WO2020235300A1 - ポートフォリオ作成支援装置およびポートフォリオ作成支援方法 - Google Patents

ポートフォリオ作成支援装置およびポートフォリオ作成支援方法 Download PDF

Info

Publication number
WO2020235300A1
WO2020235300A1 PCT/JP2020/017820 JP2020017820W WO2020235300A1 WO 2020235300 A1 WO2020235300 A1 WO 2020235300A1 JP 2020017820 W JP2020017820 W JP 2020017820W WO 2020235300 A1 WO2020235300 A1 WO 2020235300A1
Authority
WO
WIPO (PCT)
Prior art keywords
portfolio
return
risk
creation support
expected rate
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Ceased
Application number
PCT/JP2020/017820
Other languages
English (en)
French (fr)
Japanese (ja)
Inventor
学 菅沼
純 小川
山岡　雅直
拓哉 奥山
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Hitachi Ltd
Original Assignee
Hitachi Ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Hitachi Ltd filed Critical Hitachi Ltd
Priority to EP20809451.6A priority Critical patent/EP3975101A4/en
Priority to US17/611,946 priority patent/US20220230252A1/en
Priority to SG11202112705SA priority patent/SG11202112705SA/en
Publication of WO2020235300A1 publication Critical patent/WO2020235300A1/ja
Anticipated expiration legal-status Critical
Ceased legal-status Critical Current

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q40/00—Finance; Insurance; Tax strategies; Processing of corporate or income taxes
    • G06Q40/06—Asset management; Financial planning or analysis
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F30/00—Computer-aided design [CAD]
    • G06F30/20—Design optimisation, verification or simulation
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q10/00—Administration; Management
    • G06Q10/10—Office automation; Time management

