Asset allocation optimization method and device, equipment, storage medium and computer program product

Abstract

The invention discloses an asset allocation optimization method and device, equipment, a storage medium and a computer program product, and relates to the technical field of asset allocation, and the method comprises the steps: determining target asset allocation corresponding to total assets according to the expected income of a user for the total assets; constructing a target function based on the target asset configuration and the current asset configuration of the user; the target function is decomposed into a first function and a second function, the first function is used for reducing the income fluctuation rate of the current asset configuration, and the second function is used for constraining the current asset configuration; and optimizing the current asset configuration according to the first function and the second function to obtain optimized asset configuration. Compared with the prior art in which the asset configuration is distributed in a fixed proportion distribution mode, the asset configuration optimization method provided by the invention can reduce the purchase and redemption frequency of the user to the assets on the premise of ensuring that the expected income of the user is reached, thereby reducing the income fluctuation rate of the total assets of the user under the condition of optimizing the asset configuration.

Description

Technical Field

[0001] This application relates to the field of asset allocation technology, and in particular to an asset allocation optimization method, apparatus, device, storage medium, and computer program product. Background Technology

[0002] Asset allocation refers to the allocation of a user's funds among different asset classes (such as stocks, fixed income, cash, etc.) according to the user's investment needs in order to balance risk and return. Its essence is to reduce the risk of a single asset through diversified investment while pursuing reasonable return targets.

[0003] Most mainstream asset allocation schemes currently use a fixed allocation method (such as 60% equity + 40% fixed income) to allocate assets. Although this allocation method is easy to implement in the early stages, it requires frequent buy and redemption operations in order to meet users' return requirements in the later stages, resulting in high volatility of asset allocation returns. Summary of the Invention

[0004] The main purpose of this application is to provide an asset allocation optimization method, apparatus, equipment, storage medium, and computer program product, which aims to solve the technical problem of high return volatility in existing asset allocation schemes.

[0005] To achieve the above objectives, this application provides an asset allocation optimization method, which includes the following steps:

[0006] The target asset allocation corresponding to the total assets is determined based on the user's expected return on the total assets.

[0007] Construct a target function based on the target asset configuration and the user's current asset configuration;

[0008] The objective function is decomposed into a first function and a second function. The first function is used to reduce the volatility of the returns of the current asset allocation, and the second function is used to constrain the current asset allocation.

[0009] The current asset allocation is optimized based on the first function and the second function to obtain an optimized asset allocation.

[0010] In one embodiment, the step of determining the target asset allocation corresponding to the total assets based on the user's expected return on the total assets includes:

[0011] Construct efficient frontier curves for holdable assets in the asset market in real time, and determine standardized allocation templates for the holdable assets based on the efficient frontier curves. The standardized allocation templates contain several mapping relationships between asset returns and asset allocation.

[0012] By using the user's expected return on total assets as keywords, a query can be performed in the standardized configuration template to obtain the target asset configuration corresponding to the total assets.

[0013] In one embodiment, the step of constructing the objective function based on the target asset configuration and the user's current asset configuration includes:

[0014] An asset return volatility optimization function is constructed based on the target asset allocation and the user's current asset allocation, and the constraint space corresponding to the current asset allocation is determined based on the target asset allocation and preset constraint rules.

[0015] The objective function is constructed based on the asset return volatility optimization function and the constraint space.

[0016] In one embodiment, the step of decomposing the objective function into a first function and a second function includes:

[0017] The variable used to represent asset allocation in the objective function is defined as the objective variable, and the projection of the objective variable in the constraint space is defined as the auxiliary variable.

[0018] The objective function is decomposed into a first function and a second function based on the target variable and the auxiliary variable.

[0019] In one embodiment, the step of optimizing the current asset allocation based on the first function and the second function to obtain an optimized asset allocation includes:

[0020] The target variable is iteratively updated using the first function, and the auxiliary variable is iteratively updated using the second function;

[0021] The current asset allocation is optimized based on the updated target variable and the updated auxiliary variable to obtain an optimized asset allocation.

[0022] In one embodiment, the step of optimizing the current asset allocation based on the updated target variable and the updated auxiliary variable to obtain an optimized asset allocation includes:

[0023] The updated target variable and the updated auxiliary variable are reconciled using the Lagrange function to obtain the reconciled target variable and the reconciled auxiliary variable.

[0024] If the difference between the coordinated target variable and the coordinated auxiliary variable satisfies the convergence condition, the current asset allocation is optimized based on the coordinated target variable or the coordinated auxiliary variable to obtain an optimized asset allocation.

[0025] Furthermore, to achieve the above objectives, this application also proposes an asset allocation optimization device, which includes:

[0026] The configuration determination module is used to determine the target asset configuration corresponding to the total assets based on the user's expected return on the total assets.

[0027] The function construction module is used to construct a target function based on the target asset configuration and the user's current asset configuration;

[0028] The function decomposition module is used to decompose the objective function into a first function and a second function. The first function is used to reduce the volatility of the returns of the current asset allocation, and the second function is used to constrain the current asset allocation.

[0029] The configuration optimization module is used to optimize the current asset configuration according to the first function and the second function to obtain an optimized asset configuration.

