Method and system for predicting insurance profit index

Abstract

The present disclosure includes a method for predicting an insurance profit index of an insurance contract, the method being performed by at least one processor. The prediction method comprises the steps of: collecting data associated with an insurance contract; inputting the collected data to a first group model associated with a future cash flow prediction, so as to determine a value associated with a cash prediction at a first future point in time; on the basis of the value associated with the cash flow prediction at the first future point in time, calculating a value associated with a discounted present value at a point in time of the insurance contract; and predicting an insurance profit index on the basis of the calculated value associated with the present value and the collected data.

Description

Insurance Profit Index Prediction Method and System

[0001] The present disclosure relates to a method and system for predicting an insurance profit index, and more particularly, to a method for predicting an insurance profit index of an insurance contract and a system therefor.

[0002] Under the International Financial Reporting Standard 17 (IFRS 17), which regulates the accounting treatment and reporting methods for insurance contracts, insurance companies are applying a batch processing method in which data is stored (logged) or aggregated (aggregated) first and then processed all at once at a specific interval (e.g., every 30 minutes, day, week, or month) rather than processing it in real time to produce accounting-related indicators.

[0003] In the case of batch processing, data is processed at once on a regular basis, which is advantageous in detecting data duplication, omission, and error data, and in generating error-free accounting data through data consistency verification and correction.

[0004] The existing batch processing method has the characteristic of performing batch processing after a certain period of time, so it cannot utilize transaction data that accumulates in the tens of thousands or millions in real time, which causes problems such as rapid decision-making and monitoring.

[0005] In addition, data processing and analysis techniques (e.g., Polynomial Fitting) for traditional accounting systems based on batch processing methods have problems with precise modeling due to the rapid volatility of target values ​​(e.g., insurance profit index), and problems arise when processing and analyzing a large amount of categorical data.

[0006] The above-described information disclosed in the background technology of this invention is only intended to improve understanding of the background of the present invention, and therefore may include information that does not constitute prior art.

[0007] The present disclosure provides a method and system for predicting an insurance profit index for an insurance contract at the time of the insurance contract in order to solve the above-mentioned problems.

[0008] The present disclosure can be implemented in various ways, including as a method, a device (system), or a computer program stored on a readable storage medium.

[0009] According to one embodiment of the present disclosure, a method for predicting an insurance yield index of an insurance contract, performed by at least one processor, includes the steps of collecting data associated with the insurance contract, inputting the collected data into a first group model associated with a future cash flow prediction to determine a value associated with the cash flow prediction at a first future point in time, calculating a value associated with a discounted present value at the time of the insurance contract based on the value associated with the cash flow prediction at the first future point in time, and predicting the insurance yield index using a second group model based on the value associated with the calculated present value and the collected data.

[0010] According to one embodiment of the present disclosure, the step of collecting data associated with an insurance contract includes the step of collecting categorical data and non-categorical data associated with the insurance contract, wherein the categorical data includes data associated with at least one of gender, age, type of covered disease, type of coverage, scope of coverage, method of premium payment, whether premium is renewed, whether special contract is available, occupation, income level, area of ​​residence, smoking, family history, method of payment, time of coverage initiation, diagnostic criteria, payment conditions, contract conclusion channel, risk rating, health status, method of applying discount rate, method of risk adjustment, or contract group, and the non-categorical data includes data associated with at least one of premium, insurance amount, insurance contract period, insurance period, insurance waiting period, subscription age, subscription period, coverage waiting period, health index, body mass index, income, coverage limit, coverage ratio, risk adjustment ratio, annual inflation rate, discount rate, return on investment, government bond yield, mortality rate, disease incidence rate, insurance continuation rate, payment rate, contract management cost, claim processing cost, or operating incidental cost.

[0011] According to one embodiment of the present disclosure, the first group model includes a 1-1 model that receives time series data associated with categorical data or non-categorical data and predicts a first predicted value associated with a cash flow forecast at a first future point in time, a 1-2 model that receives variable data associated with the categorical data or non-categorical data and predicts a second predicted value associated with the cash flow forecast at the first future point in time, and a 1-3 model that determines a predicted value associated with the cash flow forecast at the first future point in time based on the first predicted value of the 1-1 model and the second predicted value of the 1-2 model.

[0012] According to one embodiment of the present disclosure, the second group model includes a 2-1 model that receives at least one of preset data associated with a value associated with a discounted present value at the time of a calculated insurance contract, categorical data, or non-categorical data, and provides a first predicted value associated with an insurance profit index, a 2-2 model that receives at least one of variable data associated with a value associated with a discounted present value at the time of a calculated insurance contract, categorical data, or non-categorical data, and provides a second predicted value associated with an insurance profit index, and a 2-3 model that determines an insurance profit index based on the first predicted value of the 2-1 model and the second predicted value of the 2-2 model.

[0013] According to one embodiment of the present disclosure, after the step of predicting an insurance profit index, the method further includes a step of outputting the determined insurance profit index.

[0014] A computer program stored in a computer-readable recording medium is provided for executing a method according to one embodiment of the present disclosure on a computer.

[0015] According to one embodiment of the present disclosure, an information processing system includes a memory, and one processor coupled to the memory and configured to execute at least one computer-readable program included in the memory, wherein the at least one program includes instructions for collecting data associated with an insurance contract, inputting the collected data into a first group model associated with a future cash flow forecast, determining a value associated with the cash flow forecast at a first future point in time, calculating a value associated with a discounted present value at the time of the insurance contract based on the value associated with the cash flow forecast at the first future point in time, and predicting an insurance yield index using a second group model based on the value associated with the calculated present value and the collected data.

[0016] According to one embodiment of the present disclosure, at least one program, when collecting data associated with an insurance contract, includes commands for collecting categorical data and non-categorical data associated with the insurance contract, wherein the categorical data includes data associated with at least one of gender, age, type of covered disease, type of coverage, scope of coverage, method of premium payment, whether premium is renewed, whether rider is included, occupation, income level, area of ​​residence, smoking, family history, method of payment, time of coverage initiation, diagnostic criteria, payment conditions, contract conclusion channel, risk rating, health status, method of applying discount rate, method of risk adjustment, or contract group, and the non-categorical data includes data associated with at least one of premium, insurance amount, insurance contract period, insurance period, insurance waiting period, subscription age, subscription period, coverage waiting period, health index, body mass index, income, coverage limit, coverage ratio, risk adjustment ratio, annual inflation rate, discount rate, return on investment, government bond yield, mortality rate, disease incidence rate, insurance continuation rate, payment rate, contract management cost, claim processing cost, or operating incidental cost.

[0017] According to one embodiment of the present disclosure, the first group model includes a 1-1 model that receives time series data associated with categorical data or non-categorical data and predicts a first predicted value associated with a cash flow forecast at a first future point in time, a 1-2 model that receives variable data associated with the categorical data or non-categorical data and predicts a second predicted value associated with the cash flow forecast at the first future point in time, and a 1-3 model that determines a predicted value associated with the cash flow forecast at the first future point in time based on the first predicted value of the 1-1 model and the second predicted value of the 1-2 model.