Definitions

  • the present invention relates to a portfolio creation support device and a portfolio creation support method.
  • spin is used as a variable in calculation and an attempt is made to solve a computer that enables high-speed calculation for an inverse problem or a combination optimization problem that requires 100% search.
  • the external magnetic field is gradually reduced, and each spin is time-developed as the direction is determined according to the external magnetic field of each site at time t and the effective magnetic field determined by all the actions of the spin-to-spin interaction.
  • a technique (see Patent Document 1) has been proposed in which the system is almost maintained in the ground state by making the orientation quantum-mechanically corrected rather than completely aligned with the effective magnetic field.
  • the computer is used to affect the expected value of the profitability of each financial product and the profit.
  • Optimal utility function consisting of individual variable factors, which are factors unique to financial products, common variable factors, which are factors that affect the profitability of financial products as a whole, and risks that affect the profitability and profitability of financial products as a whole.
  • an object of the present invention is to provide a technique for efficiently generating a plurality of portfolio candidates based on the investment policy of each financial institution and presenting them to the user in an easily recognizable form.
  • the portfolio creation support device of the present invention that solves the above problems has a storage unit that stores information on each financial product, and an expected rate of return, risk of price decline, and market sensitivity in a portfolio that combines the predetermined financial products indicated by the information. It has a calculation unit that calculates a predetermined expression that combines each item and the weight of each item as an inging model, and the calculation unit is obtained for each pattern of the weight of each item as a result of the calculation. , Each portfolio that minimizes the value of the predetermined equation is output to a predetermined device.
  • an information processing apparatus provided with a storage unit that stores information on each financial product has an expected rate of return, a risk of price decline, and a market in a portfolio that combines predetermined financial products indicated by the above information.
  • a predetermined formula that combines each item of sensitivity and the weight of each item is calculated as an inging model, and as a result of the calculation, the value of the predetermined formula obtained for each pattern of the weight of each item is minimized. It is characterized in that each portfolio is output to a predetermined device.
  • the present invention it is possible to efficiently generate a plurality of portfolio candidates based on the investment policy of each financial institution and present them to the user in a form that is easy to recognize.
  • Patent Document 1 As shown in Patent Document 1 described above, the applicant has developed quantum computing technology and has tried to solve various problems in, for example, a 100% search problem based on big data (including the concept of combinatorial optimization problem). ..
  • quantum computers In general, there are high expectations for quantum computers for such 100% search problems.
  • a quantum computer is composed of basic elements called qubits and realizes "0" and "1" at the same time. Therefore, all solution candidates can be calculated at the same time as initial values, and there is a possibility that an 100% search can be realized.
  • quantum computers need to maintain quantum coherence over the entire computational time.
  • H ⁇ p be the Hamiltonian of the physical system in which the problem is set.
  • the Hamiltonian is not set to H ⁇ p, but another Hamiltonian H ⁇ 0 whose ground state is clear and easy to prepare.
  • H ⁇ p the Hamiltonian is not set to H ⁇ p, but another Hamiltonian H ⁇ 0 whose ground state is clear and easy to prepare.
  • H ⁇ p the Hamiltonian becomes equation (1).
  • adiabatic quantum computation For example, consider the gate operation to a certain quantum bit. At this time, if there is an interaction between that qubit and another qubit, it causes decoherence, but in adiabatic quantum computation, all qubits interact at the same time, so in the case of this example. Does not become decoherence. Reflecting this difference, adiabatic quantum computation is considered to be more robust to decoherence than quantum computers.
  • adiabatic quantum computation is effective for difficult problems that require 100% search.
  • the spin is used as a variable in the operation, and the problem to be solved is set by the interaction between spins and the local field acting on each spin.
  • Each spin is time-evolved as its orientation is determined according to the external magnetic field of each site at time t and the effective magnetic field determined by all the actions of the interaction between spins.
  • the spin direction is not completely aligned with the effective magnetic field, but the direction is quantum-mechanically corrected so that the system maintains the ground state.
  • the annealing method includes not only hardware mounted by an electronic circuit (digital circuit or the like) but also a method of mounting by a superconducting circuit or the like. Further, hardware that realizes the Ising model other than the annealing method may be used. For example, a laser network method (optical parametric oscillation), a quantum neural network, etc. are also included. Further, although some ideas are different as described above, the present invention can also be realized in a quantum gate method in which the calculation performed by the Ising model is replaced with gates such as a Hadamard gate, a rotation gate, and a control NOT gate.
  • FIG. 1 is a network configuration diagram including the portfolio creation support device 100 of the present embodiment.
  • the portfolio creation support device 100 shown in FIG. 1 is a computer device that efficiently generates a plurality of portfolio candidates based on the investment policy of each financial institution and can present them to the user in a form that is easy to recognize. As an example, assume an annealing machine.
  • the portfolio creation support device 100 of the present embodiment is connected to the user terminal 200 and the financial information distribution system 300 via an appropriate network 10 such as the Internet so as to be capable of data communication.
  • the user terminal 200 is a terminal that receives information on a portfolio of financial products from the portfolio creation support device 100.
  • the user of this user terminal 200 can be assumed to be a person in charge of an institutional investor such as a financial institution or an insurance company, or a general individual investor.
  • the information on the portfolio of financial products provided by the portfolio creation support device 100 is weighted between each item of expected rate of return, price drop risk, and market sensitivity (interest rate delta, exchange delta, etc.) (user emphasizes).
  • the rising model expected rate of return, price decline risk, and market sensitivity of financial products
