WO2019080434A1 - 一种投资标的的选择方法、装置及计算机可读介质 - Google Patents

一种投资标的的选择方法、装置及计算机可读介质

Info

Publication number
WO2019080434A1
WO2019080434A1 PCT/CN2018/078325 CN2018078325W WO2019080434A1 WO 2019080434 A1 WO2019080434 A1 WO 2019080434A1 CN 2018078325 W CN2018078325 W CN 2018078325W WO 2019080434 A1 WO2019080434 A1 WO 2019080434A1
Authority
WO
WIPO (PCT)
Prior art keywords
ratio
factor
candidate
sotino
time point
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/CN2018/078325
Other languages
English (en)
French (fr)
Inventor
吕东哲
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.)
OneConnect Smart Technology Co Ltd
Original Assignee
OneConnect Smart Technology Co 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 OneConnect Smart Technology Co Ltd filed Critical OneConnect Smart Technology Co Ltd
Publication of WO2019080434A1 publication Critical patent/WO2019080434A1/zh
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

Definitions

  • the present application relates to the field of investment target selection technology, and more particularly, the present application relates to a method, device and computer readable medium for selecting an investment target.
  • the portfolio of Sharpe ratio is optimally selected through the Markowitz model.
  • the average annualized rate of return for these portfolios may be negative in the future, the Sharpe ratio may be negative, and the volatility may be higher.
  • a method of selecting an investment target comprising:
  • the investment target is selected from all funds according to the effective factor and the information ratio corresponding to the effective factor.
  • an apparatus for selecting an investment target comprising:
  • a candidate factor determining module for determining a candidate factor
  • a regression calculation module configured to perform regression calculation on each candidate factor, and obtain a correlation coefficient, an information ratio, and a third-order Sotino ratio corresponding to each candidate factor;
  • An effective factor determining module configured to determine an effective factor according to a correlation coefficient, an information ratio, and a third-order Sotino ratio corresponding to each candidate factor;
  • the investment target selection module is configured to select an investment target from all funds according to the effective factor and the information ratio corresponding to the effective factor.
  • a computer readable storage medium storing computer executable instructions for causing the computer to perform the following steps:
  • the investment target is selected from all funds according to the effective factor and the information ratio corresponding to the effective factor.
  • An advantageous effect of the present application is that the investment target selected according to the method of the present application can pursue a robust profit while significantly reducing the risk.
  • FIG. 1 is a flow chart of an embodiment of a method for selecting an investment target according to the present application
  • FIG. 2 is a flow chart of another embodiment of a method for selecting an investment target according to the present application.
  • FIG. 3 is a block diagram showing an implementation structure of a selection device for an investment target according to the present application.
  • FIG. 4 is a block schematic diagram showing another implementation structure of a selection device for an investment target according to the present application.
  • 1 is a flow chart of an implementation method of a method for selecting an investment target according to the present application.
  • the selection method comprises the following steps:
  • step S110 a candidate factor is determined.
  • the attribution model such as the TM performance attribution model to obtain the stock picking ability in the past three years, the timing ability in the past three years, and the beta coefficient in the past three years.
  • Candidate factor In this way, ten candidate factors can be obtained.
  • the T-M model is a quadratic regression model based on CAPM improvement.
  • the linear regression method adopted is based on comparing the fund with the market benchmark and quantifying the stock selection and timing ability of the fund.
  • the formula for the T-M performance attribution model can be:
  • R p -R f ⁇ + ⁇ (R m -R f )+ ⁇ (R m -R f ) 2 + ⁇
  • Rf is the risk-free rate
  • Rp is the actual rate of return of the fund in each period
  • Rm is the actual rate of return of the market portfolio in each period
  • the ⁇ , ⁇ and ⁇ obtained by the regression are the stock picking ability of the past three years, the past three Year beta coefficient, and timing ability in the past three years
  • ⁇ is a random error term.
  • ⁇ measures the ability of the portfolio to obtain excess returns. If the alpha value is greater than zero, it indicates that the fund manager has the ability to select stocks. The larger the alpha value, the stronger the stock picking ability. If ⁇ is greater than zero, it means that the fund manager has the timing ability.
  • Step S120 performing regression calculation on each candidate factor to obtain a correlation coefficient, an information ratio, and a third-order Sotino ratio corresponding to each candidate factor.