[0018] According to one embodiment of the present disclosure, the second group model includes a 2-1 model that receives at least one of preset data associated with a value associated with a discounted present value at the time of a calculated insurance contract, categorical data, or non-categorical data, and provides a first predicted value associated with an insurance profit index, a 2-2 model that receives at least one of variable data associated with a value associated with a discounted present value at the time of a calculated insurance contract, categorical data, or non-categorical data, and provides a second predicted value associated with an insurance profit index, and a 2-3 model that determines an insurance profit index based on the first predicted value of the 2-1 model and the second predicted value of the 2-2 model.

[0019] According to one embodiment of the present disclosure, a method for predicting an insurance yield index of an insurance contract, performed by at least one processor, includes the steps of collecting data associated with the insurance contract and inputting the collected data into a pre-trained insurance yield index prediction model to predict an insurance yield index of the insurance contract, wherein the data associated with the insurance contract may include categorical data and non-categorical data. The insurance yield index prediction model may be a model trained to predict a correct insurance yield index based on the categorical training data and the non-categorical training data. The correct insurance yield index may be calculated by calculating a value associated with a cash flow at a future time point based on the categorical training data and the non-categorical training data, calculating a value associated with a discounted present value at the time of the insurance contract based on the value associated with the cash flow at the future time point, and calculating the value associated with the present value and a risk-adjusted value.

[0020] According to some embodiments of the present disclosure, an insurance yield index of an insurance contract including a plurality of categorical data can be predicted in real time.

[0021] According to some embodiments of the present disclosure, prediction of an insurance yield index of an insurance contract can be performed at the time of the insurance contract.

[0022] According to some embodiments of the present disclosure, since an insurance profit index for an insurance contract at the time of the insurance contract can be predicted, a balance between accuracy and real-time prediction of the insurance profit index can be maintained, optimization processing for data characteristics can be performed, and the insurance market can effectively utilize the insurance profit index.

[0023] The effects of the present disclosure are not limited to the effects mentioned above, and other effects not mentioned can be clearly understood by a person having ordinary skill in the art to which the present disclosure belongs (referred to as “one skilled in the art”) from the description of the claims.

[0024] Embodiments of the present disclosure will be described below with reference to the accompanying drawings, wherein like reference numerals represent similar elements, but are not limited thereto.

[0025] FIG. 1 is a schematic diagram illustrating an insurance profit prediction system according to one embodiment of the present disclosure.

[0026] FIG. 2 is a schematic diagram showing a configuration in which an information processing system is connected to enable communication with a plurality of user terminals to predict an insurance profit index according to one embodiment of the present disclosure.

[0027] FIG. 3 is a block diagram showing the internal configuration of a user terminal and an information processing system according to one embodiment of the present disclosure.

[0028] FIG. 4 is a diagram illustrating a process for predicting an insurance profit index of an insurance contract based on collected data according to one embodiment of the present disclosure.

[0029] FIG. 5 is a diagram illustrating a configuration for predicting an insurance profit index of an insurance contract based on data associated with the insurance contract according to one embodiment of the present disclosure.

[0030] FIG. 6 is a diagram illustrating a first group model for predicting numerical values ​​associated with future cash flow prediction according to one embodiment of the present disclosure.

[0031] FIG. 7 is a diagram illustrating a second group model for predicting an insurance profit index according to one embodiment of the present disclosure.

[0032] FIG. 8 is a flowchart illustrating a method for predicting an insurance profit index of an insurance contract according to one embodiment of the present disclosure.

[0033] Embodiments of the present disclosure will be described below with reference to the accompanying drawings, wherein like reference numerals represent similar elements, but are not limited thereto.

[0034] Hereinafter, specific details for implementing the present disclosure will be described in detail with reference to the attached drawings. However, in the following description, specific descriptions of widely known functions or configurations will be omitted if they may unnecessarily obscure the gist of the present disclosure.

[0035] In the attached drawings, identical or corresponding components are assigned the same reference numerals. Furthermore, in the description of the embodiments below, duplicate descriptions of identical or corresponding components may be omitted. However, even if a description of a component is omitted, it is not intended that such component is not included in any embodiment.

[0036] The advantages and features of the disclosed embodiments, and methods for achieving them, will become clearer with reference to the embodiments described below, along with the accompanying drawings. However, the present disclosure is not limited to the embodiments disclosed below and may be implemented in various different forms. These embodiments are provided solely to ensure the completeness of the disclosure and to fully inform those skilled in the art of the scope of the invention.

[0037] The terms used in this specification will be briefly explained, followed by a detailed description of the disclosed embodiments. The terms used in this specification have been selected from widely used, current terms, taking into account the functions of the present disclosure. However, these terms may vary depending on the intentions of engineers working in the relevant field, precedents, the emergence of new technologies, etc. Furthermore, in certain cases, terms may be arbitrarily selected by the applicant, and in such cases, their meanings will be described in detail in the relevant description of the invention. Therefore, the terms used in this disclosure should not be defined simply as names of terms, but rather based on their meanings and the overall content of the present disclosure.

[0038] In this specification, singular expressions include plural expressions unless the context clearly indicates otherwise. Furthermore, plural expressions include singular expressions unless the context clearly indicates otherwise. When a part of the specification is said to include a component, this does not exclude other components, but rather implies that other components may be included, unless otherwise specifically stated.

[0039] Also, the term 'module' or 'part' used in the specification means a software or hardware component, and the 'module' or 'part' performs certain roles. However, the 'module' or 'part' is not limited to software or hardware. The 'module' or 'part' may be configured to reside on an addressable storage medium and may be configured to execute one or more processors. Thus, as an example, the 'module' or 'part' may include at least one of components such as software components, object-oriented software components, class components, and task components, processes, functions, attributes, procedures, subroutines, segments of program code, drivers, firmware, microcode, circuitry, data, databases, data structures, tables, arrays, or variables. The functionality provided within the components and 'modules' or 'parts' may be combined into a smaller number of components and 'modules' or 'parts', or further separated into additional components and 'modules' or 'parts'.

[0040] According to one embodiment of the present disclosure, a 'module' or 'unit' may be implemented as a processor and a memory. 'Processor' should be broadly construed to include a general-purpose processor, a central processing unit (CPU), a microprocessor, a digital signal processor (DSP), a controller, a microcontroller, a state machine, and the like. In some circumstances, a 'processor' may also refer to an application-specific integrated circuit (ASIC), a programmable logic device (PLD), a field-programmable gate array (FPGA), and the like. A 'processor' may also refer to a combination of processing devices, such as, for example, a combination of a DSP and a microprocessor, a combination of multiple microprocessors, a combination of one or more microprocessors in conjunction with a DSP core, or any other such combination of configurations. In addition, 'memory' should be broadly construed to include any electronic component capable of storing electronic information. 'Memory' may refer to various types of processor-readable media, such as random access memory (RAM), read-only memory (ROM), non-volatile random access memory (NVRAM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), electrically erasable PROM (EEPROM), flash memory, magnetic or optical data storage, registers, etc. Memory is said to be in electronic communication with the processor if the processor can read information from, and write information to, the memory. Memory integrated in a processor is in electronic communication with the processor.

