WO2023132544A1

WO2023132544A1 - Apparatus, method, and computer program for providing asset allocation portfolio for which investment type is considered

Info

Publication number: WO2023132544A1
Application number: PCT/KR2022/021262
Authority: WO
Inventors: 김병주; 이성순; 이승규
Original assignee: 주식회사 두물머리
Priority date: 2022-01-10
Filing date: 2022-12-26
Publication date: 2023-07-13
Also published as: KR102428665B1

Abstract

The present specification relates to a method, an apparatus, and a computer program for providing an asset management service for which investment type is considered. The method for providing an asset management service for which investment type is considered comprises the steps of: acquiring financial target information and investment propensity information about an investor; setting an objective function on the basis of a value function in which a risk aversion propensity and a loss aversion propensity included in the investment propensity information are applied to the utility of profit and loss; generating, for each of one or more investment types, a plurality of asset allocation portfolios corresponding to expiry, target profit, and initial asset size included in the financial target information from among pre-stored portfolios; and selecting, for each of the one or more investment types, an optimal portfolio from among the generated plurality of asset allocation portfolios on the basis of the set objective function.

Description

Device, method and computer program for providing asset allocation portfolio considering investment method

This specification relates to an apparatus, method, and computer program for providing an asset allocation portfolio in consideration of an investment method, and more specifically, asset allocation to improve the probability of achieving a target return expected through investor's asset management in consideration of one or more investment methods. It relates to a portfolio providing device and method.

Portfolio is an investment method to reduce risk while increasing investment return by diversifying investment by combining products with low risk and high profitability in asset investment.

Conventional portfolios have been made in such a way that experts (investment advisory companies, fund managers, etc.) with skilled knowledge in the investment comprehensively analyze and provide environmental factors such as investment propensity, cost, and economic flow of the investor.

However, recently, as artificial intelligence (AI) technology and the electronic device industry have advanced and communication infrastructure has been expanded, the Robo Advisor system that provides the investor's investment portfolio using artificial intelligence (AI) has been developed. Various studies are being conducted on this, and the prevalence rate is increasing exponentially.

In general, a robo-advisor system is configured to output the optimal investment ratio for each asset class, recommended items for each asset class, and optimal trading quantity for each recommended item according to the input investment amount and environmental factors. At this time, the asset class refers to categories such as 'domestic stocks', 'domestic bonds', 'overseas stocks', and 'overseas bonds', which are categories for classifying investment types, and recommended items refer to items included in the corresponding asset class. .

At this time, the portfolio according to the robo-advisor system was made with a focus on generating the maximum return against the investor's risk, and did not reflect the investor's individual goal achievement needs and risk appetite. For example, person A may be satisfied with the same amount of money, while person B may not be satisfied. Also, for the same loss of 100,000 won, person A is mentally unbearable, while person B can afford the loss. As such, each individual's goal achievement needs and risk appetite are different.

On the other hand, each investor has a different target return expected through asset management and a range of tolerable losses. In the case of conventional asset allocation portfolios, there were limitations in satisfying both the different target achievement needs and risk appetites of each investor.

At least some embodiments of the present specification provide an asset allocation portfolio that considers an investment method that optimizes the investor's utility and improves the probability of achieving a target return by reflecting both the investor's individualized goal and individual risk appetite. Apparatus, method and computer Its purpose is to provide a program.

A method for providing an asset allocation portfolio considering an investment method according to an embodiment of the present specification includes acquiring financial goal information and investment propensity information of an investor; setting an objective function based on a value function obtained by applying risk aversion and loss aversion included in the investment propensity information to utility for profit and loss; generating a plurality of asset allocation portfolios corresponding to maturity, target return, and initial asset size included in the financial target information among pre-stored portfolios for each of one or more investment methods; and selecting an optimal portfolio from among a plurality of asset allocation portfolios extracted based on a set objective function for each of the one or more investment methods, wherein the investment method is a deferment method in which the initial investment is deferred until maturity, the initiator investment In addition, it is characterized in that it includes any one or more of an accumulation type that periodically accumulates additional payments and a payment type that periodically pays a preset payment amount of the initial investment.

In one embodiment, the method of providing an asset allocation portfolio in consideration of an investment method may further include calculating a target achievement probability according to an additional payment amount or payment amount based on the optimal portfolio.

In one embodiment, the method for providing an asset allocation portfolio in consideration of the investment method may further include calculating a target probability increase or decrease according to a one-time additional payment or payment size based on the optimal portfolio.

In one embodiment, the investment method is characterized in that it further comprises a complex method of changing to a payment method at a preset time after the deferment or accumulation type.

In one embodiment, a method for providing an asset allocation portfolio considering an investment method is characterized in that it includes reselecting a portfolio based on a profit/loss ratio according to an optimal portfolio and a set objective function at the time of event occurrence.

In one embodiment, the event occurrence time is a preset periodic or non-periodic time, a time when a preset rate of return is achieved, a time when a preset loss is reached, or a reselection request from an investor is received, a change in the investment amount occurs Characterized in that it includes any one or more of the viewpoints.