[0030] In addition, to achieve the above objectives, this application also proposes an asset allocation optimization device, the device comprising: a memory, a processor, and an asset allocation optimization program stored in the memory and executable on the processor, the asset allocation optimization program being configured to implement the steps of the asset allocation optimization method as described above.

[0031] In addition, to achieve the above objectives, this application also proposes a storage medium, which is a computer-readable storage medium, storing an asset allocation optimization program, which, when executed by a processor, implements the steps of the asset allocation optimization method described above.

[0032] In addition, to achieve the above objectives, the present invention also provides a computer program product, the computer program product including an asset allocation optimization program, which, when executed by a processor, implements the steps of the asset allocation optimization method as described above.

[0033] This application determines the target asset allocation corresponding to the user's expected return on total assets; constructs an objective function based on the target asset allocation and the user's current asset allocation; decomposes the objective function into a first function and a second function, whereby the first function is used to reduce the volatility of the current asset allocation's returns, and the second function is used to constrain the current asset allocation; and optimizes the current asset allocation based on the first and second functions to obtain an optimized asset allocation. Compared to existing technologies that allocate asset allocation using a fixed ratio, the method of this application constructs an objective function based on the user's target asset allocation corresponding to total assets and the current asset allocation, then decomposes the objective function into a first function for reducing the volatility of the current asset allocation's returns and a second function for constraining the current asset allocation, and finally optimizes the current asset allocation based on the first and second functions. This reduces the user's buying and redeeming frequency of assets while ensuring that the user's expected return is achieved, thereby reducing the volatility of the user's total assets' returns under the optimized asset allocation. Attached Figure Description

[0034] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this application and, together with the description, serve to explain the principles of this application.

[0035] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, for those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0036] Figure 1 This is a flowchart illustrating the first embodiment of the asset allocation optimization method of this application;

[0037] Figure 2 This is a schematic diagram illustrating the user data acquisition license for the asset allocation optimization method in this application.

[0038] Figure 3 This is a flowchart illustrating the second embodiment of the asset allocation optimization method of this application;

[0039] Figure 4 This is a flowchart illustrating the third embodiment of the asset allocation optimization method of this application;

[0040] Figure 5 This is a structural block diagram of the first embodiment of the asset allocation optimization device of this application;

[0041] Figure 6 This is a schematic diagram of the structure of the asset configuration optimization device for the hardware operating environment involved in the embodiments of this application.

[0042] The realization of the purpose, functional features and advantages of this application will be further explained in conjunction with the embodiments and with reference to the accompanying drawings. Detailed Implementation

[0043] It should be understood that the specific embodiments described herein are only used to explain the technical solutions of this application and are not intended to limit this application.

[0044] It should be noted that the executing entity of the embodiments of this application can be a computing service device with data processing, network communication, and program execution functions, such as a tablet computer, personal computer, or mobile phone, or an electronic device capable of performing the above functions, such as the aforementioned asset allocation optimization device. The following embodiments will be described using the asset allocation optimization device as an example.

[0045] This application provides an asset allocation optimization method, referring to... Figure 1 , Figure 1 This is a flowchart illustrating the first embodiment of the asset allocation optimization method of this application.

[0046] In this embodiment, the asset allocation optimization method includes the following steps:

[0047] Step S1: Determine the target asset allocation corresponding to the total assets based on the user's expected return on the total assets.

[0048] It should be noted that the total assets mentioned above can be all assets held by the user in real time, including equity assets (such as stocks and equity funds), fixed-income assets (such as corporate bonds and bond funds), monetary assets (such as bank deposits and money market funds), and alternative assets (such as commodities). The expected return mentioned above can be the minimum rate of return that the user expects the total assets to achieve after allocation.

[0049] It should be understood that a user's expected return on total assets is equivalent to the overall return of the user's held assets and candidate purchase assets. Based on this, this embodiment can construct an efficient frontier analysis framework using the CAPM (Capital Asset Pricing Model). Then, based on this framework, the theoretical returns of each asset in the asset market (including the aforementioned user-held assets and candidate purchase assets) are pre-determined. Finally, with different expected returns as targets, assets in the asset market are combined based on these theoretical return scenarios to obtain different asset allocations. The aforementioned target asset allocation represents the asset portfolio in the asset market that theoretically can meet the user's expected returns, and this portfolio provides the proportions of the user's held assets and candidate purchase assets in the total assets.

[0050] Step S2: Construct a target function based on the target asset configuration and the user's current asset configuration.

[0051] It should be noted that the above-mentioned current asset allocation can be the user's real-time asset allocation, that is, the asset allocation corresponding to the assets held by the user at the current moment. The above objective function can be a function that finds the asset allocation that meets the user's expected return and has the lowest return volatility. The process of constructing the function can be regarded as an optimization process, which can be defined as a quadratic programming problem for calculation. One of the constraints is that the portfolio return rate equals the expected return rate, and the optimization direction is to minimize return volatility.

[0052] It should be understood that the target asset allocation is a portfolio of assets that theoretically can meet the user's expected returns. In actual asset allocation, asset returns are also affected by transaction costs and constraint rules, which are determined by the user and may differ between different users. Therefore, in this embodiment, transaction costs and constraint rules can be determined based on the user's current asset allocation. Then, an objective function is constructed using the target asset allocation as a benchmark, thereby incorporating transaction costs and constraint rules into the objective function and improving its fit with the user.