  • the multi-factor model regression object can set the Sotino ratio for the future, for example, the Sotino ratio for the next half year.
  • the Sotino ratio is a measure of the relative performance of a portfolio. Similar to the Sharpe ratio, but the Sotino ratio uses the lower standard deviation rather than the total standard deviation to distinguish between adverse and favorable fluctuations. Similar to the Sharpe ratio, the higher the ratio, the higher the excess return on the fund's downside risk to the same unit.
  • step S120 further includes steps S121 to S128 as shown in FIG. 2 .
  • step S121 a set of past time points is selected.
  • This group of past time points can be No. 1 of each month in the past five years, such as 20110101, 20110201, ..., 20161101, 20161201, etc., for a total of 60 time points.
  • step S122 the values of all candidate factors of all funds at each time point are calculated.
  • the fund size of each fund at each time point can be calculated the fund size of each fund at each time point, the annualized rate of return in the past three years, the maximum retracement in the past three years, the standard deviation in the past three years, and the downside standard deviation in the past three years.
  • the Sharpe ratio in the past three years the Sotino ratio in the past three years, the stock picking ability in the past three years, the timing ability in the past three years, and the beta coefficient in the past three years.
  • each candidate factor at the first time point may be a series of factor1_list1, factor2_list(1), ..., factor10_list(1); at the second time point, the value of each candidate factor may be The series factor1_list(2), factor2_list(2), ..., factor10_list(2); and so on, the value of each candidate factor at the 60th time point can be a series of factor1_list(60), factor2_list(60) ), ..., factor10_list(60).
  • each series includes the corresponding candidate factor values of all funds at corresponding time points.
  • step S123 the Sotino ratio of all funds relative to the past set time points in the future set time is calculated.
  • the formula for the Sotino ratio can be:
  • SoR is the Sotino ratio
  • R p -R f is the fund's excess return rate
  • DD EX is the downside standard deviation
  • R i is the monthly rate of return
  • n is the number of time points.
  • the Sotino ratio for the next half year relative to each of the above time points is calculated.
  • the future half year relative to the time point 20110101 is 20110701
  • n can be 6, and R i is the monthly rate of return from the time point 20110101 to the time point 20110701
  • the future half year relative to the time point 20161201 is 20170601
  • n can be 66
  • R i is the yield per month from time point 20110101 to time point 20170601.
  • the candidate factor value at any time point corresponds to the proposed ratio for the next half year at that time point, that is, the candidate factor value at time point 20110101, and the Sotino ratio at time point 20110101 in the next half year 20110701 is Corresponding.
  • the Sotino ratio corresponding to each time point is a series of SoR_list(1), SoR_list(2), ..., SoR_list(60).
  • each series includes the Sotino ratio corresponding to each fund.
  • Step S124 performing regression calculation on the value of each candidate factor and the corresponding Sotino ratio respectively, and obtaining a correlation coefficient of each candidate factor at each time point.
  • the correlation coefficient is calculated as:
  • ⁇ (x, y) is the correlation coefficient
  • Cov(x, y) is the covariance of one of the factors and the Sotino ratio of a fund
  • each candidate factor value may be separately calculated at each time point and the corresponding Sotino ratio.
  • the regression calculation may be performed according to the value of the first candidate factor factor1_list(1) and the Sotino ratio SoR_list(1) at the first time point, and the corresponding first candidate factor is obtained at each time point.
  • the correlation coefficient is factor1_ic(1); according to the value of the first candidate factor factor1_list(2) and the Sotino ratio SoR_list(2) at the second time point, the corresponding first candidate factor is obtained.
  • the correlation coefficients at time points are factor1_ic(2); whil; according to the value of the first candidate factor factor1_list(n) and the Sotino ratio SoR_list(n) at the nth time point, the regression calculation is obtained.
  • the correlation coefficient corresponding to the first candidate factor at each time point is factor1_ic(n), respectively, where, in the present embodiment, 1 ⁇ n ⁇ 60.
  • the correlation coefficient of the corresponding second candidate factor at each time point is obtained.
  • the correlation coefficient is factor1_ic(2); «; according to the value of the second candidate factor factor1_list(n) and the Sotino ratio SoR_list(n) at the nth time point, the regression calculation is performed, and the corresponding second is obtained.
  • the correlation coefficient of each candidate factor at each time point is factor1_ic(n), respectively, where, in the present embodiment, 1 ⁇ n ⁇ 60.
