Online car-hailing platform marketing activity cost estimation method
Through the preprocessing of the order completion data of the online car-hailing platform and the planning of the order-returning parameters, combined with the monitoring mechanism and data correlation analysis, the problems of inaccurate cost estimates of marketing activities and insufficient driver stickiness of the online car-hailing platform are solved. , achieving more efficient marketing effects and cost control.
Patent Information
- Application Number
- CN202410929784.X
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-07-11
- Publication Date
- 2024-11-08
AI Technical Summary
The unstable income of online ride-hailing drivers, fierce competition and insufficient stickiness, make it difficult for the platform to effectively control the cost of marketing activities and affect marketing effectiveness.
By preprocessing and analyzing the platform's completed order data, planning the core parameters of order-for-return awards, setting monitoring mechanisms and early warning mechanisms, evaluating the effectiveness of marketing activities and adjusting strategies, and using Pearson's correlation coefficient for data correlation analysis to optimize marketing strategies.
It improves the accuracy and cost control of marketing activities, enhances driver stickiness and platform order volume, optimizes marketing strategies, and achieves higher performance and goals.
Smart Images

Figure CN118917872A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the field of data analysis and monitoring, and more specifically, to a method for estimating the cost of marketing activities on an online car-hailing platform. Background Art
[0002] With the popularization of mobile Internet and the rise of the sharing economy, online ride-hailing has grown rapidly, solving various problems in the traditional taxi industry and meeting people's needs for convenient, economical and high-quality travel.
[0003] In recent years, the scale of online ride-hailing has gradually become saturated, and the market has entered an era of inventory. The stickiness of drivers has been affected to a certain extent. Factors such as unstable income, price wars, fierce competition, unstable service quality, and insufficient protection of driver rights have led to insufficient driver stickiness, making it easy for drivers to switch between different platforms and even eventually leave.
[0004] The income of online ride-hailing drivers is usually calculated based on the number and quality of completed orders, so it is greatly affected by the market and competition, and the income is unstable. In addition, as the online ride-hailing market gradually matures, competition has become increasingly fierce. Drivers and passengers have more choices, and competition between platforms has become more intense, which has also made it easier for drivers to switch to other platforms.
[0005] In order to improve the stickiness of drivers on online ride-hailing platforms and increase their activity, the platforms often take a variety of measures to ensure that drivers have a stable income and provide a better work experience. First, the platform can increase the income of drivers by providing a stable order volume and a reasonable pricing mechanism. Secondly, it can improve the interactive experience between passengers and drivers and improve service quality, including perfect customer service support, quick response to complaints and problem solving, and the establishment of good communication channels, so that drivers can feel the platform's care and support for them.
[0006] Before an online ride-hailing platform conducts a marketing campaign, it usually needs to estimate the subsidy cost of the campaign to control the budget and maximize the campaign effect within a certain budget. Compared with the model-based approach, this method is faster to implement overall and has low estimation overhead, while maintaining an estimation accuracy comparable to that of the model, providing a basis for online ride-hailing operators to evaluate campaign effects and control campaign costs. Summary of the invention
[0007] In view of the technical problems existing in the prior art, the present invention provides a method for estimating the cost of marketing activities of an online car-hailing platform to solve the problems raised in the above-mentioned background technology.
[0008] The technical solution of the present invention to solve the above technical problem is as follows: A method for estimating the cost of marketing activities on an online car-hailing platform comprises the following steps:
[0009] S101. Preprocess the platform's order volume data, observe changes in the platform's order volume data, and analyze the volatility and trend of the platform's order volume data between different natural weeks and dates;
[0010] S102. Plan the core parameters of the order-boosting bonus, and calculate the sum of the backtest values of each driver based on the core parameters of the order-boosting bonus to estimate the cost of the marketing activities of the online car-hailing platform;
[0011] S103. Set up a monitoring mechanism to track the effectiveness of online ride-hailing platform marketing activities and make timely adjustments, and establish an early warning mechanism;
[0012] S104. Evaluate the effectiveness of online ride-hailing platform marketing activities through data analysis and adjust the next stage of marketing strategy based on the results;
[0013] In a preferred embodiment, in S101, the actual amount of reward received by the driver in the marketing activities of the online car-hailing platform is positively correlated with the number of orders completed on the platform on that day, the estimated amount of marketing activity subsidy is consistent with the estimated number of orders completed on the platform, the order database API of the online car-hailing platform is connected to observe the changes in the platform's order data, and the volatility and trend of the platform's order data between different natural weeks and dates are analyzed, and the specific steps are:
[0014] A1. Check whether there are null values and missing values in the platform's order volume data, whether the value range of the platform's order volume data is within the valid range, and whether there are abnormalities and duplicate records in the platform's order volume data.