[0053] Step S3: Decompose the objective function into a first function and a second function. The first function is used to reduce the volatility of the returns of the current asset allocation, and the second function is used to constrain the current asset allocation.

[0054] It should be noted that the aforementioned volatility of returns can be the standard deviation of asset returns, which measures the degree of dispersion of asset returns around their average value: higher volatility indicates a more dispersed distribution of asset returns, more volatile prices, and higher risk, while lower volatility indicates a more concentrated distribution of asset returns, more stable prices, and lower risk.

[0055] Understandably, the optimization process of the objective function can be viewed as a quadratic programming problem. In this embodiment, the quadratic programming problem can be decomposed into two sub-problems based on the ADMM (Alternating Direction Method of Multipliers) algorithm. One sub-problem (corresponding to the first function mentioned above) focuses on optimizing the return volatility of the current asset allocation in the quadratic programming problem, while the other sub-problem (corresponding to the second function mentioned above) focuses on optimizing the constraint satisfaction in the quadratic programming problem. Specific constraint terms can be determined according to specific assets and user requirements. For example, specific constraint terms can include asset class constraints, industry style constraints, and high-quality product pool recommendation constraints, etc. This embodiment does not impose any restrictions on this.

[0056] Step S4: Optimize the current asset allocation according to the first function and the second function to obtain an optimized asset allocation.

[0057] In practical implementation, the differences between the variables of the first and second functions can be gradually reduced by coordinating them, eventually converging to a consistent solution. Optimizing the current asset allocation based on this consistent solution ensures that the user's expected returns are achieved while simultaneously reducing the frequency of asset purchases and redemptions, thereby lowering the volatility of the user's total asset returns under the optimized asset allocation. Furthermore, this embodiment can also diagnose the health of the user's asset portfolio: by penetrating the user's holdings to the distribution ratios of various asset classes, the appropriate asset allocation ratios for the user are determined based on the user's expected returns. If the current holding distribution deviates from expectations by more than the limit, the user is promptly alerted that the allocation may be deviating from expectations. By penetrating the user's holdings to the underlying asset distribution, a dynamic mapping model of "user expected returns - actual allocation ratios" is established, and multi-dimensional constraint thresholds based on asset classes and industry styles are set. This is the first time that asset penetration technology has been combined with allocation deviation warnings, enabling precise diagnosis of the user's investment plan and avoiding the reliance on only rough judgments at the product level in traditional methods.

[0058] Specifically, all user-related data involved in the embodiments of this application (such as the user's expected return on total assets, the user's current asset allocation, etc.) are obtained with the user's permission or consent; that is, when this application is applied to specific products or technologies, user permission is required to acquire and process the relevant data, and the processing of the relevant data must comply with the relevant laws, regulations, and regulatory standards of the relevant countries and regions. For example, when it is necessary to obtain the user's current asset allocation, a prompt to obtain the current asset allocation can be displayed on the user's terminal. After receiving the user's confirmation of the prompt, the terminal can obtain the user's current asset allocation. Please refer to [link / reference] for details. Figure 2 , Figure 2 This diagram illustrates the user data acquisition permission for the asset allocation optimization method in this application. The user's current asset allocation can only be acquired after the user clicks "agree" in the current asset allocation acquisition prompt interface.

[0059] This embodiment determines the target asset allocation corresponding to the total assets based on the user's expected return on total assets; constructs an objective function based on the target asset allocation and the user's current asset allocation; decomposes the objective function into a first function and a second function, whereby the first function is used to reduce the volatility of the current asset allocation's returns, and the second function is used to constrain the current asset allocation; and optimizes the current asset allocation based on the first and second functions to obtain an optimized asset allocation. Compared to existing technologies that allocate asset allocation using a fixed ratio, this embodiment constructs an objective function based on the user's total assets, the target asset allocation, and the current asset allocation. It then decomposes the objective function into a first function to reduce the volatility of the current asset allocation's returns and a second function to constrain the current asset allocation. Finally, it optimizes the current asset allocation based on the first and second functions. This reduces the user's buying and redeeming frequency of assets while ensuring the achievement of the user's expected returns, thereby reducing the volatility of the user's total assets under the optimized asset allocation.

[0060] refer to Figure 3 , Figure 3 This is a flowchart illustrating the second embodiment of the asset allocation optimization method of this application.

[0061] In one feasible implementation, step S1 may include:

[0062] Step S11: Construct an efficient frontier curve for holdable assets in the asset market in real time, and determine a standardized allocation template corresponding to the holdable assets based on the efficient frontier curve. The standardized allocation template contains a mapping relationship between asset returns and asset allocation.

[0063] Step S12: Use the user's expected return on total assets as the keyword to query the standardized configuration template and obtain the target asset configuration corresponding to the total assets.

[0064] It should be noted that the above-mentioned efficient frontier curve is a curve drawn in a "risk-return" coordinate system, representing the set of all portfolios that can achieve the highest expected return (or bear the lowest risk at the target return) under a given risk level.

[0065] In practical implementation, the efficient frontier curve can be obtained by analyzing the holdable assets in the asset market using the efficient frontier analysis framework constructed by the Capital Asset Pricing Model (CAPM). This model calculates the optimal return curves under different risk levels to form the efficient frontier curve. More specifically, the analytical objectives of the efficient frontier analysis framework can be: to find the portfolio with the highest expected return among the holdable assets in the asset market at a given risk level; and to find the portfolio with the lowest risk among the holdable assets in the asset market at a given expected return.