  • Information on the optimal portfolio that is, financial products identified by solving a formula that includes items as variables.
  • the portfolio creation support device 100 facilitates a comparative study between the optimal portfolios for the information of the optimal portfolio for each pattern of weighting (viewpoint that the user emphasizes) between the items as described above. It outputs.
  • the portfolio creation support device 100 is defined by the two axes of the expected rate of return and the expected rate of return based on the values of each item of the expected rate of return, the price drop risk, and the market sensitivity in each optimal portfolio (hereinafter, simply referred to as a portfolio). At least one of the planes defined by the two axes of the expected rate of return and the market-sensitive interest rate delta, and the plane defined by the two axes of the expected rate of return and the market-sensitive exchange delta. The position of each portfolio is plotted, and the plotted plane is output to an appropriate device such as a user terminal 200. In this case, the corresponding effective frontier curve shall be drawn on the plane on which the plot was made (existing technology may be applied to generate the effective frontier curve, etc.).
  • the user's current portfolio (naturally, the user has previously applied the portfolio creation support device 100 to the financial product and its holding ratio, Predetermined highlighting for portfolios that have lower risk of price decline, higher profitability, and above the effective frontier curve (providing values for each item of expected rate of return, risk of price decline, and market sensitivity). May be done.
  • the highlighting process described above is not particularly limited, but for example, the color, shape, size, pattern, blinking or blinking pattern, etc. of the plot (point) of the corresponding portfolio are different from those of other portfolios. Can be assumed.
  • the portfolio creation support device 100 identifies a specific portfolio in the area above the effective frontier curve among the portfolios plotted on the plane defined by the above-mentioned two axes of price drop risk and expected rate of return, and in the portfolio.
  • the value of the expected rate of return shall be divided by the value of the risk of price decline to calculate the value of profitability relative to risk.
  • the portfolio creation support device 100 arranges an object of attributes according to the magnitude of the profitability value against risk with respect to the above-mentioned specific portfolio on the plane defined by the two axes of the interest rate delta and the exchange rate delta. And output.
  • This object can be assumed to be a display object having a predetermined shape such as a circle or a rectangle.
  • the attributes are assumed to be size, color, shape, pattern, blinking or blinking pattern, etc. according to the magnitude of the value of profitability in comparison with risk.
  • the portfolio is expressed based on all the viewpoints of expected rate of return, risk of price decline, and market sensitivity (interest rate delta, exchange rate delta), that is, four-dimensional events, and the differentiation between portfolios is clarified. It will be possible to present it to the user while trying to achieve the above.
  • the portfolio creation support device 100 applies a trading cost that retains information in advance with respect to a financial product that is the difference between at least one of the above-mentioned portfolios and the user's current portfolio, and the portfolio from the current portfolio to the optimum portfolio.
  • the cost required for the change is specified and the information on the cost is output. According to this, it is possible to present the information on the cost associated with the portfolio change, and the user can present not only the information on each item mentioned above but also the cost. It will be easier to carry out portfolio creation work from a comprehensive perspective including.
  • the above-mentioned weighting pattern is a pattern in which each item is treated and evaluated equally (the weighting value is the same for each item), an emphasis is placed on profits and risk of price decline, and interest rate deltas and exchange deltas are neglected (a pattern in which interest rate deltas and exchange deltas are neglected Revenue and price drop risk item weighted values> Interest rate delta and currency delta weighted values), Revenue bias pattern (Revenue item weighted value> Price drop risk, interest rate delta and currency delta weighted items The bid price) can be assumed. However, such a pattern is an example and is not limited.
  • the financial information distribution system 300 is a system that distributes information on various financial products to the portfolio creation support device 100.
  • This financial information distribution system 300 can assume a server device operated by an organization that holds information on financial products, such as various financial institutions, securities companies, and government agencies.
  • the hardware configuration of the portfolio creation support device 100 of this embodiment is as shown in FIG. That is, the portfolio creation support device 100 includes a storage unit 101, a memory 103, a calculation unit 104, and a communication unit 105.
  • the storage unit 101 is composed of an appropriate non-volatile storage element such as an SSD (Solid State Drive) or a hard disk drive.
  • the memory 103 is composed of a volatile memory element such as a RAM.
  • calculation unit 104 is a CPU that executes the program 102 held in the storage unit 101 by reading it into the memory 103, etc., performs overall control of the device itself, and performs various determinations, calculations, and control processes.
  • the communication unit 105 is composed of a network interface card that connects to the network 10 and is responsible for communication processing with other devices such as the user terminal 200 and the financial information distribution system 300.
  • the portfolio creation support device 100 When the portfolio creation support device 100 is a stand-alone machine, it further includes an input unit (consisting of a keyboard, a mouse, etc.) for receiving key input and voice input from the user, and an output unit such as a display for displaying processing data. If so, it is suitable.
  • an input unit consisting of a keyboard, a mouse, etc.
  • an output unit such as a display for displaying processing data. If so, it is suitable.
  • At least the financial product information 125 and the weighting information 126 are stored in addition to the program 102 for implementing the function required as the portfolio creation support device of the present embodiment. However, the details of this information will be described later.
  • the program 102 that is, the algorithm that implements the operation as an annealing machine, holds the information of the Ising model 1021 which is a problem to be solved.
  • the Ising model 1021 is set in advance by the manager or the like based on the portfolio to be provided with information, various information on the financial products constituting the portfolio, the portfolio management policy of the target financial institution, and the like.