[0015] A2. Group the platform order volume data according to different natural weeks and dates, and summarize the platform order volume data for each natural week group and date group. Draw a bar chart to show the change trend of the platform order volume data and mark the total number of platform order volume for each natural week group and date group. The change trend of the platform order volume data is superimposed on the overall change trend of the date and the cyclical change trend of the natural week. According to the bar chart analysis, the platform order volume data has an overall upward or downward trend over time, and a trend line is added to the bar chart.
[0016] In a preferred embodiment, in said S102, the core parameters of the planned order-buying reward are effective driver parameters, effective order parameters, platform order completion requirements and corresponding reward amounts, wherein the order-buying reward is a reward mechanism in marketing activities, and the activity marketing of the order-buying reward to drivers in the online car-hailing scenario is aimed at encouraging drivers to accept orders more frequently within a certain period of time to obtain rewards. By marketing the order-buying reward to drivers, it can attract drivers to increase their driving time and increase their desire to accept orders, thereby increasing driver income and platform order completion. At the same time, it can also enhance the interaction and relationship between users and brands, bring more word-of-mouth communication and driver stickiness to the company, and divide the effective driver parameters into a circled driver set. Parameters, blacklist driver set parameters, driver service score requirement parameters and driver franchise type requirement parameters. According to the valid driver parameters, the final valid drivers are determined to be the drivers who are circled and not blacklisted, and meet the service score, franchise type and other requirements. The valid order parameters are divided into order time requirement parameters and whether the carpooling order, special flat-price order and stop-by order are valid. According to the valid order parameters, the final valid order is determined to be the part of the completed orders that meet all the order requirement parameters among the reached drivers. The platform's completed order requirements and the corresponding reward amount are configured in a step-by-step manner. The sum of the backtest values of each driver is calculated according to the core parameters of the rush order reward, which is the estimated cost of the marketing activities of the online car-hailing platform.
[0017] In a preferred embodiment, in S103, a monitoring mechanism is set to track the effectiveness of the marketing activities of the online ride-hailing platform and make timely adjustments, the monitoring indicators are determined to be the platform's order completion data and the core parameters of the order bonus, and the monitoring indicator frequency is set in days. The corresponding values of 50% and 100% of the budget cost are set as specific thresholds. When the estimated cost of the marketing activities of the online ride-hailing platform exceeds the first specific threshold, an early warning is issued. When the estimated cost of the marketing activities of the online ride-hailing platform exceeds the first specific threshold, the relevant staff is notified immediately.
[0018] In a preferred embodiment, in S104, the effect of the marketing activities of the online car-hailing platform is evaluated through data analysis, and the marketing strategy for the next stage is adjusted according to the results. The order completion database API, order bonus core parameter database API, user participation database API and sales database API of the online car-hailing platform are connected, and the platform order completion data, order bonus core parameter data, user participation data and sales data are selected through the Pearson correlation coefficient and correlation analysis is performed. The specific formula is:
[0019]
[0020] Where r represents the Pearson coefficient, cov(x,y) represents the covariance between the platform's order volume data, the core parameter data of the order reward, the user participation data and the sales data, Sd(x) and Sd(y) represent the standard deviation values between the platform's order volume data, the core parameter data of the order reward, the user participation data and the sales data, and the Pearson correlation coefficient ranges from -1 to 1. The closer the absolute value is to 1, the stronger the correlation is, and the closer it is to 0, the weaker the correlation is. The strength of the correlation is used to determine the impact between the platform's order volume data, the core parameter data of the order reward, the user participation data and the sales data.