In one embodiment, the value function is any one of an exponential value function represented by Equation 1 below and a hybrid type of the exponential value function and a digital value function represented by Equation 2 do.

[Equation 1]

here,

and

are the risk aversion coefficients in the profit and loss intervals, respectively,

is the loss aversion coefficient.

[Equation 2]

In one embodiment, the step of selecting the optimal portfolio is characterized in that a portfolio having the largest expected value among expected values for each of the selectable portfolios is selected as the optimal portfolio.

In one embodiment, the expected value is an average value of state values at time t + 1 by applying a probability distribution calculated by the expected rate of return and volatility of a portfolio for a random portfolio at time t. .

In the asset allocation portfolio providing device according to another embodiment of the present specification, the communication unit for acquiring the investor's financial target information and investment propensity information; A memory for storing product names, expected rates of return, and standard deviations for each financial product; A processor connected to the communication unit and the memory, wherein the processor sets an objective function based on a value function obtained by applying the risk aversion propensity and the loss aversion propensity included in the investment propensity information to the utility for profit and loss, and sets one or more investments For each method, a plurality of asset allocation portfolios corresponding to the maturity, target return, and initial asset size included in the financial target information are generated from among the pre-stored portfolios, and for each of one or more investment methods, based on the set objective function It is characterized in that it is configured to select an optimal portfolio from among a plurality of extracted asset allocation portfolios.

In one embodiment, the processor is characterized in that based on the optimal portfolio calculates the target achievement probability according to the amount of additional payment or payment.

In one embodiment, the processor is characterized in that it calculates a target probability increase or decrease according to a one-time additional payment or payment size based on the optimal portfolio.

In one embodiment, the processor is characterized in that it is configured to reselect the portfolio based on the profit and loss ratio and the set objective function according to the optimal portfolio at the time of event occurrence.

In one embodiment, the processor selects a portfolio having the largest expected value among expected values for each of the selectable portfolios as an optimal portfolio.

A computer program stored in a computer readable medium according to another embodiment of the present specification is characterized by executing a method of providing an asset allocation portfolio considering the above investment method.

According to at least some embodiments of the present specification, by providing an asset allocation portfolio reflecting individualized goals and individual risk appetites in consideration of an investment method, it is possible to increase the utility of an investor.

In addition, according to an embodiment, the probability of achieving a target profit may be improved by optimizing the utility based on the distribution of the final profit or loss.

In addition, according to an embodiment, an investor can design an individual customized portfolio considering a direct investment method through the device of the present invention.

1 is a block diagram showing the configuration of an asset allocation portfolio providing device according to an embodiment of the present invention.

2 is a block diagram showing the structure of a processor according to an embodiment of the present invention.

3 and 4 are graphs for explaining a value function according to an embodiment of the present invention.

5 is a flowchart illustrating a method for providing an asset distribution portfolio according to an embodiment of the present invention.

6 is a flowchart illustrating a method of reselecting a portfolio according to an embodiment of the present invention.

7 to 9 are graphs showing simulation results according to an asset management service providing method considering an investment method according to an embodiment of the present invention.

10 to 12 are graphs showing probability distributions of expiration points according to an embodiment of the present invention.

13 to 16 are graphs showing simulation results according to a deferred asset allocation portfolio providing method according to an embodiment of the present invention.

17 to 25 are graphs showing simulation results when an objective function is applied in a hybrid form according to an embodiment of the present invention.

Various embodiments and/or aspects are now disclosed with reference to the drawings. In the following description, for purposes of explanation, numerous specific details are set forth in order to facilitate a general understanding of one or more aspects. However, it will also be appreciated by those skilled in the art that such aspect(s) may be practiced without these specific details. The following description and accompanying drawings describe in detail certain illustrative aspects of one or more aspects. However, these aspects are exemplary and some of the various methods in principle of the various aspects may be used, and the described descriptions are intended to include all such aspects and their equivalents. Specifically, “embodiment,” “example,” “aspect,” “exemplary,” etc., as used herein, is not to be construed as indicating that any aspect or design described is superior to or advantageous over other aspects or designs. Maybe not.

Hereinafter, the same reference numerals are given to the same or similar components regardless of reference numerals, and overlapping descriptions thereof will be omitted. In addition, in describing the embodiments disclosed in this specification, if it is determined that a detailed description of a related known technology may obscure the gist of the embodiment disclosed in this specification, the detailed description thereof will be omitted. In addition, the accompanying drawings are only for easy understanding of the embodiments disclosed in this specification, and the technical ideas disclosed in this specification are not limited by the accompanying drawings.

Unless otherwise defined, all terms (including technical and scientific terms) used in this specification may be used in a meaning commonly understood by those of ordinary skill in the art to which the present invention belongs. In addition, terms defined in commonly used dictionaries are not interpreted ideally or excessively unless explicitly specifically defined.

In addition, the term “or” is intended to mean an inclusive “or” rather than an exclusive “or”. That is, unless otherwise specified or clear from the context, “X employs A or B” is intended to mean one of the natural inclusive substitutions. That is, X uses A; X uses B; Or, if X uses both A and B, "X uses either A or B" may apply to either of these cases.