  • Step S125 calculating a third-order Sotino ratio of each candidate factor at each time point according to the Sotino ratio and the value of the candidate factor.
  • the funds of each time point may be divided into three combinations according to the value of each candidate factor; and the mean of the Sotino ratios of the three combinations corresponding to each candidate factor at each time point is calculated.
  • Analysis can be performed at each time point for each candidate factor. At the first point in time, all funds are sorted according to the value of the first candidate factor, and then all funds are divided into three combinations according to the sorting order, and the relatives of all the funds in each combination are calculated.
  • the mean value of the Sotino ratio at one time point is factor1_sortino1(1), factor1_sortino2(1), factor1_sortino3(1), then the third-order Sotino ratio of the first candidate factor at the first time point is factor1_sortino1 ( 1), factor1_sortino2(1), factor1_sortino3(1).
  • the funds are sorted according to the value of the first candidate factor, and then all the funds are divided into three combinations according to the sorting order, and all the components in each combination are calculated.
  • the mean value of the fund's Sotino ratio relative to the first time point is factor1_sortino1(n), factor1_sortino2(n), factor1_sortino3(n), then the first candidate factor is the third gear Sotino at the first time point.
  • the ratio is factor1_sortino1(n), factor1_sortino2(n), factor1_sortino3(n).
  • step S125 may be after execution of step S123 is completed, before execution of step S128.
  • Step S126 calculating the mean value of the correlation coefficient of each candidate factor at each time point at all time points, and obtaining a correlation coefficient corresponding to each candidate factor.
  • calculating the mean value of the correlation coefficient of the first candidate factor at all time points may specifically calculate the average value of factor1_ic(1), factor1_ic(2), ..., factor1_ic(60) as the corresponding first Correlation coefficient of candidate factors.
  • the average value of the correlation coefficient of the tenth candidate factor at all time points is calculated, and the average value of factor10_ic(1), factor10_ic(2), ..., factor10_ic(60) can be calculated as the corresponding tenth. Correlation coefficient of candidate factors.
  • Step S127 calculating an information ratio corresponding to each candidate factor according to a correlation coefficient of each candidate factor at each time point.
  • IR is the information ratio
  • E( ⁇ (x, y)) is the mean of the correlation coefficients
  • ⁇ ⁇ (x, y) is the standard deviation of the correlation coefficients.
  • the average value of the correlation coefficient of the first candidate factor at all time points may be calculated; and the first candidate is calculated.
  • the standard deviation of the correlation coefficient of the factor at all time points that is, the standard deviation of factor1_ic(1), factor1_ic(2), ..., factor1_ic(60)
  • the information ratio factor1_ir may be calculated; and the ratio of the mean value to the standard deviation to obtain the corresponding first candidate factor.
  • the mean value of the correlation coefficient of the tenth candidate factor at all time points is calculated, that is, the average of factor10_ic(1), factor10_ic(2), ..., factor10_ic(60); then the tenth candidate factor is calculated.
  • the standard deviation of the correlation coefficients at all time points that is, the standard deviation of factor10_ic(1), factor10_ic(2), ..., factor10_ic(60), and then calculate the ratio of the mean value to the standard deviation to obtain the corresponding tenth candidate factor.
  • Information ratio factor10_ir is the standard deviation of the correlation coefficient of the tenth candidate factor at all time points.
  • Step S128, calculating the mean value of the third-order Sotino ratio corresponding to each candidate factor at each time point at all time points, and obtaining a third-order Sotino ratio corresponding to each candidate factor.
  • the third-order Sotino ratio of the first candidate factor at all time points that is, calculate the average of factor1_sortino1(1), factor1_sortino1(2), ..., factor1_sortino1(60) to obtain factor1_sortino1_avg, and calculate factor1_sortino2(1) ), the average of factor1_sortino2(2), ..., factor1_sortino2(60) is obtained by factor1_sortino2_avg, and the average of factor1_sortino3(1), factor1_sortino3(2), ..., factor1_sortino3(60) is calculated to obtain factor1_sortino3_avg, then corresponding to the first one
  • the third-order Sotino ratio of the candidate factor is factor1_sortino1_avg, factor1_sortino2_avg, factor1_sortino3_avg.
  • Step S130 determining an effective factor according to a correlation coefficient, an information ratio, and a third-order Sotino ratio corresponding to each candidate factor.