[0041] In the present disclosure, the "system" may include, but is not limited to, at least one of a server device and a cloud device. For example, the system may be comprised of one or more server devices. As another example, the system may be comprised of one or more cloud devices. As yet another example, the system may be configured and operated by a combination of a server device and a cloud device.

[0042] In the present disclosure, 'display' may refer to any display device associated with a computing device, for example, any display device capable of displaying any information / data controlled by or provided from the computing device.

[0043] In the present disclosure, 'each of the plurality of As' or 'each of the plurality of As' may refer to each of all components included in the plurality of As, or may refer to each of some components included in the plurality of As.

[0044] In this disclosure, the "insurance revenue index" represents the expected future profits in return for the services an insurance company will provide under an insurance contract. It represents the profits an insurance company can earn by receiving premiums and fulfilling its obligations to pay claims. The insurance revenue index may include a contractual service margin (CSM).

[0045] FIG. 1 is a schematic diagram illustrating an insurance profit prediction system (100) according to one embodiment of the present disclosure.

[0046] Referring to FIG. 1, the insurance profit prediction system (100) collects data (10) related to an insurance contract and can predict an insurance profit index (20) for the insurance contract at the time of the insurance contract based on the collected data.

[0047] The insurance profit prediction system (100) can calculate future cash flows for an insurance period (e.g., up to 100 years) based on multiple actuarial assumptions.

[0048] Here, actuarial assumptions are assumptions used to predict future uncertain factors in the financial and inventory evaluation of an insurance company, and may include at least one of mortality rate, morbidity rate, disability rate, lapse rate (the probability that a policyholder will lapse an insurance contract midway), continuation rate, interest rate, investment return rate, cost assumptions (including operating and administrative costs related to insurance contracts), renewal rate, claims rate, or inflation rate, but the present disclosure is not limited thereto.

[0049] The insurance revenue prediction system (100) can calculate the net present value (NPV) by discounting the calculated future cash flow based on multiple economic assumptions. The insurance revenue prediction system (100) can determine that an investment is worthwhile if the NPV is greater than 0.

[0050] Here, economic assumptions are assumptions set to reflect the economic environment and market conditions in order to predict the future cash flow and profitability of an insurance contract, and may include at least one of interest rates, investment returns, inflation rates, economic growth rates, exchange rates, asset volatility, or financial risks, but the present disclosure is not limited thereto.

[0051] Data (10) associated with an insurance contract may include categorical data (12) and non-categorical data.

[0052] Categorical data (12) is a data type in which data is expressed as a classification or category, and includes gender (male, female), age (for each age group), type of covered disease (for example, in the case of cancer, general cancer, similar cancer, minor cancer, high-cost cancer), type of coverage (fixed amount, actual loss, renewable, non-renewable, special contract, etc.), scope of coverage (domestic, overseas), method of premium payment (monthly, annual, lump sum), renewal status of premium (renewable, non-renewable), special contract status (presence or absence), occupation (high-risk group, medium-risk group, low-risk group), income level (high-income, medium-income, low-income), area of ​​residence (urban, rural), smoking status (presence or absence), family history (presence or absence), payment method (cash payment, installment payment, cost compensation), coverage start time (immediate coverage, coverage after waiting period), diagnosis criteria (clinical diagnosis, pathological diagnosis), payment conditions (single condition, multiple conditions), contract conclusion channel (face-to-face sales, online, bank connection), risk rating (high risk, medium risk, low risk), health The present disclosure may include data associated with at least one of a status (good, chronic disease, severe disease), a discount rate application method (fixed discount rate, variable discount rate), a risk adjustment method (probabilistic, non-probabilistic), or a contract group (groups by similar characteristics, individual contracts), but the present disclosure is not limited thereto.

[0053] Non-categorical data (14) may include data related to at least one of insurance premium (e.g., monthly payment of 300,000 won), insurance benefit (e.g., 50 million won in case of cancer diagnosis), insurance contract period (10 years), insurance period (5 years), insurance waiting period (180 days), subscription age (40 years), subscription period, coverage waiting period, health index, body mass index, income, coverage limit, coverage ratio, risk adjustment ratio, annual inflation rate, discount rate, investment return, government bond yield, mortality rate, disease incidence rate, insurance maintenance rate, payment rate, contract management cost, claim processing cost, or operating incidental cost. Non-categorical data (14) may include various types of insurance contract-related data, customer-related data, product and coverage-related data, economic assumption data, cost-related data, etc., but the present disclosure is not limited thereto.

[0054] An insurance profit prediction system (100) can predict an insurance profit index (20) based on data (10) associated with collected insurance contracts. The insurance profit index (20) is a value associated with a contract service margin (CSM), and may be a sum of a value associated with a future cash forecast and a value associated with a future risk adjustment.

[0055] The insurance revenue prediction system (100) can predict future cash flows based on collected data when calculating an insurance revenue index (20). The insurance revenue prediction system (100) can predict cash flows for insurance premium inflows at a specific future point in time and cash outflows at a specific future point in time (e.g., insurance payment, operating expenses, claims / management expenses, etc.).

[0056] Additionally, the insurance revenue prediction system (100) can calculate a value associated with the discounted present value at the time of the insurance contract based on a value associated with a cash flow prediction at a specific future point in time. That is, the insurance revenue prediction system (100) can calculate a present value by applying a discount rate appropriate to the future cash flow.

[0057] In addition, the insurance profit prediction system (100) can calculate a risk-adjusted value by considering the uncertainty of future cash flow, and can predict an insurance profit index based on a value associated with the calculated present value and collected data.

[0058] In one embodiment, a method for predicting an insurance yield index of an insurance contract, performed by at least one processor of an insurance yield prediction system (100), includes the steps of collecting data associated with the insurance contract and inputting the collected data into a pre-learned insurance yield index prediction model to predict an insurance yield index of the insurance contract, wherein the data associated with the insurance contract may include categorical data and non-categorical data.

[0059] Here, the insurance profit prediction system (100) may include an insurance profit index prediction model trained to receive data associated with an insurance contract including categorical data and non-categorical data, and to predict and output an insurance profit index (e.g., CSM) associated with the insurance contract. For example, the insurance profit index prediction model may include a plurality of machine learning models and a plurality of artificial neural network models. In one example, the insurance profit index prediction model may be a model trained to predict a correct insurance profit index associated with the insurance contract based on categorical learning data and non-categorical learning data associated with the insurance contract. Here, the correct insurance profit index may be calculated based on the categorical learning data and the non-categorical learning data to calculate a value associated with a cash flow at a future point in time, a value associated with a discounted present value at the time of the insurance contract based on the value associated with the cash flow at the future point in time, and a value associated with the present value and a risk-adjusted value. For example, the risk-adjusted value can be calculated as an amount that reflects the uncertainty of the contract portfolio using internal risk assessment, Value at Risk (VaR), Conditional Tail Expectation (CTE) methods, or other statistical or actuarial techniques.

[0060] FIG. 2 is a schematic diagram illustrating a configuration in which an information processing system is connected to multiple user terminals to enable communication for predicting an insurance profit index according to one embodiment of the present disclosure. Here, the information processing system (230) may be implemented as the insurance profit prediction system (100) of FIG. 1.