Also, the terms "comprises" and/or "comprising" mean that the feature and/or element is present, but excludes the presence or addition of one or more other features, elements and/or groups thereof. It should be understood that it does not. Also, unless otherwise specified or where the context clearly indicates that a singular form is indicated, the singular in this specification and claims should generally be construed to mean "one or more".

The suffixes "module" and "unit" for components used in the following description are given or used interchangeably in consideration of ease of writing the specification, and do not have meanings or roles that are distinct from each other by themselves.

An apparatus 200 (hereinafter referred to as an apparatus for providing an asset distribution portfolio) for providing an asset allocation portfolio considering an investment method may include a processor 210 , a communication unit 220 and a memory 230 . However, the above-described components are not essential to implement the asset allocation portfolio providing apparatus 200, and thus the asset allocation portfolio providing apparatus 200 may have more or fewer components than the above-listed components. The asset allocation portfolio providing device 200 may further include, for example, an input unit and an output unit. Here, each component may be configured as a separate chip, module, or device, or may be included in one device.

The processor 210 may typically process the overall operation of the asset allocation portfolio providing device 200 . The processor 210 may provide or process appropriate information or functions to a user by processing signals, data, information, etc. input or output through the components described above or by running an application program stored in the memory 230.

The communication unit 220 may include one or more modules enabling communication between the asset allocation portfolio providing device 200 and the communication system and between the asset allocation portfolio providing device 200 and external terminals and devices.

The communication unit 220 may include at least one of a mobile communication module, a wired Internet module, and a wireless Internet module.

In one embodiment, the communication unit 220 may communicate with an external device such as a financial server to periodically receive financial product information and store it in the storage unit 230 . Financial instrument information may include the product name, expected rate of return, and standard deviation (also referred to as volatility) for each financial instrument. Financial product information may be updated in real time or periodically.

In one embodiment, the communication unit 220 may communicate with an external device such as a financial server to receive investment propensity information and financial goal information of an investor and transmit them to the processor 210 . Here, the investment propensity information may include risk aversion coefficient and loss aversion coefficient, and the financial target information may include maturity, target return, and initial asset.

In another modification, some of the investment propensity information and financial target information may be received through the communication unit 220 and some may be received through an input unit (not shown).

In one embodiment, the memory 230 stores data and programs necessary for the asset allocation portfolio providing apparatus 200 to provide an asset allocation portfolio.

In one embodiment, the memory 230 may store expected returns and standard deviations of financial products included in each portfolio. Also, the memory 230 may store mathematical formulas for calculating and selecting portfolios.

In one embodiment, the memory 230 may store a portfolio generation algorithm for generating an asset allocation portfolio by combining products to meet an investor's financial target information based on expected returns and standard deviations of financial products.

In one embodiment, the memory 230 may store a goal achievement probability calculation algorithm for calculating a goal achievement probability according to an additional payment amount or payment amount for a certain portfolio.

In one embodiment, the memory 230 may store a target probability increase or decrease value calculation algorithm for calculating a target probability increase or decrease according to a one-time additional payment or payment size for a certain portfolio.

The memory 230 may include a memory and/or a permanent storage medium. Memory is a flash memory type, a hard disk type, a multimedia card micro type, a card type memory (eg SD or XD memory, etc.), RAM (Random Access Memory, RAM), SRAM (Static Random Access Memory), ROM (Read-Only Memory, ROM), EEPROM (Electrically Erasable Programmable Read-Only Memory), PROM (Programmable Read-Only Memory), magnetic memory, magnetic disk, optical disk At least one type of storage medium may be included.

The memory 230 may store any type of information generated or determined by the processor 210 and any type of information received by the communication unit 220 . The memory 230 may be implemented as an aggregate of physically separated storage devices.

2 is a block diagram showing the structure of a processor according to an embodiment of the present invention, and FIGS. 3 and 4 are graphs for explaining a value function according to an embodiment of the present invention.

2 is a diagram showing the functional structure of a processor for convenience of explanation. Referring to FIG. 2, the processor 210 includes a target function setting module 212, a portfolio creation module 214, a portfolio selection module 216, and a portfolio. A reselection module 218 may be included.

The objective function setting module 212 sets an objective function based on the value function of the investor's profit/loss ratio.

In one embodiment, the value function for the profit and loss ratio of the investor is calculated by applying the risk aversion and loss aversion included in the investment propensity information to the utility of the profit and loss.

In one embodiment, the value function may be expressed in the form of a function such as Equation 1 as an exponential value function, but is not limited thereto, and may be expressed in various functions such as a quadratic function.

[Equation 1]

here,

and

is the risk aversion coefficient in the profit and loss range, respectively, and represents the tendency to avoid fluctuations in profit and loss.

and

is the risk aversion coefficient in the profit and loss range, respectively, and represents the tendency to avoid fluctuations in profit and loss. In one embodiment

and

is assumed to be the same value, but is not limited thereto.

is the loss aversion coefficient, which represents the ratio of the relative utility reduction of loss to profit.