[0021] The beneficial effects of the present invention are: by checking the null values, missing values, abnormal values and duplicate records of the platform's order volume data, and filling and cleaning the platform's order volume data, the accuracy and completeness of the platform's order volume data are ensured, the platform's order volume data is grouped by different natural weeks and dates, and a bar chart is drawn to show the data change trend, which helps to observe the volatility and trend of the platform's order volume in different time periods. The addition of trend lines helps to more clearly show the overall change trend of the data, and by describing the impact of the rush order reward activity on the driver's platform order volume, it is pointed out that the activity's reward mechanism can motivate drivers to accept orders more frequently. Through the analysis and trend display of the platform's order volume data, the effectiveness of marketing activities can be evaluated and the degree of influence of the activities on the platform's order volume can be understood. The display of bar charts and trend lines can intuitively present the changes in the platform's order volume data, helping analysts and decision makers to better understand the trends and periodic changes of the data. By listing the division of effective driver parameters and effective order parameters in detail, it helps to clarify the conditions and requirements of activity participants and ensure the effectiveness and goal achievement of the activity. According to the core parameters of the order reward, the amount of reward that each driver should receive on the previous day is calculated to evaluate the cost of the activity, which can reflect the actual income of the drivers participating in the activity and help evaluate the effectiveness and cost-effectiveness of the activity. Using the Pearson correlation coefficient for data association analysis can provide a deeper understanding of the correlation between different factors, so as to make targeted adjustments and decisions to improve the marketing effect and performance of the online car-hailing platform, more effectively optimize marketing strategies, and improve the success rate and effect of activities, so as to achieve better performance and goals. By determining the influence relationship between the platform's order volume data, the core parameter data of the order reward, the user participation data and the sales data, it helps you scientifically adjust the marketing strategy for the next stage, optimize the activity plan, improve the activity effect and achieve the expected goals. BRIEF DESCRIPTION OF THE DRAWINGS
[0022] Figure 1 is a flow chart of the method of the present invention;
[0023] Figure 2 The trend line of the present invention shows the change of the platform's order volume data within a certain period of time; DETAILED DESCRIPTION
[0024] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of this application.
[0025] In the description of this application, the terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of the features. In the description of this application, "plurality" means two or more, unless otherwise clearly and specifically defined.
[0026] In the description of the present application, the term "for example" is used to mean "used as an example, illustration or description". Any embodiment described as "for example" in the present application is not necessarily to be construed as being more preferred or advantageous than other embodiments. The following description is given to enable any technician in the field to implement and use the present invention. In the following description, details are listed for the purpose of explanation. It should be understood that a person of ordinary skill in the art can recognize that the present invention can be implemented without using these specific details. In other examples, well-known structures and processes will not be elaborated in detail to avoid unnecessary details to obscure the description of the present invention. Therefore, the present invention is not intended to be limited to the embodiments shown, but is consistent with the widest scope consistent with the principles and features disclosed in the present application.
[0027] Example 1
[0028] This embodiment provides Figure 1 A method for estimating the cost of marketing activities on an online car-hailing platform is shown, which specifically includes the following steps:
[0029] S101. Preprocess the platform's order volume data, observe changes in the platform's order volume data, and analyze the volatility and trend of the platform's order volume data between different natural weeks and dates;
[0030] Furthermore, the actual amount of bonuses received by drivers in the marketing activities of online ride-hailing platforms is positively correlated with the number of orders completed on the platform on that day. The estimated amount of subsidies for marketing activities is consistent with the estimated number of orders completed on the platform. The order completion database API of the online ride-hailing platform is connected to observe the changes in the platform's order completion data, and the volatility and trend of the platform's order completion data between different natural weeks and dates are analyzed to help online ride-hailing platform managers better understand the business operations of marketing activities. The specific steps are as follows:
[0031] A1. Check whether there are null values and missing values in the platform's order volume data, check whether the value range of the platform's order volume data is within the valid range, and check whether there are abnormal and duplicate records in the platform's order volume data. For null values and missing values in the platform's order volume data, delete the corresponding records of the platform's order volume data, and use the average value of the platform's order volume data to fill in the corresponding values. If the value range of the platform's order volume data is within the invalid range and there are abnormal and duplicate records, delete the corresponding records of the platform's order volume data. This helps to avoid incomplete platform order volume data during the analysis process, eliminate abnormal interference in the platform's order volume data, make the analysis results more reliable and accurate, and ensure the effectiveness of platform order volume data cleaning.