  • the effective factor screening rule can be comprehensively determined according to the correlation coefficient, the monotonicity of the third-order Sotino ratio, the collinearity between the factors, and the information ratio.
  • the candidate factor whose correlation coefficient is greater than the first set value, the third-order Sotino ratio has monotonicity, and the information ratio is greater than the second set value may be selected as the effective factor.
  • a candidate factor whose absolute value of the mean value of the correlation coefficient is greater than 0.1 may be selected as the effective factor.
  • It may also be a candidate factor whose absolute value of the information ratio is greater than the second set value as the effective factor.
  • the identified effective factors may include, for example, the size of the fund, the maximum retracement over the past three years, the Sharpe ratio for the past three years, the Sotino ratio for the past three years, and the stock picking ability for the past three years.
  • Step S140 selecting an investment target from all the funds according to the effective factor and the information ratio corresponding to the effective factor.
  • the comprehensive score of each fund is calculated according to the value of each effective factor of each fund and the information ratio corresponding to each effective factor.
  • the method for calculating the comprehensive score of each fund may be to calculate the value of the effective factor of each fund, multiply by the information ratio of the corresponding effective factor, and finally accumulate to obtain the comprehensive score of each fund.
  • the formula for calculating the composite score can be:
  • FactorX i is the i-th effective factor value of each fund.
  • the present application also provides a selection device for an investment target.
  • 3 is a block schematic diagram of an implementation structure of a selection device for an investment target according to the present application.
  • the selection device further includes a candidate factor determination module 310, a regression calculation module 320, an effective factor determination module 330, and an investment target selection module 340, wherein the candidate factor determination module 310 is configured to determine a candidate factor; the regression calculation module 320 is configured to perform a regression calculation on each candidate factor to obtain a correlation coefficient, an information ratio, and a third-order Sotino ratio corresponding to each candidate factor; the effective factor determining module 330 is configured to use a correlation coefficient corresponding to each candidate factor, The information ratio and the third-order Sotino ratio determine an effective factor; the investment target selection module 340 is configured to select an investment target from all funds according to the effective factor and the information ratio corresponding to the effective factor.
  • the candidate factor determination module 310 is configured to determine a candidate factor
  • the regression calculation module 320 is configured to perform a regression calculation on each candidate factor to obtain a correlation coefficient, an information ratio, and a third-order Sotino ratio corresponding to each candidate factor
  • the effective factor determining module 330 is
  • the regression calculation module 320 includes a time point selection unit 321, a candidate factor calculation unit 322, a pitch ratio calculation unit 323, a first correlation coefficient calculation unit 324, and a first third gear ratio.
  • the above-described time point selection unit 321 is for selecting a set of past time points.
  • the above candidate factor calculation unit 322 is used to calculate values of all candidate factors of all funds at each time point.
  • the above-described promise ratio calculation unit 323 is used to calculate the Sotino ratio of all funds with respect to the set time point in the past at a set time in the future.
  • the first correlation coefficient calculation unit 324 is configured to perform a regression calculation on the value of each candidate factor and the corresponding Sotino ratio, respectively, to obtain a correlation coefficient of each candidate factor at each time point.
  • the first third gear ratio calculation unit 325 is configured to calculate a third gear ratio of each candidate factor at each time point according to the Sotino ratio and the value of the candidate factor.
  • the second correlation coefficient calculation unit 326 is configured to calculate an average of the correlation coefficients of each candidate factor at each time point at all time points, and obtain a correlation coefficient corresponding to each candidate factor.
  • the above information ratio calculation unit 327 is configured to calculate an information ratio corresponding to each candidate factor according to the correlation coefficient of each candidate factor at each time point.
  • the second third gear ratio calculation unit 328 is configured to calculate the mean value of the three-speed Sotino ratio corresponding to each candidate factor at each time point at all time points, and obtain a third-order summation corresponding to each candidate factor. Connaught ratio.
  • the first third gear ratio calculation unit 325 further includes a grouping subunit and a calculation subunit for dividing the funds at each time point according to the value of each candidate factor, respectively.
  • the calculation sub-unit is configured to calculate a mean value of the Sotino ratio of each of the three investment combinations corresponding to each candidate factor at each time point, as each candidate factor corresponds to the third gear at each time point Sotino ratio.