V(s) is the value function value of the profit and loss rate (horizontal axis: state s) drawn with 0 as the reference point for profit and loss, and can be represented graphically as shown in FIG. 3.

3 and 4, the horizontal axis represents the profit/loss ratio (state), and the vertical axis represents the value function (V(s)). 0 is the profit and loss reference point (reference point), the right side (+) of the reference price 0 on the x-axis shows the value function for the rate of return, and the left (-) value of the loss rate on the center of the reference price 0 on the x-axis show the function

The profit and loss standard price may be different for each investor.

Referring to FIG. 3, the same loss aversion coefficient (

= 3), the graph of the value function when the risk aversion coefficient α is 2 is red, the graph of the value function when the risk aversion coefficient α is 3 is green, and the value function when the risk aversion coefficient α is 4 The graph of is shown in blue. As the risk aversion coefficient α increases from 2 to 4, it can be seen that it is more sensitive to profit and loss.

Referring to FIG. 4, for the same risk aversion coefficient (α = 2), the loss aversion coefficient

When is 2, the value function is red, and the loss aversion coefficient

When is 3, the value function is green, and the loss aversion coefficient

The value function when is 4 is shown in blue.

loss aversion coefficient

It can be seen that the greater the value from 2 to 4, the more sensitive it is to the loss.

In addition, it can be seen from FIGS. 3 and 4 that the change in the loss rate is greater than the increase or decrease in the return rate. In addition, it can be seen that the increase or decrease in utility gradually decreases in a region where the rate of return or loss rate is large (for example, 1.00 or more and -1.00 or less).

On the other hand, if the goal is to achieve a target return and limit loss regardless of risk aversion at the time of maturity, a value function in the form of a digital function can be applied as follows.

That is, if the base price is exceeded, the value of the value function becomes 1, and if the base price is not exceeded, the value of the value function becomes 0.

In some cases, the target function setting module 212 may apply the objective function in a hybrid form of an exponential value function and a digital function.

The portfolio creation module 214 generates a plurality of asset allocation portfolios that meet the maturity, target return, and initial asset size included in the financial target information among the pre-stored portfolios for each of one or more investment methods. Here, the investment method includes any one or more of a deferment method for deferring the initial investment until maturity, an accumulation method for periodically accumulating additional payments in addition to the initiator investment, and a payment method for periodically paying a preset payment of the initial investment. Here, the accumulation or payment cycle can be freely set to weekly, monthly, quarterly, or yearly.

In addition, the investment method may further include a complex method of changing to a payment method at a preset time after a deferment or accumulation type.

An annuity product is an example of a complex method. Annuity products can be converted from an installment-type investment method that periodically accumulates additional payments before retirement to a payment-type investment method that periodically pays preset payments out of the amount accumulated from the point of retirement.

The portfolio generation module 214 may generate a plurality of asset allocation portfolios using a pre-stored portfolio generation algorithm. As such, the algorithm for generating a portfolio considering the investor's financial target information and the expected rate of return and volatility of the product is already widely known, so a detailed description thereof will be omitted.

The optimal portfolio selection module 216 selects an optimal portfolio from among a plurality of asset allocation portfolios generated based on a set objective function for each of one or more investment methods. That is, the optimal portfolio selection module 216 selects an optimal product combination among a plurality of product combinations generated based on the set objective function as an optimal portfolio.

For example, the optimal portfolio selection module 216 may select an optimal portfolio A for the deferred investment method, an optimal portfolio B for the installment investment method, and an optimal portfolio C for the payment investment method.

In one embodiment, the optimal portfolio selection module 216 calculates an expected value of each of a plurality of asset allocation portfolios generated to select an optimal portfolio based on a set objective function for each of one or more investment methods, An asset allocation portfolio having the highest expected value among calculated expected values may be selected as an optimal portfolio. Here, the expected value is the customer satisfaction utility.

In one embodiment, the optimal portfolio selection module 216 determines the return rate state of the ith portfolio at time t.

An expected value in Equation 2 is obtained according to the Bellman optimality equation.

First, the set A of selectable portfolios is

can be expressed as Here, action a means selecting one portfolio.

The value represents the expected rate of return and standard deviation (volatility) of portfolio a.

[Equation 2]

is state

This is the expected value when action a is selected in .

Here, Pr is the state of the current time t

state at time t+1

As the transition probability to , it can be obtained by Equation 3.

[Equation 3]

Here, the function N(•) is a standard normal distribution function,

The values are the expected return of portfolio a and the standard deviation (volatility).

In one embodiment, it is assumed that the distribution of returns follows GBM (Geometric Brownian motion), but is not limited thereto, and a t-distribution or data distribution of real assets may be applied.

Selecting the portfolio having the largest expected value among the expected values for each of the plurality of generated portfolios as the optimal portfolio can be expressed as in Equation 4.