[0061] Referring to FIG. 2, a plurality of user terminals (210_1, 210_2, 210_3, 210_4) can be connected to an information processing system (230) that predicts an insurance profit index through a network (220).

[0062] Here, the plurality of user terminals (210_1, 210_2, 210_3, 210_4) may include user terminals associated with insurance consumers, insurance company employees, insurance company managers, insurance-related telemarketers (TM channels), etc., who receive the insurance profit index predicted by the information processing system (230). In addition, the information processing system (230) may include or utilize at least one of a computing device or server, a database, NoSQL (Not Only Structured Query Language), a vector database, a database computing device or server for predicting the insurance profit index based on data associated with the collected insurance contract.

[0063] In one embodiment, the information processing system (230) may include or utilize one or more server devices and / or databases capable of storing, providing, and executing data associated with prediction of an insurance yield index based on data associated with collected insurance contracts, or computer executable programs (e.g., downloadable applications) and data associated with prediction of an insurance yield index, or one or more distributed computing devices and / or distributed databases based on cloud computing services.

[0064] The insurance profit index provided by the information processing system (230) may be provided to users through applications, web browsers, web browser extensions, etc. installed on each of a plurality of user terminals (210_1, 210_2, 210_3, 210_4). For example, the information processing system (230) may provide information corresponding to an information sharing request received from a user terminal (210_1, 210_2, 210_3, 210_4) through an application, etc., or perform corresponding processing.

[0065] A plurality of user terminals (210_1, 210_2, 210_3, 210_4) can communicate with an information processing system (230) via a network (220). The network (220) can be configured to enable communication between a plurality of user terminals (210_1, 210_2, 210_3) and the information processing system (230). Depending on the installation environment, the network (220) can be configured as a wired network such as Ethernet, a wired home network (Power Line Communication), a telephone line communication device, and RS-serial communication, a wireless network such as a mobile communication network, WLAN (Wireless LAN), Wi-Fi, Bluetooth, and ZigBee, or a combination thereof. The communication method is not limited, and may include not only a communication method utilizing a communication network (e.g., a mobile communication network, wired Internet, wireless Internet, broadcasting network, satellite network, etc.) that the network (220) may include, but also short-range wireless communication between user terminals (210_1, 210_2, 210_3, 210_4).

[0066] In FIG. 2, a mobile phone terminal (210_1), a tablet terminal (210_2), a PC terminal (210_3), and a terminal capable of wired communication (210_4) are illustrated as examples of user terminals, but are not limited thereto, and the user terminals (210_1, 210_2, 210_3, 210_4) may be any computing device capable of wired and / or wireless communication and capable of installing and executing an application or web browser for receiving and displaying a predicted insurance profit index. For example, the user terminal may include an AI speaker, a smartphone, a mobile phone, a navigation device, a computer, a laptop, a digital broadcasting terminal, a PDA (Personal Digital Assistants), a PMP (Portable Multimedia Player), a tablet PC, a game console, a wearable device, an IoT (Internet of Things) device, a VR (virtual reality) device, an AR (augmented reality) device, MR (Mixed reality), a set-top box, and the like. In addition, although FIG. 2 illustrates three user terminals (210_1, 210_2, 210_3, 210_4) communicating with the information processing system (230) via the network (220), the present invention is not limited thereto, and a different number of user terminals may be configured to communicate with the information processing system (230) via the network (220).

[0067] In FIG. 2, a configuration in which a user's request is transmitted to an information processing system (230) through a user terminal (210_1, 210_2, 210_3, 210_4) is exemplarily illustrated, but the present invention is not limited thereto, and the user's request may be provided to the information processing system (230) through an input device associated with the information processing system (230) without passing through the user terminal (210_1, 210_2, 210_3, 210_4), and the result of processing the user's request may be provided to the user through an output device (e.g., a display, etc.) associated with the information processing system (230).

[0068] Although FIG. 2 illustrates that user terminals (210_1, 210_2, 210_3, 210_4) receive predicted insurance profit indices from the information processing system (230), the present invention is not limited thereto. For example, a service for predicting insurance profit indices associated with an insurance contract may be provided through a program / application for predicting insurance profit indices installed on user terminals (210_1, 210_2, 210_3, 210_4) without communication with the information processing system (230). In addition, although the information processing system (230) is illustrated as a single device, the present invention is not limited thereto, and the information processing system (230) may be composed of multiple devices.

[0069] FIG. 3 is a block diagram showing the internal configuration of a user terminal and an information processing system according to one embodiment of the present disclosure.

[0070] Referring to FIG. 3, the user terminal (210) may refer to any computing device capable of executing applications, web browsers, etc. and capable of wired / wireless communication, and may include, for example, a mobile phone terminal (210_1), a tablet terminal (210_2), a PC terminal (210_3), a wired communication capable terminal (210_4), etc. of FIG. 2. As illustrated, the user terminal (210) may include a memory (312), a processor (314), a communication module (316), and an input / output interface (318). Similarly, the information processing system (230) may include a memory (332), a processor (334), a communication module (336), and an input / output interface (338). As illustrated in FIG. 3, the user terminal (210) and the information processing system (230) may be configured to communicate information and / or data via a network (220) using their respective communication modules (316, 336). Additionally, the input / output device (320) may be configured to input information and / or data to the user terminal (210) or output information and / or data generated from the user terminal (210) via the input / output interface (318).

[0071] The memory (312, 332) may include any non-transitory computer-readable recording medium. According to one embodiment, the memory (312, 332) may include a permanent mass storage device such as a read-only memory (ROM), a disk drive, a solid-state drive (SSD), or flash memory. As another example, a permanent mass storage device such as a ROM, an SSD, a flash memory, or a disk drive may be included in the user terminal (210) or the information processing system (230) as a separate permanent storage device distinct from the memory. In addition, an operating system and at least one program code may be stored in the memory (312, 332).

[0072] These software components may be loaded from a computer-readable recording medium separate from the memory (312, 332). This separate computer-readable recording medium may include a recording medium directly connectable to the user terminal (210) and the information processing system (230), and may include, for example, a computer-readable recording medium such as a floppy drive, a disk, a tape, a DVD / CD-ROM drive, a memory card, etc. As another example, the software components may be loaded into the memory (312, 332) through a communication module (316, 336) other than a computer-readable recording medium. For example, at least one program may be loaded into the memory (312, 332) based on a computer program that is installed by files provided by developers or a file distribution system that distributes installation files of applications through a network (220).

[0073] The processor (314, 334) may be configured to process instructions of a computer program by performing basic arithmetic, logic, and input / output operations. Instructions may be provided to the processor (314, 334) by a memory (312, 332) or a communication module (316, 336). For example, the processor (314, 334) may be configured to execute instructions received according to program code stored in a storage device such as the memory (312, 332).