  • the effective factor determining module 330 is further configured to select, as the effective factor, a candidate factor whose absolute value of the correlation coefficient is greater than the first set value, the third-order Sotino ratio has monotonicity, and the information ratio is greater than the second set value.
  • the investment target selection module 340 further includes a score calculation unit and a selection unit, configured to calculate a comprehensive score for each fund according to a value of each effective factor of each fund and an information ratio corresponding to each effective factor;
  • the selection unit is configured to select a fund with a set number of the highest comprehensive score as an investment target.
  • the application also provides a computer readable storage medium storing computer executable instructions for causing the computer to perform the aforementioned selection method.
  • the application can be an apparatus, method, and/or computer program product.
  • the computer program product can comprise a computer readable storage medium having computer readable program instructions embodied thereon for causing a processor to implement various aspects of the present application.
  • the computer readable storage medium can be a tangible device that can hold and store the instructions used by the instruction execution device.
  • the computer readable storage medium can be, for example, but not limited to, an electrical storage device, a magnetic storage device, an optical storage device, an electromagnetic storage device, a semiconductor storage device, or any suitable combination of the foregoing.
  • Non-exhaustive list of computer readable storage media include: portable computer disks, hard disks, random access memory (RAM), read only memory (ROM), erasable programmable read only memory (EPROM) Or flash memory), static random access memory (SRAM), portable compact disk read only memory (CD-ROM), digital versatile disk (DVD), memory stick, floppy disk, mechanical encoding device, for example, with instructions stored thereon A raised structure in the hole card or groove, and any suitable combination of the above.
  • a computer readable storage medium as used herein is not to be interpreted as a transient signal itself, such as a radio wave or other freely propagating electromagnetic wave, an electromagnetic wave propagating through a waveguide or other transmission medium (eg, a light pulse through a fiber optic cable), or through a wire The electrical signal transmitted.
  • the computer readable program instructions described herein can be downloaded from a computer readable storage medium to various computing/processing devices or downloaded to an external computer or external storage device over a network, such as the Internet, a local area network, a wide area network, and/or a wireless network.
  • the network may include copper transmission cables, fiber optic transmissions, wireless transmissions, routers, firewalls, switches, gateway computers, and/or edge servers.
  • a network adapter card or network interface in each computing/processing device receives computer readable program instructions from the network and forwards the computer readable program instructions for storage in a computer readable storage medium in each computing/processing device .
  • Computer program instructions for performing the operations of the present application can be assembly instructions, instruction set architecture (ISA) instructions, machine instructions, machine related instructions, microcode, firmware instructions, state setting data, or in one or more programming languages.
  • the computer readable program instructions can execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer, partly on the remote computer, or entirely on the remote computer or server. carried out.
  • the remote computer can be connected to the user's computer through any kind of network, including a local area network (LAN) or wide area network (WAN), or can be connected to an external computer (eg, using an Internet service provider to access the Internet) connection).
  • the customized electronic circuit such as a programmable logic circuit, a field programmable gate array (FPGA), or a programmable logic array (PLA), can be customized by utilizing state information of computer readable program instructions.
  • Computer readable program instructions are executed to implement various aspects of the present application.
  • the computer readable program instructions can be provided to a general purpose computer, a special purpose computer, or a processor of other programmable data processing apparatus to produce a machine such that when executed by a processor of a computer or other programmable data processing apparatus Means for implementing the functions/acts specified in one or more of the blocks of the flowcharts and/or block diagrams.
  • the computer readable program instructions can also be stored in a computer readable storage medium that causes the computer, programmable data processing device, and/or other device to operate in a particular manner, such that the computer readable medium storing the instructions includes An article of manufacture that includes instructions for implementing various aspects of the functions/acts recited in one or more of the flowcharts.
  • the computer readable program instructions can also be loaded onto a computer, other programmable data processing device, or other device to perform a series of operational steps on a computer, other programmable data processing device or other device to produce a computer-implemented process.
  • instructions executed on a computer, other programmable data processing apparatus, or other device implement the functions/acts recited in one or more of the flowcharts and/or block diagrams.
  • each block in the flowchart or block diagram can represent a module, a program segment, or a portion of an instruction that includes one or more components for implementing the specified logical functions.
  • Executable instructions can also occur in a different order than those illustrated in the drawings. For example, two consecutive blocks may be executed substantially in parallel, and they may sometimes be executed in the reverse order, depending upon the functionality involved.