[Equation 4]

here,

The value is max(

) is the value

The portfolio a that maximizes the value is the optimal portfolio for that state. The expected value Q at time t is the expected return on the parameter of portfolio a (

), volatility (

), and is the average of the state values at t+1. In this way, since the expected value Q is obtained backward, the value value is calculated in the reverse direction starting from the objective function at the time of expiration until the time t = 0. Since the present value is derived from the optimal value of the future, optimizing the current action becomes a choice considering the optimal action in the future.

The portfolio reselection module 218 reselects the portfolio based on the rate of return according to the optimal portfolio at the time of event occurrence.

Here, the event occurrence time is any one of a preset cycle or non-cycle time, a preset return rate, a preset loss, a reselection request from an investor, or a change in the investment amount. may contain more than Here, there may be a case where a change in the investment amount occurs, for example, when a payment occurs on a specific day (birthday, anniversary, etc.).

The portfolio reselection module 218 may reselect a future portfolio based on the profit/loss ratio achieved on a quarterly basis, for example, when the event occurrence time is set to quarterly. Or, at the point of achieving a pre-set rate of return, the portfolio can be reselected more conservatively to keep the rate of return already achieved. At this time, even when the portfolio is reselected, the loss aversion propensity of each customer can be applied.

In this way, the probability of achieving the customer's goal is increased by the portfolio reselection module 218 .

Hereinafter, a method of providing an asset distribution portfolio in consideration of an investment method by the apparatus for providing an asset distribution portfolio described in FIGS. 1 to 2 will be described in detail with reference to FIGS. 5 to 25 .

5 is a flowchart illustrating a method of providing an asset distribution portfolio considering an investment method according to an embodiment of the present invention.

First, in step S100, the processor acquires the investor's financial target information and investment propensity information. Financial target information includes maturity, target profit, and initial asset size, and investment propensity information includes risk aversion and loss aversion. In one embodiment, a pre-prepared diagnosis table for determining the value of an investor's achievement of a target return and loss limit may be provided, and a quantified value function may be calculated through the diagnosis table checked by the investor.

In step S110, the processor sets an objective function based on the value function for the investor's profit/loss ratio.

In one embodiment, the value function is a function obtained by applying the investor's risk aversion and loss aversion to utility for profit and loss, and the objective function is an action a (portfolio selection) to obtain the investor's goal (time, rate of return) ) is a function that maximizes the expected value.

The value function can be expressed as in Equation 1 above.

In step S120, for each of one or more investment methods, a plurality of asset allocation portfolios corresponding to the maturity, target return, and initial asset size included in the financial target information are generated from among the pre-stored portfolios using a portfolio generation algorithm. For example, a plurality of asset allocation portfolios for the deferred investment method are created, a plurality of asset allocation portfolios for the accumulation type investment method are created, and a plurality of asset allocation portfolios for the payment investment method are created.

In the next step S130, an optimal portfolio is selected from among a plurality of generated asset allocation portfolios for each of one or more investment methods based on the objective function set in the previous step S110. For example, an optimal asset allocation portfolio for deferred investment method is selected, an optimal asset allocation portfolio for installment investment method is selected, and an optimal asset allocation portfolio for payment investment method is selected.

For each of one or more investment methods, expected values of the generated plurality of asset allocation portfolios are calculated, and an optimal portfolio is selected based on the calculated expected values.

In one embodiment, calculation speed can be improved by adopting a method of converting the reserve money and the payment into a probability distribution.

In one embodiment, in the selected optimal portfolio, it is possible to calculate the target achievement probability according to the size of the reserve or payout according to the pre-stored target achievement probability algorithm in the accumulation type investment method or the payment method. For example, if you pay 1 million won per month for 10 years, you can calculate the probability of achieving the * billion goal **%.

In one embodiment, in the selected optimal portfolio, the increase or decrease in the target achievement probability can be calculated according to the pre-stored target achievement probability algorithm for one-time additional payments or payments in the deferred investment method, the savings investment method, or the payment investment method. there is. For example, if one million won is currently paid as a one-off, the increase in the probability of achieving the *billion goal **% can be calculated.

In addition, in the selected optimal portfolio, an optimal reserve amount or payment amount required to reach a goal achievement probability may be calculated according to a goal achievement probability algorithm stored in advance. For example, it can be calculated that the optimal reserve and payment amount to achieve the ** billion goal by 90% or more *** is ten thousand won.

After that, in step S140, the asset allocation portfolio is reselected by monitoring whether an event occurs over time.

In one embodiment, the asset allocation portfolio is reselected based on the rate of return and the objective function at the time of event occurrence.

In step S210, the portfolio reselection module 218 monitors the occurrence of an event. Here, the occurrence of the event may be any one of a preset cycle or non-cycle time, a preset return rate, a preset loss, a reselection request from an investor, or a change in the investment amount. there is.

In step S220, the portfolio reselection module 218 determines whether the value function is changed based on the reacquired information.

In S230, if it is determined that the value function is changed, the objective function setting module resets the objective function based on the changed value function.

In step S240, the portfolio reselection module reselects the optimal portfolio according to the reset objective function. In one embodiment, the portfolio reselection module calculates expected values of a plurality of asset allocation portfolios generated according to the reset objective function, and selects an optimal portfolio based on the calculated expected values.