[0066] For example, the efficient frontier curve of holdable assets in an asset market can be expressed mathematically as follows:

[0067]

[0068] in, This means maximizing W within the selectable range of asset weights W, expected portfolio return μ, and return volatility σ. T The probability of exceeding G, W T The formula represents the total wealth value at the end of the investment period, W0 represents the total wealth value at the beginning of the investment period, G represents the target wealth level set by the user, T represents the investment period, w represents the asset weight vector, μ0 represents the expected return vector of the asset portfolio, ∑0 represents the covariance matrix of the returns (the diagonal elements of this matrix are the squares of the volatility of each asset's returns, and the off-diagonal elements are the covariance between assets), n represents the number of assets, i represents the asset index, and Φ represents the standard normal cumulative distribution function. Furthermore, the assets mentioned in the formula include equity assets, fixed-income assets, money market assets, and alternative assets; for example, asset weights include equity asset weights, fixed-income asset weights, money market asset weights, and alternative asset weights.

[0069] In practical implementation, a standardized allocation template corresponding to the assets that can be held in the asset market can be established based on the mathematical expression of the above-mentioned efficient frontier curve, providing a benchmark for subsequent diagnosis and optimization.

[0070] In one feasible implementation, step S2 may include:

[0071] Step S21: Construct an asset return volatility optimization function based on the target asset allocation and the user's current asset allocation, and determine the constraint space corresponding to the current asset allocation based on the target asset allocation and preset constraint rules.

[0072] It should be noted that the above asset return volatility optimization function represents a function that optimizes the return volatility of asset allocation. The above preset constraint rules may include asset class constraints, industry style constraints, high-quality product pool recommendation constraints, user preference constraints, etc.

[0073] Step S22: Construct an objective function based on the asset return volatility optimization function and the constraint space.

[0074] It should be understood that the above objective function can be constructed in the following form:

[0075] minimize(1 / 2)x T Px+q T x;

[0076] subject to l≤Ax≤u;

[0077] Where x represents the ratio vector corresponding to the user's held assets and candidate purchase assets (x can be obtained by obtaining the user's held assets and candidate purchase assets ratio from the user's target asset allocation and current asset allocation, and then converting them into vector form), P represents the covariance matrix, and q represents the transaction cost weight vector (q T x represents transaction costs, A represents the attribute matrix such as asset class and industry style, l represents the lower limit of constraints, u represents the upper limit of constraints, T represents the matrix transpose operation, minimize represents the minimization operation, and subject to represents the constrained state.

[0078] Understandably, in the objective function above, "minimize" corresponds to the asset return volatility optimization function, which can be used to minimize the return volatility of the asset allocation while ensuring that the user's expected return is achieved; "subject to" corresponds to the constraint space, which can be used to set the constraint space for the asset return volatility optimization function to meet the user's constraints.

[0079] This embodiment constructs an efficient frontier curve for holdable assets in the asset market in real time. Based on the efficient frontier curve, a standardized allocation template corresponding to the holdable assets is determined. This standardized allocation template contains several mapping relationships between asset returns and asset allocation. A query is performed on the standardized allocation template using the user's expected return on total assets as a keyword to obtain the target asset allocation corresponding to the total assets. An asset return volatility optimization function is constructed based on the target asset allocation and the user's current asset allocation. A constraint space corresponding to the current asset allocation is determined based on the target asset allocation and preset constraint rules. An objective function is constructed based on the asset return volatility optimization function and the constraint space. This embodiment constructs an efficient frontier analysis framework using the Capital Asset Pricing Model (CAPM), thereby accurately obtaining the target asset allocation corresponding to the user's total assets by combining relevant parameters from four major asset classes: equities, fixed income, currencies, and alternative assets. This achieves optimal asset allocation under a risk-return trade-off, breaking through the limitations of traditional static allocation schemes and providing a theoretical basis for subsequent diagnosis and optimization. Simultaneously, this embodiment also constructs an objective function based on the asset return volatility optimization function and the constraint space, thereby minimizing the return volatility of the asset allocation while ensuring that the user's expected return is achieved and the user's constraints are met.

[0080] refer to Figure 4 , Figure 4 This is a flowchart illustrating the third embodiment of the asset allocation optimization method of this application.

[0081] In one feasible implementation, step S3 may include:

[0082] Step S31: Define the variable used to represent asset allocation in the objective function as the objective variable, and define the projection of the objective variable in the constraint space as the auxiliary variable.

[0083] It should be noted that, assuming the asset allocation of the user's held assets and candidate purchase assets corresponding to the objective function is: the proportion of asset x1 is 40%, the proportion of asset x2 is 30%, and the proportion of asset x3 is 30%, then the objective variable in this objective function can be expressed as x = [x1, x2, x3] = [0.4, 0.3, 0.3]. The above auxiliary variables are projections of the objective variable into the constraint space of the objective function; essentially, they are proxy variables for the constraints. By decoupling complex constraints from the objective function, the quadratic programming problem corresponding to the objective function can be decomposed into subproblems and solved separately. Specifically, the objective variable represents the proportion vector corresponding to the user's held assets and candidate purchase assets.