  • each block of the block diagrams and/or flowcharts, and combinations of blocks in the block diagrams and/or flowcharts can be implemented in a dedicated hardware-based system that performs the specified function or function. Or it can be implemented by a combination of dedicated hardware and computer instructions. It is well known to those skilled in the art that implementation by hardware, implementation by software, and implementation by a combination of software and hardware are equivalent.

Landscapes

  • Engineering & Computer Science (AREA)
  • Business, Economics & Management (AREA)
  • Finance (AREA)
  • Accounting & Taxation (AREA)
  • Development Economics (AREA)
  • Operations Research (AREA)
  • Game Theory and Decision Science (AREA)
  • Human Resources & Organizations (AREA)
  • Entrepreneurship & Innovation (AREA)
  • Economics (AREA)
  • Marketing (AREA)
  • Strategic Management (AREA)
  • Technology Law (AREA)
  • Physics & Mathematics (AREA)
  • General Business, Economics & Management (AREA)
  • General Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Financial Or Insurance-Related Operations Such As Payment And Settlement (AREA)

Abstract

本申请公开了一种投资标的的选择方法、装置及计算机可读介质，该选择方法包括：确定候选因子；对每一候选因子进行回归计算，得到对应每一候选因子的相关系数、信息比率及三档索提诺比率；根据所述每一候选因子对应的相关系数、信息比率及三档索提诺比率确定有效因子；根据所述有效因子、及所述有效因子对应的信息比率，从所有基金选择投资标的。这样，根据本申请的方法选择的投资标的，就可以在显著降低风险的同时追求稳健的收益。

Description

一种投资标的的选择方法、装置及计算机可读介质
本申请申明享有2017年10月26日递交的申请号为CN2017110293515、名称为“一种投资标的的选择方法、装置及存储介质”的中国专利申请的优先权，该中国专利申请的整体内容以参考的方式结合在本申请中。
技术领域
本申请涉及投资标的选择技术领域，更具体地，本申请涉及一种投资标的的选择方法、装置及计算机可读介质。
背景技术
目前，可以是通过人为宏观选择出投资组合，也可以是人为预选出的一定数量的基金，根据这些基金在过去的收益率，通过马科维茨模型选择出夏普比率最优情况下的投资组合。但是，这些投资组合在未来的平均年化收益率可能会为负数，夏普比率也可能为负数，波动率也可能会偏高。
发明内容
本申请的一个目的是提供一种至少能够解决上述问题之一的新的技术方案。
根据本申请的第一方面，提供了一种投资标的的选择方法，包括：
确定候选因子；
对每一候选因子进行回归计算，得到对应每一候选因子的相关系数、信息比率及三档索提诺比率；
根据所述每一候选因子对应的相关系数、信息比率及三档索提诺比率确定有效因子；
根据所述有效因子、及所述有效因子对应的信息比率，从所有基金选择投资标的。
根据本申请的第二方面，提供了一种投资标的的选择装置，包括：
候选因子确定模块，用于确定候选因子；
回归计算模块，用于对每一候选因子进行回归计算，得到对应每一候选因子的相关系数、信息比率及三档索提诺比率；
有效因子确定模块，用于根据所述每一候选因子对应的相关系数、信息比率及三档索提诺比率确定有效因子；
投资标的选择模块，用于根据所述有效因子、及所述有效因子对应的信息比率，从所有基金选择投资标的。