7 to 9 are graphs showing simulation results according to a method for providing asset management services considering an investment method according to an embodiment of the present invention, and FIGS. 10 to 12 show probability distributions at maturity according to an embodiment of the present invention. it's a graph

In one embodiment of the present invention, assuming a 10-year maturity, a target return of 6%, and an initial asset of 100, it is a simulation result assuming a 4% annual accumulation in the accumulation-type investment method and a 4% annual payment method in the payment-type investment method .

The x-axis of the Action Heatmap is the time axis in terms of months, and the y-axis is the state axis, which is the value representing the portfolio's asset value with a base price of 100. When the action value is high (yellow), risky assets are selected, and when the action value is low (purple), safe assets are selected. The investment principal is shown as a solid blue line.

7 is an action heatmap of the optimal portfolio of the deferred investment method, and the base price (RP) at the time of maturity is 179, and FIG. 9 is an action heatmap of the optimal portfolio of the payment type investment method, and the base price (RP) at the time of maturity is 124.

10 is a graph showing the probability distribution at maturity of the optimal portfolio of the deferred investment method, FIG. 11 is a graph showing the probability distribution of the optimal maturity of the portfolio of the savings-type investment method, and FIG. This is a graph showing the probability distribution at maturity of a portfolio.

10, 11, and 12, the blue distribution represents the probability distribution of assets to maturity according to the optimal portfolio, and the orange distribution represents the probability distribution of assets to maturity according to one portfolio (portfolio with an average return of 6.4%) without optimization as a control.

Through the simulations of FIGS. 7 to 12 , it can be confirmed that the optimal portfolio based on the objective function maximizes the probability of achieving a rate of return rather than maximizing the rate of return.

Parameters for each of the 8 portfolios included in the set of portfolios

,

is assumed to be as shown in Table 1 below.

AA	1One	22	33	44	55	66	77	88
	0.0150.015	0.0280.028	0.0440.044	0.0550.055	0.0640.064	0.0720.072	0.080.08	0.0850.085
	0.020.02	0.040.04	0.060.06	0.080.08	0.10.1	0.120.12	0.140.14	0.160.16

13 to 16, under the assumption of the parameters in Table 1, the maturity period is 5 years (60 months), the target rate of return is 40%, the loss limit is -10%, and the digital function is applied as the maturity value function to rebalance the period. This is the simulation result when (portfolio reselection period) is set to 1 month.

In (a) of FIGS. 13 to 16, the Action Heatmap represents the optimal portfolio, the x-axis of the Action Heatmap is the time axis in monthly units, and the y-axis is the state axis and is a value representing the asset value of the portfolio with a base price of 100. When the action value is high (yellow), risky assets are selected, and when the action value is low (purple), safe assets are selected.

In FIG. 14, the Prob Heatmap indicates the probability of achieving the goal, and the brighter the color, the higher the probability of achieving the goal. The x-axis of the Prob Heatmap is the time axis by month, and the y-axis is the state axis.

In FIG. 15, the Dist Plot shows the distribution of portfolio returns over time. The yield at 12 months is shown in purple in the first graph, and it can be seen that the distribution is concentrated around the target rate of return (140) and the limiting loss rate (90) as the expiration date approaches 60 months.

In FIG. 16, Dist Compare is a graph comparing a log normal distribution in the case where the initially set portfolio is maintained until maturity and a distribution in the case of resetting the portfolio (action) at each event occurrence point at maturity. A graph in which the portfolio is reset at each event occurrence point is shown in purple, and graphs in other colors indicate a case in which the initially set portfolio is maintained as it is. It can be seen that the rate of return of the purple graph, which resets the portfolio at each event, is concentrated around the target rate of return compared to the graphs of other colors. The result values for each distribution are shown in Table 2.

DistDist	수익률평균값average rate of return	수익률중간값median rate of return	목표달성확률Probability of goal achievement	원금보장확률Probability of principal guarantee	CVaR(99%)CVaR (99%)	손실제한확률Loss Limit Probability
actionaction	32.2%32.2%	43.0%43.0%	67.1%67.1%	80.3%80.3%	-42.5%-42.5%	96.0%96.0%
μ, σ = 8.5%, 16%μ, σ = 8.5%, 16%	53.0%53.0%	43.0%43.0%	53.1%53.1%	84.6%84.6%	-44.4%-44.4%	90.6%90.6%
μ, σ = 8.0%, 14%μ, σ = 8.0%, 14%	49.2%49.2%	41.5%41.5%	52.3%52.3%	87.2%87.2%	-38.2%-38.2%	92.9%92.9%
μ, σ = 7.2%, 12%μ, σ = 7.2%, 12%	43.3%43.3%	38.0%38.0%	48.7%48.7%	88.9%88.9%	-31.9%-31.9%	94.7%94.7%
μ, σ = 6.4%, 10%μ, σ = 6.4%, 10%	37.7%37.7%	34.0%34.0%	43.3%43.3%	90.9%90.9%	-26.2%-26.2%	96.4%96.4%
μ, σ = 5.5%, 8%μ, σ = 5.5%, 8%	31.7%31.7%	29.0%29.0%	34.1%34.1%	92.8%92.8%	-19.5%-19.5%	98.0%98.0%
μ, σ = 4.4%, 6%μ, σ = 4.4%, 6%	24.6%24.6%	23.0%23.0%	18.4%18.4%	94.4%94.4%	-2.0%-2.0%	99.1%99.1%
μ, σ = 2.8%, 4%μ, σ = 2.8%, 4%	15.0%15.0%	14.0%14.0%	1.6%1.6%	93.7%93.7%	-2.0%-2.0%	99.6%99.6%
μ, σ = 1.5%, 2%μ, σ = 1.5%, 2%	7.8%7.8%	7.0%7.0%	0.0%0.0%	94.3%94.3%	-1.0%-1.0%	100.0%100.0%