[0084] Step S32: Decompose the objective function into a first function and a second function based on the objective variable and the auxiliary variable.

[0085] In this specific implementation, the ADMM algorithm is used to solve the quadratic programming problem. Its core idea is to introduce an auxiliary variable z and decompose it into two subproblems: optimizing the target variable x and updating the auxiliary variable z. The update of the target variable x corresponds to the first function mentioned above, and the update of the auxiliary variable z corresponds to the second function mentioned above.

[0086] Based on this, the first function mentioned above can be expressed in the following mathematical form:

[0087]

[0088] Where x represents the target variable, z represents the auxiliary variable, and k represents the number of iterations. k+1 Let x represent the updated value of x in the (k+1)th iteration, and z represent the updated value of z. k Let z and u represent the auxiliary variables for the k-th iteration. k Let ρ denote the Lagrange multiplier for the k-th iteration, ρ denote the penalty parameter of the ADMM algorithm, P denote the covariance matrix, and q denote the transaction cost weight vector (qk). T x represents the transaction cost, and T represents the matrix transpose operation.

[0089] The second function mentioned above can be expressed in the following mathematical form:

[0090]

[0091] Where x represents the target variable, z represents the auxiliary variable, and k represents the number of iterations. k+1 Let x represent the updated value of x in the (k+1)th iteration, and z represent the updated value of z. k+1 Let u represent the z update value in the (k+1)th iteration. k Let represent the Lagrange multiplier for the k-th iteration, ρ represent the penalty parameter of the ADMM algorithm, I(z) represent the indicator function (used to indicate the constraint condition l≤Az≤u), A represent the attribute matrix such as asset class and industry style, l represent the lower limit of the constraint, u represent the upper limit of the constraint, and T represent the matrix transpose operation.

[0092] In one feasible implementation, step S4 may include:

[0093] Step S41: Iteratively update the target variable using the first function, and iteratively update the auxiliary variable using the second function.

[0094] Step S42: Optimize the current asset configuration based on the updated target variable and the updated auxiliary variable to obtain the optimized asset configuration.

[0095] In practical implementation, the target variable and auxiliary variable can be iteratively updated based on the mathematical forms corresponding to the first and second functions mentioned above, respectively, to obtain the updated target variable and updated auxiliary variable. Based on this, after each iterative update of the target variable and auxiliary variable, it is necessary to obtain the real-time difference between the updated target variable and the updated auxiliary variable: if the real-time difference reaches a difference threshold, the current asset allocation can be optimized based on the updated target variable and updated auxiliary variable; if the real-time difference does not reach the difference threshold, the updated target variable and updated auxiliary variable continue to be iteratively updated until the real-time difference reaches the difference threshold.

[0096] In one feasible implementation, step S42 may include:

[0097] Step S421: Use the Lagrangian function to reconcile the updated target variable and the updated auxiliary variable to obtain the reconciled target variable and the reconciled auxiliary variable.

[0098] It should be noted that the Lagrange function mentioned above can be expressed in the following mathematical form:

[0099]

[0100] in, Let x represent the Lagrange function, z represent the target variable, u represent the Lagrange multipliers, P represent the covariance matrix, and q represent the transaction cost weight vector. T x represents the transaction cost, and ρ represents the penalty parameter of the ADMM algorithm.

[0101] In practice, if the difference between the updated target variable and the updated auxiliary variable does not reach the difference threshold, the Lagrange multiplier can be updated according to the Lagrange function, and then the updated target variable and the updated auxiliary variable can be reconciled through the updated Lagrange multiplier to obtain the reconciled target variable and the reconciled auxiliary variable.

[0102] Step S422: If the difference between the coordinated target variable and the coordinated auxiliary variable satisfies the convergence condition, the current asset allocation is optimized based on the coordinated target variable or the coordinated auxiliary variable to obtain an optimized asset allocation.

[0103] It should be understood that the aforementioned convergence condition can be that the reconciled target variable equals the reconciled auxiliary variable. If the difference between the reconciled target variable and the reconciled auxiliary variable satisfies the convergence condition, the current asset allocation can be optimized based on either the reconciled target variable or the reconciled auxiliary variable to obtain an optimized asset allocation. If the difference between the reconciled target variable and the reconciled auxiliary variable does not satisfy the convergence condition, the Lagrange multipliers are updated, and the target variable and auxiliary variable are reconciled based on the updated Lagrange multipliers to initiate a new round of iterative updates until the difference between the reconciled target variable and the reconciled auxiliary variable satisfies the convergence condition.