[0074] The communication modules (316, 336) may provide a configuration or function for the user terminal (210) and the information processing system (230) to communicate with each other via the network (220), and may provide a configuration or function for the user terminal (210) and / or the information processing system (230) to communicate with another user terminal or another system (e.g., a separate cloud system, etc.). For example, a request or data generated by the processor (314) of the user terminal (210) according to a program code stored in a recording device such as a memory (312) may be transmitted to the information processing system (230) via the network (220) under the control of the communication module (316). Conversely, a control signal or command provided under the control of the processor (334) of the information processing system (230) may be received by the user terminal (210) via the communication module (316) of the user terminal (210) via the communication module (336) and the network (220).

[0075] The input / output interface (318) may be a means for interfacing with an input / output device (320). As an example, the input device may include a device such as a camera, keyboard, microphone, mouse, etc., including an audio sensor and / or an image sensor, and the output device may include a device such as a display, a speaker, a haptic feedback device, etc. As another example, the input / output interface (318) may be a means for interfacing with a device that has a configuration or function integrated into one for performing input and output, such as a touch screen. For example, when the processor (314) of the user terminal (210) processes a command of a computer program loaded into the memory (312), a service screen configured using information and / or data provided by the information processing system (230) or another user terminal may be displayed on the display through the input / output interface (318). In FIG. 3, the input / output device (320) is illustrated as not being included in the user terminal (210), but is not limited thereto, and may be configured as a single device with the user terminal (210). In addition, although the input / output device (not shown) is illustrated as not being included in the information processing system (230), it is not limited thereto and may be configured as one system with the information processing system (230).

[0076] In addition, the input / output interface (338) of the information processing system (230) may be a means for interfacing with a device (not shown) for input or output that is connected to the information processing system (230) or that the information processing system (230) may include. In FIG. 3, the input / output interfaces (318, 338) are illustrated as elements configured separately from the processors (314, 334), but are not limited thereto, and the input / output interfaces (318, 338) may be configured to be included in the processors (314, 334).

[0077] The user terminal (210) and the information processing system (230) may include more components than those shown in FIG. 3. However, there is no need to explicitly illustrate most of the conventional components. In one embodiment, the user terminal (210) may be implemented to include at least some of the input / output devices (320) described above. In addition, the user terminal (210) may further include other components, such as a transceiver, a Global Positioning System (GPS) module, a camera, various sensors, a database, and the like. For example, if the user terminal (210) is a smartphone, it may include components that a smartphone generally includes, and various components, such as an acceleration sensor, a gyro sensor, a microphone module, a camera module, various physical buttons, buttons using a touch panel, input / output ports, and a vibrator for vibration, may be implemented to be further included in the user terminal (210).

[0078] While the program or application for predicting insurance profit index is running, the processor (314) can receive text, images, videos, voices and / or actions, etc. input or selected through input devices such as a camera, microphone, including a touch screen, keyboard, audio sensor and / or image sensor connected to the input / output interface (318), and can store the received text, images, videos, voices and / or actions, etc. in the memory (312) or provide them to the information processing system (230) through the communication module (316) and the network (220).

[0079] In one embodiment, the processor (314) may receive a sharing request for the predicted results of an insurance profit index associated with an insurance contract via the input / output interface (318). In this case, the processor (314) may store the received sharing request in the memory (312). Additionally or alternatively, the processor (314) may transmit the received sharing request to the information processing system (230) via the communication module (316) and the network (220).

[0080] In one embodiment, the processor (334) of the information processing system (230) may receive a request to share a prediction result of an insurance profit index associated with an insurance contract from a user terminal (210) via a communication module (336) and a network (220). In this case, the processor (334) may provide information to the user terminal (210) via the network (220) according to the received sharing request. In addition, the processor (334) may store information associated with the insurance profit index determined to be shared in the memory (332) or transmit the information to the user terminal (210) via the communication module (336) and the network (220).

[0081] The processor (314) of the user terminal (210) may be configured to manage, process, and / or store information and / or data received from an input / output device (320), another user terminal, an information processing system (230), and / or multiple external systems. The information and / or data processed by the processor (314) may be provided to the information processing system (230) via a communication module (316) and a network (220). The processor (314) of the user terminal (210) may transmit the information and / or data to the input / output device (320) via an input / output interface (318) and output the information and / or data. For example, the processor (314) may output or display the received information and / or data on a screen associated with the user terminal (210).

[0082] In one embodiment, the processor (314) of the user terminal (210) may output an information sharing request related to the prediction result of the insurance profit index received through the input / output interface (318) on the display of the user terminal (210). In addition, the processor (314) may receive related information from the information processing system (230) through the communication module (316) and the network (220).

[0083] The processor (334) of the information processing system (230) may be configured to manage, process, and / or store information and / or data received from multiple user terminals (210) and / or multiple external systems. The information and / or data processed by the processor (334) may be provided to the user terminal (210) via the communication module (336) and the network (220). Hereinafter, various embodiments performed by the processor of the information processing system (230) or the user terminal (210) will be described.

[0084] FIG. 4 is a diagram illustrating a process (400) for predicting an insurance profit index of an insurance contract based on collected data according to one embodiment of the present disclosure. The process (400) may be performed by one or more processors of an information processing system (230).

[0085] Referring to FIG. 4, the processor may obtain collected data (410) associated with an insurance contract. The processor may use a preprocessing module (420), a first group model (430), and a second group model (440) to predict an insurance yield index based on the collected data (410) and values ​​associated with a discounted present value.

[0086] The preprocessing module (420) can process missing values ​​in the collected data (410) and perform outlier detection and removal. The preprocessing module (420) can perform encoding (e.g., one-hot encoding) on ​​categorical data and perform normalization and standardization operations on non-categorical data.

[0087] The preprocessing module (420) can perform preprocessing on data input to the first group model (430) and can perform preprocessing on data input to the second group model (440).

[0088] The first group model (430) is a model for predicting values ​​associated with a first future point in time cash flow associated with an insurance contract, and may include multiple models. For example, the multiple models may include a 1-1 model based on Long Short-Term Memory (LSTM), a 1-2 model based on XGBoost (eXtreme Gradient Boosting), and a 1-3 model based on a Voting Ensemble.

[0089] The second group model (440) is a model for predicting the insurance profit index based on values ​​associated with the calculated present value and collected data, and may include multiple models. For example, the multiple models may include a 2-1 model based on an autoencoder, a 2-2 model based on XGBoost, and a 2-3 model based on a multilayer perceptron stacking ensemble.

[0090] FIG. 5 is a diagram illustrating a configuration for predicting an insurance yield index of an insurance contract based on data associated with the insurance contract according to one embodiment of the present disclosure. FIG. 6 is a diagram illustrating a first group model for predicting a numerical value associated with a future cash flow forecast according to one embodiment of the present disclosure, and FIG. 7 is a diagram (700) illustrating a second group model for predicting an insurance yield index according to one embodiment of the present disclosure. When describing FIG. 5, FIG. 6 and FIG. 7 will be referred to together where necessary.

[0091] Referring to FIG. 5, the processor may collect data (510) associated with an insurance contract. The data (510) associated with an insurance contract may include categorical data (512) and non-categorical data (514).