In Table 2, the result value when the portfolio is reset at each event occurrence point is shown as an action. It can be seen that the probability of achieving the goal of Action is 67.1%, which is significantly increased compared to other cases where the initially set portfolio is maintained as it is. In Table 2, CVaR represents the average loss amount of the bottom 1% with the worst return, and it can be seen that Action's CVaR is lower than other cases where the initially set portfolio is maintained as it is. It can be seen that the probability of achieving the goal is higher than when the portfolio with the highest volatility σ is maintained until maturity, and the CVaR values are similar. It can be seen that the increasing probability of achieving the goal progresses in the direction of exchanging the possibility of excess return with the stability of achieving the goal by reselecting the portfolio with low volatility at the time the goal is reached.

Here, the hybrid form is the application of the exponential value function and the digital value function together, and each objective function assumes a 25% return -15% loss based on a 3-year maturity, and the exponential value function is used as a parameter.

and

is 1.5,

1 was applied. The exponential value function can change and apply parameters according to individual risk aversion propensity.

The distribution of final profit and loss and the change in the asset proportion action can be confirmed by the difference in the value function at maturity, and the action gradation is determined by the difference in the proportion of the index value function and the digital value function. The digital function serves to penalize the achievement of RP and can be used as an extreme substitute for α ^- value.

The action map in FIG. 18 is in the form of an added path penalty function, and a penalty is applied by fixing the value of the state value below the loss-limited return (85%) to -1 even at a time other than maturity.

Referring to FIGS. 17, 20, and 23, the investor's value function has an RP of approximately 125 and feels the most value in state 125, but the weight for value becomes very small beyond state 125. Therefore, until reaching state 125 in the action map, a portfolio with a high target rate of return is selected even if the volatility is high, and if it exceeds state 125, a portfolio with low volatility is reselected even if the target rate of return is small.

Referring to FIGS. 18, 21, and 24, the investor's value function feels a high value for loss when the state is 85 or less, and the value generally increases as the state increases.

In the case of the investor, even if the rate of return is achieved, even if the range of volatility is not significantly lowered, the portfolio with a higher target rate of return is reselected or the existing portfolio is maintained.

Referring to Figures 19, 21 and 24, it is almost similar to the first investor, but in the case of the investor, since the value fluctuations are large in states 85, 100, and 125, at the point of return approaching state85, 100, 125 Reselect your portfolio. This maximizes utility by increasing the probability of achieving the target rate of return for investors.

According to an embodiment of the present invention, it is possible to provide an asset allocation portfolio tailored to individual goals by using an optimization algorithm considering 1) an individual's loss aversion tendency and risk appetite, 2) based on goal-based investment, and 3) an investment method. can

If conventional derivatives such as ELS are based on a method of matching payoffs with changes in underlying assets, the asset allocation portfolio provided according to an embodiment of the present invention can optimize utility with the distribution of final profit and loss.

Meanwhile, according to an embodiment of the present specification, execution of a method for providing an asset allocation portfolio by an apparatus for providing an asset allocation portfolio may be implemented as a software program and recorded on a predetermined computer-readable recording medium. The recording medium may include, for example, a computer readable recording medium suitable for storing computer program instructions and data.

Computer readable recording media suitable for storing computer program instructions and data include, for example, semiconductor memory devices such as EPROM, EEPROM and flash memory devices, magnetic disks such as internal hard disks or external disks, magneto-optical disks and CD-ROMs. Includes all forms of non-volatile memory, media and memory devices, including ROM and DVD-ROM disks. The processor and memory may be supplemented by, or incorporated into, special purpose logic circuitry.

The functional operations and implementations described in this specification may be implemented as digital electronic circuitry, implemented as computer software, firmware, or hardware, or as a combination of one or more of these. Implementations described herein are implemented as one or more modules of computer program instructions encoded on a tangible program storage medium for execution by or for controlling the operation of one or more computer program products, that is, a data processing device. It can be.

Although the drawings herein depict operational processes, it should not be understood that all illustrated operations must be performed or that those operations must be performed in the specific order shown to obtain desired results. In certain cases, multitasking and parallel processing can be advantageous.