[0104] Furthermore, the matrix operation steps (such as matrix multiplication in the first function, second function, and Lagrange function) have been optimized in this embodiment and the above embodiments. In the prior art, NumPy (an open-source numerical computation extension for Python) is commonly used for matrix calculations. This method offers significant coding convenience, but the dynamic nature of the Python interpreter introduces substantial performance overhead in areas such as type checking and dynamic type dispatch. The core of computational acceleration is to perform on-the-fly compilation of matrix iteration operations, eliminating the performance loss caused by dynamic typing. Considering the deep integration and ease of use with NumPy, this application uses Numba (a just-in-time compilation accelerator) for just-in-time compilation in practice: it uses the LLVM (Low Level Virtual Machine) compilation framework, which can translate Python functions into intermediate representations before runtime and further compile them into efficient machine code; simultaneously, Numba can also generate machine code based on NumPy array operations, without relying on NumPy's own Python-level calls; it compiles for loops into efficient native code, which is extremely effective for loop-intensive computational processes such as iterative operations. This application utilizes NumPy to design a computational acceleration scheme, allowing for the definition of different state transition functions for different scenarios, and unifying the formalities through matrix iteration operations. By eliminating the type checking overhead of the Python interpreter, this application improves the performance of complex matrix operations in financial scenarios (such as calculating expected asset balances), achieving faster speeds compared to traditional NumPy solutions. For example, when calculating the expected asset balances of customers at different ages, the following transition function can be used:

[0105]

[0106] Among them, E(w) t+1 e(w) represents the customer's expected asset balance at time point t+1. t f represents the customer's expected asset balance at time t, w represents the customer's held asset balance, and f tσ represents the net cash flow occurring between time period t and t+1 (positive deposits and negative withdrawals), μ represents the expected rate of return of the client's portfolio, and σ represents the standard deviation of the annualized rate of return of the client's portfolio.

[0107] In this embodiment, the variable representing asset allocation in the objective function is defined as the objective variable, and the projection of the objective variable into the constraint space is defined as the auxiliary variable. Based on the objective variable and the auxiliary variable, the objective function is decomposed into a first function and a second function. The objective variable is iteratively updated using the first function, and the auxiliary variable is iteratively updated using the second function. The updated objective variable and the updated auxiliary variable are coordinated using a Lagrange function to obtain coordinated objective variable and coordinated auxiliary variable. If the difference between the coordinated objective variable and the coordinated auxiliary variable satisfies the convergence condition, the current asset allocation is optimized based on the coordinated objective variable or the coordinated auxiliary variable to obtain an optimized asset allocation. In this embodiment, the method optimizes the asset allocation problem into a quadratic programming problem and innovatively introduces the ADMM algorithm. By introducing auxiliary variables, the subproblem decomposition of the objective and constraint variables is achieved, making the algorithm naturally support parallel computing and breaking through the performance bottleneck of traditional solvers in large-scale financial data processing. At the same time, this embodiment also coordinates the objectives of minimizing return volatility and minimizing transaction costs through Lagrange multipliers, significantly reducing the frequency of actual buying and redemption by users, thus improving the user experience while ensuring the effectiveness of the investment strategy.

[0108] Reference Figure 5 , Figure 5 This is a structural block diagram of the first embodiment of the asset allocation optimization device of this application.

[0109] like Figure 5 As shown, the asset allocation optimization device proposed in this application includes:

[0110] The configuration determination module 501 is used to determine the target asset configuration corresponding to the total assets based on the user's expected return on the total assets.

[0111] Function construction module 502 is used to construct a target function based on the target asset configuration and the user's current asset configuration;

[0112] The function decomposition module 503 is used to decompose the objective function into a first function and a second function. The first function is used to reduce the volatility of the returns of the current asset allocation, and the second function is used to constrain the current asset allocation.

[0113] The configuration optimization module 504 is used to optimize the current asset configuration according to the first function and the second function to obtain an optimized asset configuration.

[0114] This embodiment determines the target asset allocation corresponding to the total assets based on the user's expected return on total assets; constructs an objective function based on the target asset allocation and the user's current asset allocation; decomposes the objective function into a first function and a second function, whereby the first function is used to reduce the volatility of the current asset allocation's returns, and the second function is used to constrain the current asset allocation; and optimizes the current asset allocation based on the first and second functions to obtain an optimized asset allocation. Compared to existing technologies that allocate asset allocation using a fixed ratio, this embodiment constructs an objective function based on the user's total assets, the target asset allocation, and the current asset allocation. It then decomposes the objective function into a first function to reduce the volatility of the current asset allocation's returns and a second function to constrain the current asset allocation. Finally, it optimizes the current asset allocation based on the first and second functions. This reduces the user's buying and redeeming frequency of assets while ensuring the achievement of the user's expected returns, thereby reducing the volatility of the user's total assets under the optimized asset allocation.

[0115] Based on the first embodiment of the asset allocation optimization device described in this application, a second embodiment of the asset allocation optimization device of this application is proposed.

[0116] In this embodiment, the configuration determination module 501 is further configured to construct an efficient frontier curve of holdable assets in the asset market in real time, determine a standardized configuration template corresponding to the holdable assets based on the efficient frontier curve, and the standardized configuration template contains a mapping relationship between several asset returns and asset configurations; and query the standardized configuration template using the user's expected return on total assets as a keyword to obtain the target asset configuration corresponding to the total assets.

[0117] Furthermore, the function construction module 502 is also used to construct an asset return volatility optimization function based on the target asset configuration and the user's current asset configuration, determine the constraint space corresponding to the current asset configuration based on the target asset configuration and preset constraint rules, and construct a target function based on the asset return volatility optimization function and the constraint space.

[0118] Furthermore, the function decomposition module 503 is also used to define the variable used to represent asset allocation in the objective function as the objective variable, and to define the projection of the objective variable in the constraint space as the auxiliary variable; based on the objective variable and the auxiliary variable, the objective function is decomposed into a first function and a second function.