  • the adiabatic quantum computation described in the outline of the annealing machine is also called quantum annealing, which is a development of the classical annealing concept into quantum mechanics. That is, the adiabatic quantum computation is originally capable of classical operation, and can be interpreted as having a quantum mechanical effect added to improve the performance in terms of high speed and correct answer rate of the solution. Therefore, in the present invention, the arithmetic unit itself is considered to be classical, and by introducing parameters that are determined quantum mechanically into the arithmetic process, an arithmetic method / apparatus that is classical but includes quantum mechanical effects is realized.
  • the following example describes the classical algorithm for obtaining the ground state as a solution and the device for realizing it while explaining the relationship with adiabatic quantum computation.
  • Sj Z (tk-1) ⁇ ⁇ tk / ⁇ is obtained, and the function f is defined so that the range of the variable Sj z (tk) described above is -1 ⁇ sj z (tk) ⁇ 1, and Sj z (tk).
  • the coefficient gpimb is, for example, a value of 50% to 200% of the average value of
  • the correction term ⁇ gj'can be added to gj'only for a certain site j', and the magnitude of gj'can be increased only for the site j'.
  • the correction term ⁇ gj' is, for example, a value of 10% to 100% of the average value of
  • the Ising spin Hamiltonian ground state search problem given by equation (3) is known to be a useful problem, including a classification problem called NP-hardness (Reference: F. Barahona, "On the computational comp” lex ity of Ising spin glass models, "J. Phys. A: Math. Gen. 15, 3241 (1982).).
  • Equation 3 Jij and gj are task setting parameters, and ⁇ ⁇ Z is the z component of Pauli's spin matrix and takes an eigenvalue of ⁇ 1.
  • i and j represent spin sites.
  • the Ising spin is a variable that can take only ⁇ 1 as a value, and in Eq. (3), the Ising spin system is obtained because the eigenvalue of ⁇ ⁇ z is ⁇ 1.
  • the Ising spin of equation (3) does not have to be a literal spin, and physically anything is acceptable as long as the Hamiltonian is described by equation (3).
  • Equation 4 ⁇ is a proportionality constant determined by the size of the external field uniformly applied to all sites j, and ⁇ ⁇ j x is the x component of Pauli's spin matrix. If the arithmetic system is spin itself, the external field means a magnetic field.
  • Equation (4) corresponds to the application of a transverse magnetic field, and the ground state is when all spins are oriented in the x direction ( ⁇ > 0).
  • the Hamiltonian in the problem setting was defined as an Ising spin system with only the z component, but the x component of the spin appears in equation (4). Therefore, the spin in the calculation process is not Ising but vector (Broch vector).
  • the Hamiltonian of the equation (4) was started, but the Hamiltonian is gradually changed as the time t progresses, and finally the Hamiltonian described by the equation (3) is obtained and its ground state is obtained as a solution.
  • Equation 5 ⁇ ⁇ displays the three components of Pauli's spin matrix as a vector.
  • Equation 6 Since the spin direction can be defined by ⁇ ⁇ z > / ⁇ ⁇ X >, if the spin direction follows the effective magnetic field, the spin direction is determined by Eq. (7).
  • Equation (7) is a quantum mechanical description, but since it has an expected value, it is a relational equation related to classical quantities, unlike equations (1) to (6).
  • equation (7) determines the behavior of the classical spin system.
  • equation (7) is deformed due to nonlocal correlation, which will be described later.
  • the classical system determined by equation (7) will be described. Describe.
  • the time t is continuous, but in the actual calculation process, it can be discrete to improve convenience. The discrete case will be described below.
  • the spin illustrated here is a vector spin because not only the z component but also the x component is added.
  • the behavior as a vector can be understood from FIG.
  • a three-dimensional vector of size 1 (this is called a Bloch vector, and the state can be described by a point on the sphere) is assumed, but the axis in the example shown in the figure is two-dimensional. Only need to be considered (the state can be described by a point on the circle).
  • the two-dimensional spin vector can be described only by a semicircle, and if Sj z is specified in [-1,1], the two-dimensional spin vector is determined by one variable of Sj z . Therefore, in the example here, the spin is a two-dimensional vector, but it can also be expressed as a one-dimensional continuous variable having a range of [-1,1].
  • Equation 8 is a rewrite of Equation (7) into a notation related to classical quantities, so it is not marked with ⁇ >.
  • FIG. 4 shows a flowchart of the above algorithms.
  • tm ⁇ .
  • the specific issue here that is, the Ising model 1021, is the combination of the risk of price decline-expected rate of return-interest rate delta + foreign exchange delta, in the predetermined holding ratio of financial instruments, that is, the problem of estimating the optimum portfolio. Is assumed. At this time, the coefficient multiplied by the variables of the equation (risk of price decline, expected rate of return, interest rate delta, and exchange rate delta), that is, the weighted value, can be assumed to have various variations depending on the portfolio management policy desired by the user.
  • ⁇ ⁇ jz is considered to be a variable for influencing the price increase / decrease of a predetermined financial product on the price increase / decrease of other financial products.
  • the correlation strength of price increase / decrease between financial instruments, that is, the sensitivity, is expressed through the intervariable interaction Jij.
  • the intervariable interaction Jij is specifically set, and the ground state search of the Ising model 1021 represented by the equation (3), that is, the above-mentioned price drop risk-expected rate of return-interest rate delta + exchange rate delta
  • the ground state search of the Ising model 1021 represented by the equation (3) that is, the above-mentioned price drop risk-expected rate of return-interest rate delta + exchange rate delta
  • the balance point where the holding ratio of each financial instrument converges is identified.
  • the holding ratio of financial instruments in this ground state is the optimal portfolio (predetermined holding ratio of financial products that composes) predicted for the weighting pattern.
  • FIG. 5 shows an example of the financial instrument information 125 in this embodiment.
  • the financial product information 125 of this embodiment is a table in which information on various financial products is accumulated. This information includes expected volatility, price decline risk, interest rate delta, exchange rate delta, and other market sensitivities of various financial products (eg stocks, future products, foreign exchange, etc.) distributed by the financial information distribution system 300. Commodity prices (eg stock index, commodity futures price, forex quotes, forex forward quotes, long / short open position ratios, volatility of various indicators, risk reversal, etc.) and various fees (eg trading fees, management fees) ) Is included.
  • Commodity prices eg stock index, commodity futures price, forex quotes, forex forward quotes, long / short open position ratios, volatility of various indicators, risk reversal, etc.