[0092] Categorical data (512) may include data associated with at least one of gender, age, type of covered disease, type of coverage, scope of coverage, method of premium payment, whether premium is renewed, whether special contract is in place, occupation, income level, area of ​​residence, smoking status, family history, payment method, coverage start time, diagnosis criteria, payment conditions, contract conclusion channel, risk rating, health status, discount rate application method, risk adjustment method, or contract group.

[0093] Non-categorical data (514) may include data associated with at least one of insurance premium, insurance amount, insurance contract period, insurance lapse period, insurance waiting period, subscription age, subscription lapse period, coverage waiting period, health index, body mass index, income, coverage limit, coverage ratio, risk adjustment ratio, annual inflation rate, discount rate, investment return, government bond yield, mortality rate, disease incidence rate, insurance continuation rate, payment rate, contract administration cost, claim processing cost, or operating incidental cost.

[0094] The processor can generate categorical data (512) and non-categorical data (514) as time series data (520). The time series data (520) in the learning phase can correspond to a preset past period in which a contract has been completed.

[0095] The processor can generate categorical data (512) and non-categorical data (514) as time-series data, and can generate categorical data (512) as numbers (e.g., indices) corresponding to categories based on in-hot encoding.

[0096] The processor can generate categorical data (512) and non-categorical data (514) into variable data (530). The variable data (530) can be generated based on a table and can include each variable and a value corresponding to the variable. The processor can digitize the categorical data (512) through label encoding or one-hot encoding.

[0097] When generating variable data (530), the processor can perform preprocessing on all variables of categorical data (512) and non-categorical data (514).

[0098] The processor can generate insurance-related core data (540). At this time, the processor can extract variables by removing variables with a low correlation with the insurance profit index or performing an importance analysis with the insurance profit index based on feature importance analysis.

[0099] For example, with respect to profitability, the processor may set at least one of the type of covered disease, type of coverage, scope of coverage, or renewal of insurance premium as a key variable of categorical data, and may set at least one of the premium, coverage limit, insurance contract period, discount rate, or investment return as a key variable of non-categorical data.

[0100] The processor may set at least one of occupation, smoking status, health status, family history, or list grade as a key variable of categorical data in relation to risk, and may set at least one of mortality rate, disease incidence rate, risk-adjusted rate, coverage rate, or government bond yield as a key variable of non-categorical data.

[0101] With respect to sustainability, the processor may set at least one of the following as a key variable of categorical data: premium payment method, residential area, contract conclusion channel (related to retention rate), or contract status; and may set at least one of the following as a key variable of non-categorical data: insurance retention rate, subscription period, health index, income, or annual inflation rate.

[0102] When generating variable data (550), the processor can perform preprocessing on all variables of categorical data (512) and non-categorical data (514).

[0103] The processor may input the generated time series data (520) and variable data (530) into the first group model (560). In addition, the processor may input the generated insurance-related core data (540) and variable data (550) into the second group model (570). In addition, the processor may calculate a value associated with the discounted present value at the time of the insurance contract based on the predicted value associated with the cash flow forecast, which is the output value of the first group model (560), and input the value associated with the discounted present value into the second group model (570).

[0104] Referring to FIG. 6, a processor may input time series data (610) associated with an insurance contract into a first model (630), which is an LSTM-based model. The first model (630) may receive time series data associated with categorical or non-categorical data and provide a first predicted value associated with a cash flow prediction for a first future point in time.

[0105] The processor may input variable data (620) associated with an insurance contract into a second model (640) that is an XGBoost-based model. The second model (640) may receive variable data associated with categorical data or non-categorical data and provide a second predicted value associated with a cash flow prediction at a first future point in time.

[0106] At this time, the processor may input all variables of categorical data and non-categorical data as variable data input into the second model (640), or input categorical data and non-categorical data related to profitability into the second model (640). For example, the processor may input categorical data including at least one of the type of covered disease, type of coverage, scope of coverage, or renewal of insurance premium, and non-categorical data including at least one of insurance premium, coverage limit, insurance contract period, discount rate, or investment return into the second model (640).

[0107] The third model (650) may be a model based on a voting ensemble model, and may determine a predicted value (660) associated with a cash flow forecast at a first future point in time based on a first predicted value of the first model (630) and a second predicted value of the second model (640).

[0108] In one embodiment, the third model (650) may determine a predicted value associated with the cash forecast at the first future point in time by giving a greater weight (2x) to the time-series cash forecast of the first model (630), but the present disclosure is not limited thereto.

[0109] In this way, the processor can use the first group model (600) to predict cash flow for the insurance premium inflow amount and the outflow amount at a specific future point in time.

[0110] The processor can calculate a value associated with a discounted present value at the time of the insurance contract based on a value associated with a cash flow forecast at a future point in time.

[0111] The processor may calculate the discount rate by applying either a top-down approach or a bottom-up approach, and may calculate the discount rate by taking into account interest rate fluctuations, credit risk, illiquidity premium, nature of contractual cash flows, currency, term, market conditions, etc.

[0112] The processor can calculate a risk-adjusted value by taking into account the uncertainty of future cash flows, and can predict an insurance yield index based on the values ​​associated with the calculated present values ​​and the collected data.

[0113] Referring to FIG. 7, the processor may input key data (710) associated with an insurance contract into a first model (730), which is an autoencoder-based model. Furthermore, the processor may input a value (712) associated with the discounted present value at the time of the insurance contract into the first model (730). The first model (730) may receive preset data associated with the value (712) associated with the discounted present value, categorical data, or non-categorical data, and provide a first predicted value associated with an insurance yield index.

[0114] The processor may input all variables of categorical data and non-categorical data as variable data input into the first model (730), or input categorical data and non-categorical data related to risk into the first model (730). For example, the processor may input categorical data including at least one of occupation, smoking status, health status, family history, or list grade, and non-categorical data including at least one of mortality rate, disease incidence rate, risk adjustment rate, coverage rate, or government bond yield into the first model (730).

[0115] An autoencoder compresses input data into a low-dimensional latent space, which can then be restored to its original form using a decoder. Autoencoders can encode categorical data using one-hot encoding and embed the encoded categorical and non-categorical data into the latent space.

[0116] In one embodiment, the first model (730) may additionally include XGBoost, which outputs risk-adjusted predictions for future time points. The first model (730) may produce risk-adjusted predictions for core data based on XGBoost, based on the output data of the autoencoder.

[0117] The processor can input variable data (720) associated with an insurance contract into a second model (740), which is an XGBoost-based model. The second model (740) can receive variable data associated with a value (722) associated with a discounted present value, categorical data, or non-categorical data, and provide a second predicted value associated with an insurance yield index. In one embodiment, the processor may not input all variable data, but only data related to risk and / or persistence. For example, the processor may input categorical data including at least one of a premium payment method, a place of residence, a contract conclusion channel (related to a retention rate), or a contract status, as well as risk-related data, and non-categorical data including at least one of an insurance retention rate, a subscription period, a health index, income, or an annual inflation rate into the second model (740).

[0118] The third model (650) may be a stacking ensemble model based on a multilayer perceptron, and may finally determine an insurance profit index based on the first prediction value of the first model (730) and the second prediction value of the second model (740).