根据本申请的第三方面，提供了一种计算机可读存储介质，所述计算机可读存储介质存储有计算机可执行指令，所述计算机可执行指令用于使所述计算机执行以下步骤：
确定候选因子；
对每一候选因子进行回归计算，得到对应每一候选因子的相关系数、信息比率及三档索提诺比率；
根据所述每一候选因子对应的相关系数、信息比率及三档索提诺比率确定有效因子；
根据所述有效因子、及所述有效因子对应的信息比率，从所有基金选择投资标的。
本申请的一个有益效果在于，根据本申请的方法选择的投资标的，就可以在显著降低风险的同时追求稳健的收益。
通过以下参照附图对本申请的示例性实施例的详细描述，本申请的其它特征及其优点将会变得清楚。
附图说明
被结合在说明书中并构成说明书的一部分的附图示出了本申请的实施例，并且连同其说明一起用于解释本申请的原理。
图1为根据本申请一种投资标的的选择方法的一种实施方式的流程图；
图2为根据本申请一种投资标的的选择方法的另一种实施方式的流程图；
图3为根据本申请一种投资标的的选择装置的一种实施结构的方框原 理图；
图4为根据本申请一种投资标的的选择装置的另一种实施结构的方框原理图。
具体实施方式
现在将参照附图来详细描述本申请的各种示例性实施例。应注意到：除非另外具体说明，否则在这些实施例中阐述的部件和步骤的相对布置、数字表达式和数值不限制本申请的范围。
以下对至少一个示例性实施例的描述实际上仅仅是说明性的，决不作为对本申请及其应用或使用的任何限制。
对于相关领域普通技术人员已知的技术、方法和设备可能不作详细讨论，但在适当情况下，所述技术、方法和设备应当被视为说明书的一部分。
在这里示出和讨论的所有例子中，任何具体值应被解释为仅仅是示例性的，而不是作为限制。因此，示例性实施例的其它例子可以具有不同的值。
应注意到：相似的标号和字母在下面的附图中表示类似项，因此，一旦某一项在一个附图中被定义，则在随后的附图中不需要对其进行进一步讨论。
图1为根据本申请一种投资标的的选择方法的一种实施方法的流程图。
根据图1所示，该选择方法包括以下步骤：
步骤S110，确定候选因子。
例如，可以预先选取基金规模、过去三年的年化收益率、过去三年的最大回撤、过去三年标准差、过去三年的下行标准差、过去三年的夏普比率、过去三年的索提诺比率等作为基本的候选因子。
为了寻找更多候选因子，增加模型的预测稳定性，还可以利用T-M业绩归因模型等归因模型，得到过去三年选股能力、过去三年择时能力、过去三年贝塔系数等三个候选因子。这样，就可以得到十个候选因子。
具体的，T-M模型是基于CAPM改良的一个二次回归模型，采取的线性 回归方法，其本质是将基金与市场基准比较，量化基金的选股及择时能力。
T-M业绩归因模型的公式具体可以为：
R p-R f＝α+β(R m-R f)+γ(R m-R f) 2+ε
其中，Rf为无风险利率,Rp为基金在各时期的实际收益率；Rm为市场组合在各时期的实际收益率；回归得到的α、β和γ分别为过去三年选股能力、过去三年贝塔系数、及过去三年择时能力；ε是随机误差项。
α衡量了投资组合获取超额收益的能力，如果α值大于零，表明基金经理具备选股能力，α值越大，这种选股能力也就越强。如果γ大于零，则表示基金经理具有择时能力，由于(R m-R f) 2为非负数，故当证券市场上涨即(R m-R f)＞0时，基金的超额收益R p-R f会大于市场基准R m-R f；反之，当证券市场下跌即(R m-R f)＜0时，基金的超额收益R p-R f即下跌却会小于市场基准R m-R f下跌的幅度。
步骤S120，对每一候选因子进行回归计算，得到对应每一候选因子的相关系数、信息比率及三档索提诺比率。
多因子模型回归的对象可以为未来设定时间的索提诺比率，例如可以是未来半年的索提诺比率。索提诺比率是一种衡量投资组合相对表现的方法。与夏普比率有相似之处，但索提诺比率运用下档标准差而不是总标准差，以区别不利和有利的波动。和夏普比率类似，这一比率越高，表明基金承担相同单位下行风险能获得更高的超额回报率。
具体的，步骤S120进一步包括如图2所示的步骤S121～S128。
步骤S121，选择一组过去的时间点。
这一组过去的时间点可以是过去五年内每个月的1号，例如20110101、20110201、......、20161101、20161201等这5年共60个时间点。
步骤S122，计算所有基金在每个时间点上的所有候选因子的值。
具体的，可以是计算出每个基金在每个时间点上的基金规模、过去三年的年化收益率、过去三年的最大回撤、过去三年标准差、过去三年的下行标准差、过去三年的夏普比率、过去三年的索提诺比率、过去三年选股能力、过去三年择时能力、过去三年贝塔系数。
