540A (en) * | 2015-05-04 | 2015-08-26 | 华中科技大学 | Personalized recommendation method based on group user behavior analysis |
| CN107274191A (en) * | 2017-05-12 | 2017-10-20 | 南京邮电大学 | A kind of shopping at network return of goods forecasting system based on seller |
| CN110009154A (en) * | 2019-04-03 | 2019-07-12 | 深圳威狮物流网络科技有限公司 | A kind of reimbursement prediction technique, device, terminal device and storage medium |
Non-Patent Citations (1)
| Title |
|---|
| 王丹: "基于信息不对称的退货运费险的定价模型研究", CNKI优秀硕士学位论文全文库, 15 April 2017 (2017-04-15), pages 5 - 6 * |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116433145A (en) * | 2023-03-10 | 2023-07-14 | 广州手拉手互联网股份有限公司 | E-commerce data monitoring and order management method and system |
| CN116433145B (en) * | 2023-03-10 | 2023-12-19 | 广州手拉手互联网股份有限公司 | E-commerce data monitoring and order management method and system |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US9165270B2 (en) | Predicting likelihood of customer attrition and retention measures | |
| Kikkawa et al. | Imperfect competition in firm-to-firm trade | |
| US8442854B2 (en) | System and method for estimating residual lifetime value of a customer base utilizing survival analysis | |
| US7392221B2 (en) | Methods and systems for identifying early terminating loan customers | |
| US8620763B2 (en) | System, method and computer program product for demand-weighted selection of sales outlets | |
| KR101061094B1 (en) | Information providing and selling system for used car on network | |
| US20100145772A1 (en) | System and Method for Analyzing Customer Segments | |
| KR102018679B1 (en) | Method for Evaluating Technological Value of Intellectual Property | |
| WO2011050371A1 (en) | System and method for generating product decisions | |
| WO2012058655A2 (en) | System and method for modeling by customer segments | |
| Elmaghraby et al. | Sales force behavior, pricing information, and pricing decisions | |
| CN116579809B (en) | Aggregate payment system based on cloud computing | |
| KR20230122524A (en) | Method for credit evaluation based on end-to-end data generated on process of purchase, sales, inventory, logistics, distribution and calculation on ECS(e-commerce solution) and apparatus for performing the method | |
| CN115147144A (en) | Data processing method and electronic equipment | |
| CN114445099A (en) | Returned freight insurance pricing method, pricing system and construction method thereof | |
| CN117252614A (en) | Cross-border electronic commerce dynamic pricing method based on deep reinforcement learning | |
| CN117333262A (en) | Big data demand prediction method and system based on artificial intelligence for electronic commerce platform | |
| KR101677316B1 (en) | Method of evaluating Brand value using substantial value-oriented method | |
| US20130090983A1 (en) | System and method for tiered offer forecasting | |
| Rabinovich et al. | Omnichannel retailing as a balancing act between in-store and home fulfillment | |
| CN118469677B (en) | Order purchase platform based on cloud computing | |
| Singh et al. | Managerial Efficiency of Production System with Price-Sensitive Demand. | |
| Cao | E-commerce Platform Risk Identification Using AHP Hierarchical Analysis and BPNN Neural Network | |
| Hellström | Multiple linear regression for predicting payment time in factoring | |
| CN113256098A (en) | Electric power data credit investigation product pricing method based on customer utility |
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 |