[0119] The third model (750) includes a meta model based on a multilayer perceptron, and the meta model may include an input layer that receives a first prediction value of the first model (730) and a second prediction value of the second model (740), a plurality of hidden layers, and an output layer that ultimately determines a risk-adjusted prediction value.

[0120] FIG. 8 is a flowchart illustrating a method (800) for predicting an insurance profit index of an insurance contract according to one embodiment of the present disclosure.

[0121] At step S810, the processor may collect data associated with the insurance contract. The data associated with the insurance contract may include categorical data and non-categorical data.

[0122] At step S820, the processor inputs the collected data into a first group model associated with a future cash flow forecast, thereby determining a value associated with the cash flow at a first future point in time. The first group models may include Model 1-1, Model 1-2, and Model 1-3.

[0123] The first-1 model can receive time series data associated with categorical data or non-categorical data and provide a first forecast value associated with a cash flow at a first future point in time.

[0124] The first-second model can receive variable data associated with categorical data or non-categorical data and provide a second predicted value associated with a cash flow at a first future point in time.

[0125] Model 1-3 can determine a cash flow forecast value at the first future point in time based on the first forecast value of Model 1-1 and the second forecast value of Model 1-2.

[0126] At step S830, the processor can calculate a value associated with a discounted present value at the time of the insurance contract based on a value associated with the cash flow forecast at the first future time point.

[0127] At step S840, the processor can predict the insurance yield index based on the values ​​associated with the calculated present value and the collected data. Specifically, the processor can predict the insurance yield index using a second group model. The second group models may include the 2-1 model, the 2-2 model, and the 2-3 model.

[0128] The second-first model can receive preset data associated with at least one of a value associated with a discounted present value at the time of the insurance contract, categorical data, or non-categorical data, and provide a first predicted value associated with an insurance profit index.

[0129] The second-second model can receive at least one of variable data associated with a discounted present value at the time of the calculated insurance contract, categorical data, or non-categorical data, and provide a first predicted value associated with an insurance profit index.

[0130] The 2-3 model can determine a risk-adjusted forecast value at the first future point in time based on the first forecast value of the 2-1 model and the second forecast value of the 2-2 model.

[0131] At step S840, the processor can determine an insurance yield index based on the cash forecast value and the risk-adjusted forecast value at the determined first future point in time.

[0132] At step S850, the processor can output a predicted insurance profit index.

[0133] In one embodiment, the processor may display the values ​​output by the first group model and the values ​​output by the second group model using visual items. Additionally, the processor may output information regarding key data associated with the insurance contract.

[0134] The sequence diagram of FIG. 8 and the above description are merely exemplary and the scope of the present disclosure is not limited thereto. For example, at least one step may be added / changed / deleted, or the order of each step may be changed.

[0135] The above-described method may be provided as a computer program stored on a computer-readable recording medium for execution on a computer. The medium may be one that continuously stores a computer-executable program or one that temporarily stores it for execution or download. In addition, the medium may be various recording means or storage means in the form of a single or multiple hardware combinations, and is not limited to a medium directly connected to a computer system, but may also be distributed over a network. Examples of the medium may include magnetic media such as hard disks, floppy disks, and magnetic tapes, optical recording media such as CD-ROMs and DVDs, magneto-optical media such as floptical disks, and those configured to store program instructions, including ROM, RAM, and flash memory. In addition, examples of other media may include recording or storage media managed by app stores that distribute applications, sites that supply or distribute various software, servers, etc.

[0136] The methods, operations, or techniques of the present disclosure may be implemented by various means. For example, these techniques may be implemented in hardware, firmware, software, or a combination thereof. Those skilled in the art will appreciate that the various exemplary logical blocks, modules, circuits, and algorithm steps described in connection with the disclosure herein may be implemented as electronic hardware, computer software, or combinations of both. To clearly illustrate this interchangeability of hardware and software, various exemplary components, blocks, modules, circuits, and steps have been described above generally in terms of their functionality. Whether such functionality is implemented as hardware or software will depend on the particular application and the design requirements imposed on the overall system. Those skilled in the art may implement the described functionality in various ways for each particular application, but such implementations should not be construed as departing from the scope of the present disclosure.

[0137] In a hardware implementation, the processing units used to perform the techniques may be implemented within one or more ASICs, DSPs, GPUs, digital signal processing devices (DSPDs), programmable logic devices (PLDs), field programmable gate arrays (FPGAs), processors, controllers, microcontrollers, microprocessors, electronic devices, other electronic units designed to perform the functions described herein, a computer, or a combination thereof.

[0138] Accordingly, the various exemplary logical blocks, modules, and circuits described in connection with the present disclosure may be implemented or performed by any combination of a general-purpose processor, a DSP, an ASIC, an FPGA or other programmable logic device, discrete gate or transistor logic, discrete hardware components, or those designed to perform the functions described herein. A general-purpose processor may be a microprocessor, but in the alternative, the processor may be any conventional processor, controller, microcontroller, or state machine. A processor may also be implemented as a combination of computing devices, e.g., a combination of a DSP and a microprocessor, a plurality of microprocessors, one or more microprocessors in conjunction with a DSP core, or any other such configuration.

[0139] In a firmware and / or software implementation, the techniques may be implemented as instructions stored on a computer-readable medium, such as random access memory (RAM), read-only memory (ROM), non-volatile random access memory (NVRAM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), electrically erasable PROM (EEPROM), flash memory, a compact disc (CD), a magnetic or optical data storage device, etc. The instructions may be executable by one or more processors and may cause the processor(s) to perform certain aspects of the functionality described herein.

[0140] When implemented in software, the techniques may be stored on or transmitted as one or more instructions or code on a computer-readable medium. Computer-readable media includes both computer storage media and communication media, including any medium that facilitates transfer of a computer program from one place to another. Storage media may be any available media that can be accessed by a computer. By way of example, and not limitation, such computer-readable media can include RAM, ROM, EEPROM, CD-ROM or other optical disk storage, magnetic disk storage or other magnetic storage devices, or any other medium that can be used to carry or store desired program code in the form of instructions or data structures and that can be accessed by a computer. In addition, any connection is suitably made to a computer-readable medium.

[0141] For example, if the software is transmitted from a website, server, or other remote source using coaxial cable, fiber optic cable, twisted pair, digital subscriber line (DSL), or wireless technologies such as infrared, radio, and microwave, then the coaxial cable, fiber optic cable, twisted pair, digital subscriber line, or wireless technologies such as infrared, radio, and microwave are included within the definition of media. Disk and disc, as used herein, includes compact discs, laser discs, optical discs, digital versatile discs (DVDs), floppy disks, and Blu-ray discs, where disks usually reproduce data magnetically, whereas discs reproduce data optically using lasers. Combinations of the above should also be included within the scope of computer-readable media.

[0142] A software module may reside in RAM memory, flash memory, ROM memory, EPROM memory, EEPROM memory, registers, a hard disk, a removable disk, a CD-ROM, or any other form of storage medium known in the art. An exemplary storage medium may be coupled to the processor such that the processor can read information from, and write information to, the storage medium. Alternatively, the storage medium may be integral to the processor. The processor and the storage medium may reside in an ASIC. The ASIC may reside in a user terminal. Alternatively, the processor and the storage medium may reside as discrete components in the user terminal.