Certain embodiments have also been described herein. The embodiments are within the scope of the following claims. For example, the actions recited in the claims can be performed in a different order and still achieve desirable results.

The above description is merely illustrative of the technology of this specification, and various modifications may be made by those skilled in the art to which this specification belongs without departing from the technical spirit of this specification. Therefore, the embodiments disclosed herein are not intended to limit the scope of the present specification. The scope of this specification should be construed by the claims below, and all technologies within the scope equivalent thereto should be construed as being included in the scope of this specification.

The present invention can be used in the financial industry, such as providing an asset allocation portfolio considering an investment method.

Claims

Acquiring investor's financial goal information and investment propensity information;

setting an objective function based on a value function obtained by applying risk aversion and loss aversion included in the investment propensity information to utility for profit and loss;

generating a plurality of asset allocation portfolios corresponding to maturity, target return, and initial asset size included in the financial target information among pre-stored portfolios for each of one or more investment methods; and

For each of one or more investment methods, selecting an optimal portfolio from among a plurality of asset allocation portfolios extracted based on the set objective function

including,

The investment method includes at least one of a deferment type for deferring the initial investment until maturity, an accumulation type for periodically accumulating additional payments in addition to the initiator investment, and a payment type for periodically paying a preset payment of the initial investment. A method of providing an asset allocation portfolio considering the investment method.
According to claim 1,

Calculating the probability of achieving a goal according to the amount of additional payment or payment based on the optimal portfolio

A method for providing an asset allocation portfolio considering an investment method further comprising.
According to claim 1,

Calculating a target probability increase or decrease according to the size of a one-time additional payment or payment based on the optimal portfolio

A method for providing an asset allocation portfolio considering an investment method further comprising.
According to claim 1,

The method of providing an asset allocation portfolio considering the investment method, characterized in that the investment method further comprises a complex method of changing to a payment method at a preset time after the deferment or accumulation type.
According to claim 1,

A step of reselecting a portfolio based on the profit/loss ratio according to the optimal portfolio at the time of event occurrence and the set objective function

A method of providing an asset allocation portfolio considering an investment method including
According to claim 5,

The event occurrence time is any one or more of a preset periodic or non-periodic time, a time when a preset rate of return is achieved, a time when a preset loss is reached, a time when a reselection request is received from an investor, or a time when a change in the investment amount occurs. A method of providing an asset allocation portfolio considering an investment method comprising a.
According to claim 1,

The value function provides an asset allocation portfolio, characterized in that either an index value function represented by Equation 1 below or a hybrid type of the index value function and a digital value function represented by Equation 2 method.

[Equation 1]

here,
and
are the risk aversion coefficients in the profit and loss intervals, respectively,
is the loss aversion coefficient.

[Equation 2]
According to claim 1,

The step of selecting the optimal portfolio is

A method of providing an asset allocation portfolio considering an investment method, characterized in that a portfolio having the largest expected value among the expected values for each of the selectable portfolios is selected as an optimal portfolio.
According to claim 8,

The expected value is the average value of state values at time t + 1 by applying a probability distribution calculated by the expected rate of return and volatility of the portfolio for any portfolio at time t Asset considering the investment method How to provide a distribution portfolio.
In the asset allocation portfolio providing device,

a communication unit that acquires investor's financial target information and investment propensity information;

A memory for storing product names, expected rates of return, and standard deviations for each financial product;

A processor connected to the communication unit and the memory

Including,

The processor

Establish an objective function based on a value function that applies the risk aversion and loss aversion included in the investment propensity information to the utility for profit and loss,

For each of one or more investment methods, a plurality of asset allocation portfolios corresponding to the maturity, target return, and initial asset size included in the financial target information are created among the pre-stored portfolios, and the objective function set for each of the one or more investment methods An asset allocation portfolio providing device characterized in that configured to select an optimal portfolio from among a plurality of asset allocation portfolios extracted based on.
According to claim 10,

The processor

An apparatus for providing an asset allocation portfolio, characterized in that for calculating a target achievement probability according to the amount of additional payment or payment based on the optimal portfolio.
According to claim 10,

The processor

An asset allocation portfolio providing device, characterized in that for calculating a target probability increase or decrease according to the size of a one-time additional payment or payment based on the optimal portfolio.
According to claim 10,

The processor

An asset allocation portfolio providing device characterized in that it is configured to reselect the portfolio based on the profit and loss rate according to the optimal portfolio and the set objective function at the time of event occurrence.
According to claim 10,

The value function provides an asset allocation portfolio, characterized in that either an index value function represented by Equation 1 below or a hybrid type of the index value function and a digital value function represented by Equation 2 Device.

[Equation 1]

here,
and
are the risk aversion coefficients in the profit and loss intervals, respectively,
is the loss aversion coefficient.

[Equation 2]
According to claim 10,

The processor

An apparatus for providing an asset allocation portfolio, characterized in that for selecting a portfolio having the largest expected value among expected values for each of selectable portfolios as an optimal portfolio.
A computer program stored in a computer readable medium to execute the asset allocation portfolio providing method considering the investment method of any one of claims 1 to 9.