[0032] A2. Group the platform order volume data according to different natural weeks and dates, and summarize the platform order volume data of each natural week group and date group. Draw a bar chart to show the change trend of the platform order volume data and mark the total number of platform orders for each natural week group and date group. The change trend of the platform order volume data is superimposed on the overall change trend of the date and the periodic change trend of the natural week. From the platform order volume data of the date group, the order volume of a single driver or a group of drivers has periodic fluctuations with the natural week, and this volatility is similar between different natural weeks. For example, the platform order volume on Saturday is much higher than that on Friday. According to the bar chart analysis, the platform order volume data has an overall upward or downward trend over time. For example, the daily operation of the platform has steadily increased the order volume, or the overall order volume is higher due to the increase in passenger demand during holidays. Add a trend line to the bar chart to help analyze the change trend of the platform order volume and show the change of the platform order volume data within a certain period of time. Among them, the trend line shows the change of the platform order volume data within a certain period of time. Figure 2 , the horizontal axis represents the date, the 1st is Monday and so on, the vertical axis represents the platform's order volume on the date, the platform's order volume shows an overall growth trend, and the platform's order volume in the natural week has the same volatility, the order volume on weekends is higher than that on weekdays and falls on Monday, where it is assumed that a certain order-boosting reward activity on the Tth day is required to be estimated, and the set of drivers reached on the Tth day is S, cnt_ord_done_7 and cnt_ord_done_8 represent the platform's order volume on the 7th and 8th days of history, and Tn represents the n days before the Tth day, where the order-boosting reward is a reward mechanism in marketing activities, and the order-boosting reward activity marketing is carried out for drivers in the online car-hailing scenario to encourage drivers to accept orders more frequently within a certain period of time to obtain rewards.
[0033] S102. Plan the core parameters of the order-boosting bonus, and calculate the sum of the backtest values of each driver based on the core parameters of the order-boosting bonus to estimate the cost of the marketing activities of the online car-hailing platform;
[0034] Furthermore, the core parameters of the rush order reward are planned to be valid driver parameters, valid order parameters, platform order completion requirements and corresponding reward amounts. The valid driver parameters are divided into circled driver set parameters, blacklist driver set parameters, driver service score requirement parameters and driver franchise type requirement parameters. The final valid driver is determined to be the driver who is circled and not on the blacklist and meets the service score, franchise type and other requirements based on the valid driver parameters. The valid order parameters are divided into order time requirement parameters and whether carpooling orders, special fixed-price orders and on-the-way orders are valid. The final valid order is determined to be the reaching driver based on the valid order parameters. The part of the completed orders of the machine that meets all the order requirement parameters is configured in a step-by-step manner. For example, if the driver completes 10 orders on the same day, he will be rewarded 20 yuan. If the driver completes 20 orders on the same day, he will be rewarded 50 yuan. The highest reward is calculated on the same day and only rewarded once. The sum of the backtest values of each driver is calculated according to the core parameters of the rush order reward, that is, the cost estimate of the marketing activities of the online car-hailing platform. The backtest value is defined as if the driver i in S participated in the same activity on T-1, based on the reward rules of the activity, and the reward amount that driver i should receive on T-1 is calculated.
[0035] S103. Set up a monitoring mechanism to track the effectiveness of online ride-hailing platform marketing activities and make timely adjustments, and establish an early warning mechanism;
[0036] Furthermore, a monitoring mechanism is set up to track the effectiveness of the marketing activities of the online ride-hailing platform and make timely adjustments to improve effectiveness and cost-effectiveness. The monitoring indicators are determined as the platform's order completion data and the core parameters of the order bonus. The monitoring indicator frequency is set in days, and the corresponding values of 50% and 100% of the budget cost are set as specific thresholds. When the estimated cost of the marketing activities of the online ride-hailing platform exceeds the first specific threshold, an early warning is issued. When the estimated cost of the marketing activities of the online ride-hailing platform exceeds the first specific threshold, the relevant staff is notified immediately to help the management team understand the effectiveness of the marketing activities in a timely manner so as to make necessary adjustments and optimizations while effectively controlling costs.