  • various fees eg trading fees, management fees
  • the data structure is, for example, a collection of records consisting of data such as the expected rate of return, price drop risk, interest rate delta, exchange rate delta, product price, and fee, using the name of the financial product as a key.
  • FIG. 6 shows an example of the weighting information 126 in the present embodiment.
  • the weighting information 126 of this embodiment is assumed by a user of a financial institution or the like (a person who is assuming improvement of the current portfolio) for each item of expected rate of return, price drop risk, interest rate delta, and exchange rate delta. It is a table that stores information that defines the magnitude of importance as a weighted value. In other words, it is information that defines the weighting of each of the above items corresponding to the characteristics of the portfolio that financial institutions are considering (eg, emphasis on balance, emphasis on expected rate of return and risk of price decline, emphasis on expected rate of return). ..
  • the data structure is a collection of records consisting of data such as weighted values of each item corresponding to the portfolio characteristics, for example, using the identification information of the portfolio characteristics as a key.
  • FIG. 7 is a diagram showing a flow example of the portfolio creation support method in the present embodiment.
  • the portfolio creation support device 100 calculates the ground state of a portfolio composed of, for example, three financial products (FIGS. 8 and 9) as an annealing machine with the above-mentioned Ising model 1021 as an issue. ..
  • the three financial products exemplified here are the brands "A" to "C" shown in FIGS. 8 and 9.
  • the portfolio creation support device 100 normalizes the values of each variable (item) in the formula of "risk of price drop-expected rate of return-interest rate delta + exchange rate delta" already described (s10).
  • the values normalized here are the values exemplified for each of the expected rate of return, the risk of price decline, the interest rate delta, and the exchange rate delta in FIG.
  • each variable is converted so that each value is in the range of 1 to 10 based on the maximum value and the minimum value of each variable between financial instruments.
  • the maximum value of the expected rate of return is “20” of the brand “C”
  • the minimum value is “5” of the brand “B”.
  • the portfolio creation support device 100 normalizes each variable of the above-mentioned brands "A" to "C” based on the slope and the intercept value obtained for each variable as shown in FIG. 10, and the result of FIG. 111. Will be obtained. As shown in FIG. 11, the values of each variable are all in the range of 1 to 10.
  • the portfolio creation support device 100 automatically generates a combination of coefficients of each variable within a range in which the total of the coefficients for each of the above variables, that is, the weighting values is 1. (s11).
  • the coefficient is "C”
  • the above formula is expressed as "Crisk”, “risk of price decline-Cear”, “expected rate of return-Cir”, interest rate delta-Cfx, and exchange rate delta.
  • the number of variables is "5" and a combination of coefficients is assumed in 10% increments, the number of combinations will be "1001" or the like.
  • the portfolio creation support device 100 calculates the ground state of the portfolio composed of the three financial products as described above, with the ging model 1021 as the number of combinations of coefficients generated in s11 as an issue. Estimate the optimal portfolio (s12).
  • the search for the ground state itself is similar to the processing in the existing technology.
  • the processing result of s12 described above that is, the objective function value (formula: value of price drop risk-expected rate of return-interest rate delta + exchange rate delta, for each portfolio), expected rate of return, for each weight pattern. Shows the risk of price decline, interest rate delta, and exchange rate delta.
  • the weighting pattern is considered only for each variable of the expected rate of return, the risk of price decline, and the interest rate delta.
  • the portfolio creation support device 100 is defined by two axes, the price drop risk and the expected rate of return, based on the processing results shown in FIG. 12, that is, the expected rate of return, the price drop risk, and the market sensitivity in each portfolio.
  • Plan (see FIG. 13), a plane defined by the two axes of the expected rate of return and the expected rate of return (see FIG. 14), and a plane defined by the two axes of the expected rate of return and the exchange delta (not shown).
  • the position of each portfolio is plotted on at least one of the planes of the above, and the effective frontier curve Fc corresponding to the plane is drawn on the plane on which the plot is performed and output to the user terminal 200 (s13).
  • the portfolio creation support device 100 has a lower risk of price drop than the user's current portfolio Np among the portfolios plotted on the plane (see FIG. 13) defined by the two axes of price drop risk and expected rate of return, and the expected rate of return. It is assumed that a predetermined highlighting process (in the example of FIG. 13, a group of portfolio Xp is surrounded by a red circle) is executed for the portfolio Xp having a high rate of return and in the region above the effective frontier curve Fc.
  • the portfolio creation support device 100 has the expected rate of return, the risk of price decline, the interest rate delta, as well as risk assets, the number of stocks purchased, the number of stocks sold, and the required cost for the above-mentioned portfolio Xp.
  • the value is output to the user terminal 200 (s14).
  • the portfolio creation support device 100 identifies a financial product that is the difference between each of the above-mentioned portfolio Xp and the user's current portfolio, and purchases the number of financial products that need to be purchased when changing to the portfolio Xp.
  • the number of issues and the number of financial products that need to be sold are calculated as the number of issues to be sold.
  • the portfolio creation support device 100 calculates the purchase cost by multiplying, for example, the number of purchased brands by the unit price of the purchase cost (various fees paid to a securities company or the like and the product price).
  • the portfolio creation support device 100 calculates the selling cost by multiplying the number of stocks to be sold by the unit price of the selling cost (various commissions and losses paid to securities companies and the like).
  • the portfolio creation support device 100 adds up the above-mentioned purchase cost and sale cost to calculate the required cost.
  • the user browses FIGS. 13 to 15 described above on the user terminal 200, and for example, from each portfolio included in the portfolio Xp, in addition to indicators such as expected rate of return, price drop risk, interest rate delta, etc., portfolio change You can select the desired portfolio after recognizing the costs involved and use it as a candidate for portfolio reorganization.