[0119] Furthermore, the configuration optimization module 504 is also used to iteratively update the target variable through the first function and iteratively update the auxiliary variable through the second function; and to optimize the current asset configuration based on the updated target variable and the updated auxiliary variable to obtain an optimized asset configuration.

[0120] Furthermore, the configuration optimization module 504 is also used to coordinate the updated target variable and the updated auxiliary variable through a Lagrange function to obtain a coordinated target variable and a coordinated auxiliary variable; if the difference between the coordinated target variable and the coordinated auxiliary variable satisfies the convergence condition, the current asset configuration is optimized according to the coordinated target variable or the coordinated auxiliary variable to obtain an optimized asset configuration.

[0121] Other embodiments or specific implementations of the asset allocation optimization device of this application can be found in the above-described method embodiments, and will not be repeated here.

[0122] This application provides an asset allocation optimization device, which includes: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the asset allocation optimization method in the first embodiment described above.

[0123] The following is for reference. Figure 6 The diagram illustrates a structural schematic suitable for implementing the asset configuration optimization device in the embodiments of this application. The asset configuration optimization device in the embodiments of this application may include, but is not limited to, mobile terminals such as mobile phones, laptops, digital broadcast receivers, PDAs (Personal Digital Assistants), PADs (Portable Application Description), PMPs (Portable Media Players), in-vehicle terminals (e.g., in-vehicle navigation terminals), and fixed terminals such as digital TVs and desktop computers. Figure 6 The asset allocation optimization device shown is merely an example and should not impose any limitations on the functionality and scope of use of the embodiments of this application.

[0124] like Figure 6As shown, the asset allocation optimization device may include a processing unit 1001 (e.g., a central processing unit, a graphics processing unit, etc.) that can perform various appropriate actions and processes according to a program stored in a read-only memory 1002 or a program loaded from a storage device 1003 into a random access memory 1004. The random access memory 1004 also stores various programs and data required for the operation of the asset allocation optimization device. The processing unit 1001, the read-only memory 1002, and the random access memory 1004 are interconnected via a bus 1005. An input / output interface 1006 is also connected to the bus. Typically, the following systems can be connected to the input / output interface 1006: input devices 1007 including, for example, a touchscreen, touchpad, keyboard, mouse, image sensor, microphone, accelerometer, gyroscope, etc.; output devices 1008 including, for example, a liquid crystal display (LCD), speaker, vibrator, etc.; storage devices 1003 including, for example, magnetic tape, hard disk, etc.; and communication devices 1009. The communication device 1009 allows the asset configuration optimization device to communicate wirelessly or wiredly with other devices to exchange data. While the figure shows an asset configuration optimization device with various systems, it should be understood that implementing or having all of the systems shown is not required. More or fewer systems may be implemented alternatively.

[0125] Specifically, according to the embodiments disclosed in this application, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, embodiments disclosed in this application include a computer program product comprising a computer program carried on a computer-readable medium, the computer program containing program code for performing the methods shown in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network via a communication device, or installed from storage device 1003, or installed from read-only memory 1002. When the computer program is executed by processing device 1001, it performs the functions defined in the methods of the embodiments disclosed in this application.

[0126] The asset allocation optimization device provided in this application, employing the asset allocation optimization method described in the above embodiments, can solve the technical problem of high return volatility in existing asset allocation schemes. Compared with the prior art, the beneficial effects of the asset allocation optimization device provided in this application are the same as those of the asset allocation optimization method provided in the above embodiments, and other technical features of the asset allocation optimization device are the same as those disclosed in the previous embodiment method, and will not be repeated here.

[0127] It should be understood that the various parts disclosed in this application can be implemented using hardware, software, firmware, or a combination thereof. In the description of the above embodiments, specific features, structures, materials, or characteristics can be combined in any suitable manner in one or more embodiments or examples.

[0128] The above description is merely a specific embodiment of this application, but the scope of protection of this application is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the technical scope disclosed in this application should be included within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.

[0129] This application provides a computer-readable storage medium having computer-readable program instructions (i.e., a computer program) stored thereon, the computer-readable program instructions being used to execute the asset configuration optimization method in the above embodiments.

[0130] The computer-readable storage medium provided in this application may be, for example, a USB flash drive, but is not limited to, electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems or devices, or any combination thereof. More specific examples of computer-readable storage media may include, but are not limited to: electrical connections having one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fibers, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof. In this embodiment, the computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system or device. The program code contained on the computer-readable storage medium may be transmitted using any suitable medium, including but not limited to: wires, optical cables, RF (Radio Frequency), etc., or any suitable combination thereof.

[0131] The aforementioned computer-readable storage medium may be included in the asset allocation optimization device; or it may exist independently and not be assembled into the asset allocation optimization device.

[0132] The aforementioned computer-readable storage medium carries one or more programs that, when executed by the asset configuration optimization device, enable the asset configuration optimization device to write computer program code for performing the operations of this application in one or more programming languages ​​or a combination thereof. These programming languages ​​include object-oriented programming languages ​​such as Java, Smalltalk, and C++; and also conventional procedural programming languages ​​such as C or similar languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as a standalone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving remote computers, the remote computer can be connected to the user's computer via any type of network, such as a local area network (LAN) or a wide area network (WAN), or connected to an external computer (e.g., via the Internet using an Internet service provider).