[0037] S104. Evaluate the effectiveness of online ride-hailing platform marketing activities through data analysis and adjust the next stage of marketing strategy based on the results;
[0038] Furthermore, the order completion database API, order reward core parameter database API, user participation database API, and sales database API of the online car-hailing platform are connected to help you conduct a comprehensive data correlation analysis. The platform order completion data, order reward core parameter data, user participation data, and sales data are selected through the Pearson correlation coefficient and correlation analysis is performed. The specific formula is:
[0039]
[0040] Where r represents the Pearson coefficient, cov(x,y) represents the covariance between the platform's order volume data, the core parameter data of the order reward, the user participation data and the sales data, Sd(x) and Sd(y) represent the standard deviation values between the platform's order volume data, the core parameter data of the order reward, the user participation data and the sales data, and the Pearson correlation coefficient ranges from -1 to 1. The closer its absolute value is to 1, the stronger the correlation is, and the closer it is to 0, the weaker the correlation is. The strength of the correlation is used to determine the influence between the platform's order volume data, the core parameter data of the order reward, the user participation data and the sales data. The Pearson correlation coefficient can measure the degree of linear correlation between the two variable data, and determine the influence relationship between the platform's order volume data, the core parameter data of the order reward, the user participation data and the sales data, which will help you scientifically adjust the next stage of marketing strategies, optimize activity plans, improve activity effects and achieve expected goals.
[0041] Example 2
[0042] This embodiment provides Figure 1 A method for estimating the cost of marketing activities on an online car-hailing platform is shown. In order to verify the beneficial effects of the present invention, through the scheme of the present invention, the online car-hailing platform can more accurately evaluate the cost of each activity and control the budget. This embodiment evaluates the estimated effect of all activities for rushing orders within a certain period of time, specifically as shown in the following table:
[0043]
[0044]
[0045] Table 1: Estimated accuracy
[0046] Among them, the absolute error of the activity is the difference between the estimated value cost_pred and cost, that is, cost_pred-cost, and the relative error is (cost_pred-cost) / cost. The cost estimation method that estimates at the driver granularity, collects samples, trains models, and provides model services has relatively high costs and overheads. At the same time, after going online, the entire estimation process is complex to calculate, and the platform needs to wait for a long time to produce the estimation results, usually 1 minute. According to the effect data in the table, the effect of this embodiment is the same as that of the cost estimation method that collects samples, trains models, and provides model services. However, the calculation process of this embodiment is simple, and there is no need to maintain driver characteristics and models. The estimation overhead is low, and the estimation speed is faster.
[0047] It should be noted that in the above embodiments, the description of each embodiment has its own emphasis, and for parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.
[0048] Those skilled in the art will appreciate that embodiments of the present invention may be provided as methods, systems, or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.
[0049] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded computer, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.
[0050] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.
[0051] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 A step that specifies a function in one or more boxes.
[0052] Although the preferred embodiments of the present invention have been described, those skilled in the art may make other changes and modifications to these embodiments once they have learned the basic creative concept. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications that fall within the scope of the present invention.
[0053] Obviously, those skilled in the art can make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if these modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalents, the present invention is also intended to include these modifications and variations.
Claims
1. A method for estimating the cost of marketing activities on an online car-hailing platform, characterized in that: The specific steps include: S101. Preprocess the platform's order volume data, observe changes in the platform's order volume data, and analyze the volatility and trend of the platform's order volume data between different natural weeks and dates; S102. Plan the core parameters of the order-boosting bonus, and calculate the sum of the backtest values of each driver based on the core parameters of the order-boosting bonus to estimate the cost of the marketing activities of the online car-hailing platform; S103. Set up a monitoring mechanism to track the effectiveness of online ride-hailing platform marketing activities and make timely adjustments, and establish an early warning mechanism; S104. Evaluate the effectiveness of the online ride-hailing platform’s marketing activities through data analysis and adjust the next stage of marketing strategies based on the results.
2. A method for estimating the cost of marketing activities of an online car-hailing platform according to claim 1, characterized in that: In S101, the actual amount of bonus received by drivers in the marketing activities of the online ride-hailing platform is positively correlated with the number of orders completed on the platform on that day. The estimated subsidy amount for the marketing activities is consistent with the estimated number of orders completed on the platform. The order completion database API of the online ride-hailing platform is connected to observe the changes in the platform's order completion data, and the volatility and trend of the platform's order completion data between different natural weeks and dates are analyzed.