  • the portfolio creation support device 100 of the present embodiment arranges an object of attributes according to the magnitude of the profitability value of the risk contrast with respect to the portfolio Xp on the plane defined by the two axes of the interest rate delta and the exchange rate delta. Then, it is preferable to output to the user terminal 200 (FIG. 16).
  • the portfolio creation support device 100 is a specific portfolio located in the area above the effective frontier curve Fc among the portfolios plotted on the plane defined by the two axes of the price drop risk and the expected rate of return shown in FIG. Is specified, and the value of the expected rate of return in the portfolio is divided by the value of the risk of price decline to calculate the value of profitability in comparison with risk.
  • the expected rate of return value "0.00025" in a certain portfolio is divided by the price drop risk value "0.00001" to calculate the risk-contrast profitability value "25".
  • the portfolio creation support device 100 arranges an object of attributes according to the magnitude of the profitability value against risk with respect to a specific portfolio, that is, portfolio Xp, on a plane defined by two axes of interest rate delta and exchange rate delta. And output to the user terminal 200.
  • This object can be assumed to be a display object having a predetermined shape such as a circle or a rectangle.
  • the attributes are assumed to be size, color, shape, pattern, blinking or blinking pattern, etc. according to the magnitude of the value of profitability in comparison with risk.
  • the portfolio is expressed based on all the viewpoints of expected rate of return, risk of price decline, and market sensitivity (interest rate delta, exchange rate delta), that is, four-dimensional events, and the differentiation between portfolios is clarified. It will be possible to present it to the user while trying to achieve the above.
  • the calculation unit is defined by two axes of the expected rate of return, the expected rate of return, and the expected rate of return based on each value of the expected rate of return, the price decrease risk, and the market sensitivity in each of the portfolios.
  • the position of each portfolio is plotted in, and a process of drawing an effective frontier curve corresponding to the plane on at least one of the planes on which the plot is made and outputting it to a predetermined device is further executed. May be.
  • each portfolio will be clearly presented from multiple perspectives, and the portfolio formulation work of the person in charge of the financial institution will be effectively supported.
  • the calculation unit has a risk of price drop compared to the current portfolio of a predetermined user among the portfolio plotted on the plane defined by the two axes of the price drop risk and the expected rate of return. It is also possible that a predetermined highlighting process is performed on a portfolio that has a low rate of return and a high rate of return and is in a region above the effective frontier curve.
  • the calculation unit is in a region above the effective frontier curve of the portfolio plotted on the plane defined by the two axes of the price drop risk and the expected rate of return. It is defined by the process of identifying a specific portfolio and dividing the value of the expected rate of return in the portfolio by the value of the risk of price decline to calculate the value of profitability against risk, and the two axes of the interest rate delta and the exchange delta.
  • an object having an attribute corresponding to the magnitude of the value of the rate of return in comparison with the risk may be further arranged and output to a predetermined device.
  • the calculation unit performs the calculation, and the value of each item of the expected rate of return, the risk of price decrease, and the market sensitivity indicated by the information regarding the financial products constituting the portfolio. May be normalized so as to fall within a predetermined specified range, and the process of setting the corresponding item in the predetermined formula may be further executed.
  • the calculation unit applies a trading cost for holding information in advance regarding a financial product which is a difference between at least one of the portfolios and the current portfolio of a predetermined user.
  • the cost required for changing the portfolio from the current portfolio may be specified, and the process of outputting the cost information to the predetermined device may be further executed.
  • portfolio creation support device of the present embodiment may be a CMOS annealing machine that solves a combinatorial optimization problem with respect to the Ising model.
  • the operation of the Zing model is simulated by a circuit using elements such as CMOS (Complementary Metal Oxide Semiconductor) of semiconductors, and a practical solution of a combinatorial optimization problem such as creation of a portfolio candidate of a financial product is realized. It can be obtained efficiently at room temperature. As a result, multiple portfolio candidates based on the investment policy of each financial institution can be generated more efficiently and presented to the user in a form that is easy to recognize.
  • CMOS Complementary Metal Oxide Semiconductor
  • the price of the information processing device is lower than the current portfolio of a predetermined user among the portfolios plotted on the plane defined by the two axes of the price drop risk and the expected rate of return.
  • a predetermined highlighting process may be performed on a portfolio having a low risk, a high expected rate of return, and a region above the effective frontier curve.
  • the area above the effective frontier curve of the portfolio plotted on the plane defined by the two axes of the price drop risk and the expected rate of return by the information processing apparatus is also possible to further perform a process of arranging an object of an attribute corresponding to the magnitude of the value of the rate of return of the risk contrast with respect to the specific portfolio on the plane to be output to a predetermined device.
  • each item of the expected rate of return, the risk of price decline, and the market sensitivity indicated by the information regarding the financial products constituting the portfolio The value may be normalized so as to fall within a predetermined specified range, and the process of setting the corresponding item in the predetermined formula may be further executed.
  • the information processing apparatus applies a trading cost for holding information in advance regarding a financial product which is a difference between at least one of the portfolios and the current portfolio of a predetermined user.
  • the cost required to change the portfolio from the current portfolio may be specified, and the process of outputting the information of the cost to the predetermined device may be further executed.
  • the information processing device may be a CMOS annealing machine that solves a combinatorial optimization problem with respect to the Ising model.
  • Network 100 Portfolio creation support device (annealing machine) 101 Storage unit 102 Program 1021 Ising model 103 Memory 104 Calculation unit 105 Communication unit 125 Financial product information 126 Weighting information 200 User terminal 300 Financial information distribution system