[0133] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of this application. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions indicated in the blocks may occur in a different order than those indicated in the drawings. For example, two consecutively indicated blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, can be implemented using a dedicated hardware-based system that performs the specified function or operation, or using a combination of dedicated hardware and computer instructions.

[0134] The modules described in the embodiments of this application can be implemented in software or hardware. The names of the modules do not necessarily limit the functionality of the unit itself.

[0135] The readable storage medium provided in this application is a computer-readable storage medium that stores computer-readable program instructions (i.e., a computer program) for executing the above-described asset allocation optimization method, which can solve the technical problem of high return volatility in existing asset allocation schemes. Compared with the prior art, the beneficial effects of the computer-readable storage medium provided in this application are the same as the beneficial effects of the asset allocation optimization method provided in the above embodiments, and will not be repeated here.

[0136] This application also provides a computer program product, including a computer program that, when executed by a processor, implements the steps of the asset allocation optimization method described above.

[0137] The computer program product provided in this application can solve the technical problem of asset allocation optimization. Compared with the prior art, the beneficial effects of the computer program product provided in this application are the same as the beneficial effects of the asset allocation optimization method provided in the above embodiments, and will not be repeated here.

[0138] The above description is only a part of the embodiments of this application and does not limit the scope of protection of this application. All equivalent structural transformations made under the technical concept of this application and using the content of this application specification and drawings, or direct / indirect applications in other related technical fields, are included in the scope of protection of this application.

Claims

1. An asset allocation optimization method, characterized in that, The method includes the following steps: The target asset allocation corresponding to the total assets is determined based on the user's expected return on the total assets. Construct a target function based on the target asset configuration and the user's current asset configuration; The objective function is decomposed into a first function and a second function. The first function is used to reduce the volatility of the returns of the current asset allocation, and the second function is used to constrain the current asset allocation. The current asset allocation is optimized based on the first function and the second function to obtain an optimized asset allocation.

2. The asset allocation optimization method as described in claim 1, characterized in that, The step of determining the target asset allocation corresponding to the total assets based on the user's expected return on the total assets includes: Construct efficient frontier curves for holdable assets in the asset market in real time, and determine standardized allocation templates for the holdable assets based on the efficient frontier curves. The standardized allocation templates contain several mapping relationships between asset returns and asset allocation. By using the user's expected return on total assets as keywords, a query can be performed in the standardized configuration template to obtain the target asset configuration corresponding to the total assets.

3. The asset allocation optimization method as described in claim 1, characterized in that, The step of constructing the objective function based on the target asset configuration and the user's current asset configuration includes: An asset return volatility optimization function is constructed based on the target asset allocation and the user's current asset allocation, and the constraint space corresponding to the current asset allocation is determined based on the target asset allocation and preset constraint rules. The objective function is constructed based on the asset return volatility optimization function and the constraint space.

4. The asset allocation optimization method as described in claim 1, characterized in that, The step of decomposing the objective function into a first function and a second function includes: The variable used to represent asset allocation in the objective function is defined as the objective variable, and the projection of the objective variable in the constraint space is defined as the auxiliary variable. The objective function is decomposed into a first function and a second function based on the target variable and the auxiliary variable.

5. The asset allocation optimization method as described in claim 4, characterized in that, The step of optimizing the current asset allocation based on the first function and the second function to obtain an optimized asset allocation includes: The target variable is iteratively updated using the first function, and the auxiliary variable is iteratively updated using the second function; The current asset allocation is optimized based on the updated target variable and the updated auxiliary variable to obtain an optimized asset allocation.

6. The asset allocation optimization method as described in claim 5, characterized in that, The step of optimizing the current asset allocation based on the updated target variable and the updated auxiliary variable to obtain the optimized asset allocation includes: The updated target variable and the updated auxiliary variable are reconciled using the Lagrange function to obtain the reconciled target variable and the reconciled auxiliary variable. If the difference between the coordinated target variable and the coordinated auxiliary variable satisfies the convergence condition, the current asset allocation is optimized based on the coordinated target variable or the coordinated auxiliary variable to obtain an optimized asset allocation.

7. An asset allocation optimization device, characterized in that, The asset allocation optimization device includes: The configuration determination module is used to determine the target asset configuration corresponding to the total assets based on the user's expected return on the total assets. The function construction module is used to construct a target function based on the target asset configuration and the user's current asset configuration; The function decomposition module is used to decompose the objective function into a first function and a second function. The first function is used to reduce the volatility of the returns of the current asset allocation, and the second function is used to constrain the current asset allocation. The configuration optimization module is used to optimize the current asset configuration according to the first function and the second function to obtain an optimized asset configuration.

8. An asset allocation optimization device, characterized in that, The device includes: a memory, a processor, and an asset configuration optimization program stored in the memory and executable on the processor, the asset configuration optimization program being configured to implement the steps of the asset configuration optimization method as described in any one of claims 1 to 6.

9. A storage medium, characterized in that, The storage medium is a computer-readable storage medium, and the storage medium stores an asset allocation optimization program, which, when executed by a processor, implements the steps of the asset allocation optimization method as described in any one of claims 1 to 6.

10. A computer program product, characterized in that, The computer program product includes an asset allocation optimization program, which, when executed by a processor, implements the steps of the asset allocation optimization method as described in any one of claims 1 to 6.

Images