[0143] While the embodiments described above have been described as utilizing aspects of the presently disclosed subject matter in one or more standalone computer systems, the present disclosure is not limited thereto and may be implemented in conjunction with any computing environment, such as a network or distributed computing environment. Furthermore, aspects of the present disclosure may be implemented in multiple processing chips or devices, and storage may be similarly affected across multiple devices. Such devices may include personal computers, network servers, and portable devices.

[0144] While the present disclosure has been described in connection with certain embodiments herein, various modifications and variations may be made without departing from the scope of the present disclosure, which would be apparent to those skilled in the art. Furthermore, such modifications and variations are intended to fall within the scope of the claims appended to this specification.

Claims

1. A method for predicting an insurance yield index of an insurance contract, performed by at least one processor, Step of collecting data related to the insurance contract; A step of inputting the collected data into a first group model associated with future cash flow prediction to determine a value associated with the cash flow prediction at a first future point in time; A step of calculating a value associated with a discounted present value at the time of the insurance contract based on a value associated with the cash flow forecast at the first future point in time; and A step of predicting the insurance profit index using a second group model based on the values ​​associated with the present value calculated above and the collected data. A method for predicting an insurance yield index, comprising:

2. In paragraph 1, The step of collecting data related to the above insurance contract is: Step of collecting categorical and non-categorical data associated with the above insurance contract Including, The above categorical data is, Contains data related to at least one of gender, age, type of covered disease, type of coverage, scope of coverage, method of premium payment, renewal of premium, special contract, occupation, income level, area of ​​residence, smoking, family history, payment method, start of coverage, diagnostic criteria, payment conditions, contract conclusion channel, risk rating, health status, discount rate application method, risk adjustment method, or contract group. The above non-categorical data is, A method for predicting an insurance yield index, comprising data associated with at least one of insurance premium, insurance amount, insurance contract period, insurance lapse period, insurance waiting period, subscription age, subscription lapse period, coverage waiting period, health index, body mass index, income, coverage limit, coverage ratio, risk adjustment ratio, annual inflation rate, discount rate, investment return, government bond yield, mortality rate, disease incidence rate, insurance continuation rate, payment rate, contract administration cost, claim processing cost, or operating incidental cost.

3. In paragraph 2, The above first group model is, A first-1 model that receives time series data associated with the categorical data or the non-categorical data and predicts a first predicted value associated with a cash flow prediction at the first future point in time, A first-second model that receives variable data associated with the categorical data or the non-categorical data and predicts a second predicted value associated with the cash flow prediction of the first future point in time, and An insurance yield index prediction method, comprising a 1-3 model for determining a prediction value associated with a cash flow forecast at the first future point in time based on a first prediction value of the 1-1 model and a second prediction value of the 1-2 model.

4. In paragraph 3, The above second group model is, A second-1 model that provides a first predicted value associated with the insurance profit index by receiving at least one of the preset data associated with the discounted present value at the time of the insurance contract calculated above, the categorical data or the non-categorical data; A second-2 model that receives at least one of the values ​​associated with the discounted present value at the time of the insurance contract calculated above, the variable data associated with the categorical data or the non-categorical data, and provides a second predicted value associated with the insurance profit index, and An insurance profit index prediction method, comprising a 2-3 model for determining the insurance profit index based on a first prediction value of the 2-1 model and a second prediction value of the 2-2 model.

5. In paragraph 1, After the step of predicting the above insurance profit index, Step for outputting the above-determined insurance profit index A method for predicting an insurance yield index, which further includes:

6. A computer-readable, non-transitory recording medium recording commands for executing the method according to Article 1 on a computer.

7. In information processing systems, memory; and One processor connected to said memory and configured to execute at least one computer-readable program contained in said memory Including, At least one of the above programs, Collect data related to insurance contracts, By inputting the above collected data into a first group model associated with future cash flow forecasting, a value associated with the cash flow forecasting at the first future point in time is determined, Based on the value associated with the cash flow forecast at the first future point in time, a value associated with the discounted present value at the time of the insurance contract is calculated, An information processing system comprising commands for predicting an insurance yield index based on a value associated with the calculated present value and the collected data.

8. In paragraph 7, At least one of the above programs, When collecting data related to the above insurance contract, it includes commands for collecting categorical data and non-categorical data related to the above insurance contract, The above categorical data is, Contains data related to at least one of gender, age, type of covered disease, type of coverage, scope of coverage, method of premium payment, renewal of premium, special contract, occupation, income level, area of ​​residence, smoking, family history, payment method, start of coverage, diagnostic criteria, payment conditions, contract conclusion channel, risk rating, health status, discount rate application method, risk adjustment method, or contract group. The above non-categorical data is, An information processing system including data associated with at least one of insurance premiums, insurance benefits, insurance contract period, insurance lapse period, insurance waiting period, subscription age, subscription lapse period, coverage waiting period, health index, body mass index, income, coverage limit, coverage ratio, risk adjustment ratio, annual inflation rate, discount rate, investment return, government bond yield, mortality rate, disease incidence rate, insurance continuation rate, payment rate, contract administration cost, claim processing cost, or operating incidental cost.

9. In paragraph 8, The above first group model is, A first-1 model that receives time series data associated with the categorical data or the non-categorical data and predicts a first predicted value associated with a cash flow prediction at the first future point in time, A first-second model that receives variable data associated with the categorical data or the non-categorical data and predicts a second predicted value associated with the cash flow prediction of the first future point in time, and An information processing system, comprising a 1-3 model for determining a predicted value associated with a cash flow forecast at the first future point in time based on a first predicted value of the 1-1 model and a second predicted value of the 1-2 model.

10. In paragraph 9, The above second group model is, A second-1 model that provides a first predicted value associated with the insurance profit index by receiving at least one of the preset data associated with the discounted present value at the time of the insurance contract calculated above, the categorical data or the non-categorical data; A second-2 model that receives at least one of the values ​​associated with the discounted present value at the time of the insurance contract calculated above, the variable data associated with the categorical data or the non-categorical data, and provides a second predicted value associated with the insurance profit index, and An information processing system, comprising a 2-3 model for determining the insurance profit index based on the first prediction value of the 2-1 model and the second prediction value of the 2-2 model.

11. A method for predicting an insurance yield index of an insurance contract, performed by at least one processor, A step of collecting data related to an insurance contract; and A step of predicting the insurance profit index of the insurance contract by inputting the collected data into a pre-learned insurance profit index prediction model. Including, The data associated with the above insurance contract includes categorical data and non-categorical data, The above insurance profit index prediction model is a model trained to predict the correct insurance profit index based on categorical learning data and non-categorical learning data. The above correct answer insurance profit index is a method for predicting an insurance profit index, wherein the above correct answer insurance profit index calculates a value associated with a cash flow at a future point in time based on the above categorical learning data and the above non-categorical learning data, calculates a value associated with a discounted present value at the time of an insurance contract based on the value associated with the cash flow at the future point in time, and calculates a value associated with a discounted present value at the time of an insurance contract based on the value associated with the present value and a risk-adjusted value.

Images