Landscapes

  • Engineering & Computer Science (AREA)
  • Business, Economics & Management (AREA)
  • Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Entrepreneurship & Innovation (AREA)
  • Human Resources & Organizations (AREA)
  • Strategic Management (AREA)
  • General Physics & Mathematics (AREA)
  • Finance (AREA)
  • Development Economics (AREA)
  • Accounting & Taxation (AREA)
  • General Business, Economics & Management (AREA)
  • Marketing (AREA)
  • Operations Research (AREA)
  • Economics (AREA)
  • Technology Law (AREA)
  • Game Theory and Decision Science (AREA)
  • General Engineering & Computer Science (AREA)
  • Tourism & Hospitality (AREA)
  • Geometry (AREA)
  • Evolutionary Computation (AREA)
  • Data Mining & Analysis (AREA)
  • Computer Hardware Design (AREA)
  • Quality & Reliability (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)
  • Financial Or Insurance-Related Operations Such As Payment And Settlement (AREA)
PCT/JP2020/017820 2019-05-20 2020-04-24 ポートフォリオ作成支援装置およびポートフォリオ作成支援方法 Ceased WO2020235300A1 (ja)

Priority Applications (3)

Application Number Priority Date Filing Date Title
EP20809451.6A EP3975101A4 (en) 2019-05-20 2020-04-24 DEVICE AND METHOD TO ASSIST IN THE CREATION OF PORTFOLIOS
US17/611,946 US20220230252A1 (en) 2019-05-20 2020-04-24 Portfolio creation assistance device and portfolio creation assistance method
SG11202112705SA SG11202112705SA (en) 2019-05-20 2020-04-24 Portfolio creation assistance device and portfolio creation assistance method

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
JP2019094586A JP7141365B2 (ja) 2019-05-20 2019-05-20 ポートフォリオ作成支援装置およびポートフォリオ作成支援方法
JP2019-094586 2019-05-20

Publications (1)

Publication Number Publication Date
WO2020235300A1 true WO2020235300A1 (ja) 2020-11-26

Family

ID=73454691

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/JP2020/017820 Ceased WO2020235300A1 (ja) 2019-05-20 2020-04-24 ポートフォリオ作成支援装置およびポートフォリオ作成支援方法

Country Status (5)

Country Link
US (1) US20220230252A1 (https=)
EP (1) EP3975101A4 (https=)
JP (1) JP7141365B2 (https=)
SG (1) SG11202112705SA (https=)
WO (1) WO2020235300A1 (https=)

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2004220196A (ja) * 2003-01-10 2004-08-05 Quants Research Kk ポートフォリオ算出プログラム、ポートフォリオ算出方法およびポートフォリオ算出装置
JP2006221679A (ja) 2005-02-08 2006-08-24 Victor Co Of Japan Ltd デジタルオーディオインターフェースの付加情報伝送方法並びに情報送信装置及び情報受信装置
JP2009294765A (ja) * 2008-06-03 2009-12-17 Quants Research Kk ポートフォリオ構築支援装置、ポートフォリオ構築支援プログラムおよびポートフォリオ構築支援方法
JP2016051350A (ja) * 2014-08-29 2016-04-11 株式会社日立製作所 情報処理システム及び管理装置
WO2016157333A1 (ja) 2015-03-27 2016-10-06 株式会社日立製作所 計算機、及び演算プログラム

Family Cites Families (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US6078904A (en) * 1998-03-16 2000-06-20 Saddle Peak Systems Risk direct asset allocation and risk resolved CAPM for optimally allocating investment assets in an investment portfolio
AU2002356073A1 (en) * 2001-08-16 2003-03-03 James Eric Damschroder Method and apparatus for creating a visual representation of a portfolio and determining an efficient allocation
JP2006134269A (ja) * 2004-11-09 2006-05-25 Kigen In ポートフォリオ構築プログラム
US7991230B2 (en) * 2005-10-14 2011-08-02 Microsoft Corporation Modeling micro-structure for feature extraction
US20170323385A1 (en) * 2016-05-09 2017-11-09 Axioma, Inc. Methods and apparatus employing hierarchical conditional variance to minimize downside risk of a multi-asset class portfolio and improved graphical user interface