3. A method for estimating the cost of marketing activities of an online car-hailing platform according to claim 1, characterized in that: In S101, preprocessing the platform order completion data includes: checking whether there are null values and missing values in the platform order completion data, checking whether the value range of the platform order completion data is within the valid range, and checking whether there are abnormalities and duplicate records in the platform order completion data.
4. A method for estimating the cost of marketing activities of an online car-hailing platform according to claim 1, characterized in that: In S101, the platform order completion data is grouped according to different natural weeks and dates, and the platform order completion data of each natural week group and date group is summarized. A bar chart is drawn to show the change trend of the platform order completion data and the total number of platform order completions of each natural week group and date group is marked.
5. A method for estimating the cost of marketing activities of an online car-hailing platform according to claim 4, characterized in that: According to the bar chart analysis platform, the order volume data has an overall upward or downward trend over time, and a trend line is added to the bar chart.
6. A method for estimating the cost of marketing activities of an online car-hailing platform according to claim 1, characterized in that: In S102, the core parameters for planning the order-filling reward are valid driver parameters, valid order parameters, platform order completion requirements and corresponding reward amount.
7. A method for estimating the cost of marketing activities of an online car-hailing platform according to claim 6, characterized in that: The valid driver parameters are divided into the parameters of the circled driver set, the parameters of the blacklist driver set, the driver service score requirement parameters and the driver franchise type requirement parameters; the valid order parameters are divided into the order time requirement parameters and the validity parameters of carpooling orders, special flat-price orders and stop-by orders. The platform's order completion requirements and corresponding reward amounts are configured in a step-by-step manner.
8. A method for estimating the cost of marketing activities of an online car-hailing platform according to claim 7, characterized in that: Based on the effective driver parameters, the final effective drivers are determined to be those who have been circled and not hit the blacklist, and who meet the requirements of service points, franchise type, etc. Based on the effective order parameters, the final effective orders are determined to be the part of the completed orders that reach the drivers and meet all the order requirement parameters. The cost estimate of the marketing activities of the online car-hailing platform is calculated based on the core parameters of the order bonus.
9. A method for estimating the cost of marketing activities of an online car-hailing platform according to claim 1, characterized in that: In S103, a monitoring mechanism is set up to track the effectiveness of the marketing activities of the online ride-hailing platform and make timely adjustments. The monitoring indicators are determined to be the platform's order completion data and the core parameters of the order bonus. The monitoring indicator frequency is set in days, and the corresponding values of 50% and 100% of the budget cost are set as specific thresholds. When the estimated cost of the marketing activities of the online ride-hailing platform exceeds the first specific threshold, an early warning is issued. When the estimated cost of the marketing activities of the online ride-hailing platform exceeds the first specific threshold, the relevant staff is notified immediately.
10. The method for estimating the cost of marketing activities of an online car-hailing platform according to claim 1, characterized in that: In S104, the effectiveness of the marketing activities of the online ride-hailing platform is evaluated through data analysis, and the marketing strategy for the next stage is adjusted according to the results. The order completion database API, order bonus core parameter database API, user participation database API and sales database API of the online ride-hailing platform are connected, and the platform's order completion data, order bonus core parameter data, user participation data and sales data are selected through the Pearson correlation coefficient and correlation analysis is performed. The value range of the Pearson correlation coefficient is between -1 and 1. The closer the absolute value is to 1, the stronger the correlation is, and the closer it is to 0, the weaker the correlation is. The strength of the correlation is used to determine the influence between the platform's order completion data, order bonus core parameter data, user participation data and sales data.
11. A method for estimating the cost of marketing activities of an online car-hailing platform according to claim 10, characterized in that: The specific formula of the Pearson correlation coefficient is: Where r represents the Pearson coefficient, cov(x,y) represents the covariance between the platform's order volume data, the core parameter data of the order reward, the user participation data, and the sales data, and Sd(x) and Sd(y) represent the standard deviation values between the platform's order volume data, the core parameter data of the order reward, the user participation data, and the sales data.
Citation Information
Cited By
E-commerce transaction management method
CN119379397A