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2004220196A (ja) * 2003-01-10 2004-08-05 Quants Research Kk ポートフォリオ算出プログラム、ポートフォリオ算出方法およびポートフォリオ算出装置
JP2006221679A (ja) 2005-02-08 2006-08-24 Victor Co Of Japan Ltd デジタルオーディオインターフェースの付加情報伝送方法並びに情報送信装置及び情報受信装置
JP2009294765A (ja) * 2008-06-03 2009-12-17 Quants Research Kk ポートフォリオ構築支援装置、ポートフォリオ構築支援プログラムおよびポートフォリオ構築支援方法
JP2016051350A (ja) * 2014-08-29 2016-04-11 株式会社日立製作所 情報処理システム及び管理装置
WO2016157333A1 (ja) 2015-03-27 2016-10-06 株式会社日立製作所 計算機、及び演算プログラム

Non-Patent Citations (5)

* Cited by examiner, † Cited by third party
Title
E. FARHI ET AL.: "A quantum adiabatic evolution algorithm applied to random instances of an NP-complete problem", SCIENCE, vol. 292, 2001, pages 472
F. BARAHONA: "On the computational complexity of Isingspin glass models", J. PHYS. A: MATH. GEN., vol. 15, 1982, pages 3241, XP020035128, DOI: 10.1088/0305-4470/15/10/028
See also references of EP3975101A4
WATANABE, GEN: "During a demonstration experiment with Quantum annealing machine such as portfolio optimization and stock price prediction", NEW MEDIA,, vol. 37, no. 5, 1 May 2019 (2019-05-01), JP, pages 46 - 48, XP009531586 *
YAMAOKA, MASANAO: "Overview of CMOS Annealing Machine", PROCEEDINGS OF THE 2019 IEICE GENERAL CONFERENCE: ELECTRONICS 2, no. 2, 5 March 2019 (2019-03-05), JP, pages SS-38 - SS-39, XP009531588, ISSN: 1349-1369 *

Also Published As

Publication number Publication date
JP2020190829A (ja) 2020-11-26
EP3975101A1 (en) 2022-03-30
SG11202112705SA (en) 2021-12-30
US20220230252A1 (en) 2022-07-21
EP3975101A4 (en) 2023-03-01
JP7141365B2 (ja) 2022-09-22

Similar Documents

Publication Publication Date Title
Egger et al. Quantum computing for finance: State-of-the-art and future prospects
Shaban et al. SMP-DL: a novel stock market prediction approach based on deep learning for effective trend forecasting
Chan Algorithmic trading: winning strategies and their rationale
Zhou Quantum finance: Exploring the implications of quantum computing on financial models
Li et al. Forecasting stock prices changes using long-short term memory neural network with symbolic genetic programming
Özorhan et al. A strength-biased prediction model for forecasting exchange rates using support vector machines and genetic algorithms
Hejazi et al. Efficient valuation of SCR via a neural network approach
JP7109337B2 (ja) 情報提供装置および情報提供方法
Gupta et al. H3O-LGBM: hybrid Harris hawk optimization based light gradient boosting machine model for real-time trading
Snihovyi et al. Implementation of robo-advisor services for different risk attitude investment decisions using machine learning techniques
Ivanov et al. Implementation of Robo-Advisors Tools for Different Risk Attitude Investment Decisions.
Fattoh et al. Unveiling market dynamics: a machine and deep learning approach to Egyptian stock prediction
Korczak et al. Fundamental analysis in the multi-agent trading system
Suresh et al. Historical analysis and forecasting of stock market using Fbprophet
Chen et al. Benchmarking of quantum and classical computing in large-scale dynamic portfolio optimization under market frictions
JP7141365B2 (ja) ポートフォリオ作成支援装置およびポートフォリオ作成支援方法
Türkoğlu et al. Machine learning in portfolio optimization
JP7376390B2 (ja) ポートフォリオ作成支援装置、ポートフォリオ作成支援方法、及びポートフォリオ作成支援システム
Klimenko et al. Comparative analysis on neural networks and ARIMA for forecasting heterogeneous portfolio returns
Pik et al. Hands-On AI Trading with Python, QuantConnect, and AWS
Mohan et al. Sentiment-Driven Predictive Models for Nifty 50 Stock Market Fluctuations: A Time Series Analysis Perspective
Marszałek et al. Ordered fuzzy candlesticks
Guo et al. Exploring the Synergy of Quantitative Factors and Newsflow Representations from Large Language Models for Stock Return Prediction
Sorensen et al. Practical Meta-Reinforcement Learning of Evolutionary Strategy with Quantum Neural Networks for Stock Trading
Nayak et al. Predicting Forex Trends: A Comprehensive Analysis of Supervised learning in Exchange Rate Prediction

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 20809451

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

ENP Entry into the national phase

Ref document number: 2020809451

Country of ref document: EP

Effective date: 20211220