例如，在第一个时间点每个候选因子的值可以为数列factor1_list1、 factor2_list(1)、......、factor10_list(1)；在第二个时间点每个候选因子的值可以为数列factor1_list(2)、factor2_list(2)、......、factor10_list(2)；以此类推，在第60个时间点每个候选因子的值可以为数列factor1_list(60)、factor2_list(60)、......、factor10_list(60)。其中，每个数列中均包括所有基金在对应时间点的对应候选因子值。
步骤S123，计算所有基金相对于过去每一设定时间点在未来设定时间的索提诺比率。
索提诺比率的计算公式可以为：
Figure PCTCN2018078325-appb-000001
Figure PCTCN2018078325-appb-000002
其中，SoR为索提诺比率；R p-R f为基金的超额收益率；DD EX为下行标准差；R i为每月的收益率；n为时间点的数量。
具体的，可以是计算出相对于上述每一时间点未来半年的索提诺比率。例如，相对于时间点20110101的未来半年为20110701，那么，n就可以为6，R i为时间点20110101至时间点20110701内每个月的收益率；相对于时间点20161201的未来半年为20170601，那么，n就可以为66，R i为时间点20110101至时间点20170601内每个月的收益率。
对于每一只基金，任一时间点的候选因子值与该时间点未来半年的所提诺比率相对应，即时间点20110101的候选因子值、与时间点20110101未来半年20110701的索提诺比率是相对应的。
那么，对应每一时间点的索提诺比率为数列SoR_list(1)、SoR_list(2)、……、SoR_list(60)。其中，每个数列均中包括对应每只基金的索提诺比率。
步骤S124，分别将每一候选因子的值与对应的索提诺比率做回归计算，得到每一候选因子在每一时间点的相关系数。
相关系数的计算公式为：
Figure PCTCN2018078325-appb-000003
其中，ρ(x,y)为相关系数；Cov(x,y)为其中一个任意一个因子和一只基金的索提诺比率的协方差；
Figure PCTCN2018078325-appb-000004
为该因子的标准差，
Figure PCTCN2018078325-appb-000005
为该基金的索提诺比率的标准差。
具体的，可以是分别将每个候选因子值在每个时间点与对应的索提诺比率做回归计算。
例如，可以是根据在第一个时间点上第一个候选因子的值factor1_list(1)与索提诺比率SoR_list(1)做回归计算，得到对应第一个候选因子在每个时间点上的相关系数分别为factor1_ic(1)；根据在第二个时间点上第一个候选因子的值factor1_list(2)与索提诺比率SoR_list(2)做回归计算，得到对应第一个候选因子在每个时间点上的相关系数分别为factor1_ic(2)；……；根据在第n个时间点上第一个候选因子的值factor1_list(n)与索提诺比率SoR_list(n)做回归计算，得到对应第一个候选因子在每个时间点上的相关系数分别为factor1_ic(n)，其中，在本实施例中，1≤n≤60。
再根据在第一个时间点上第二个候选因子的值factor1_list(1)与索提诺比率SoR_list(1)做回归计算，得到对应第二个候选因子在每个时间点上的相关系数分别为factor1_ic(1)；根据在第二个时间点上第二个候选因子的值factor1_list(2)与索提诺比率SoR_list(2)做回归计算，得到对应第二个候选因子在每个时间点上的相关系数分别为factor1_ic(2)；……；根据在第n个时间点上第二个候选因子的值factor1_list(n)与索提诺比率SoR_list(n)做回归计算，得到对应第二个候选因子在每个时间点上的相关系数分别为factor1_ic(n)，其中，在本实施例中，1≤n≤60。以此类推，计算出每一候选因子在每一时间点的相关系数。
步骤S125，根据索提诺比率和候选因子的值，计算每一候选因子在每一时间点的三档索提诺比率。
具体的，可以是分别根据每一候选因子的值，将每一时间点的基金分 成三个组合；再计算对应每一候选因子的三个组合在每一时间点的索提诺比率的均值，作为每一候选因子在每一时间点对应的三档索提诺比率。
可以针对每一个候选因子在每一个时间点进行分析。在第一个时间点，将所有基金按照第一个候选因子的值进行从大到小的排序，再根据排序顺序将所有基金分成三个组合，计算每个组合中的所有基金的相对于第一时间点的索提诺比率的均值，分别为factor1_sortino1(1)、factor1_sortino2(1)、factor1_sortino3(1)，那么第一个候选因子在第一时间点的三档索提诺比率则为factor1_sortino1(1)、factor1_sortino2(1)、factor1_sortino3(1)。在第一个时间点，将所有基金按照第二个候选因子的值进行从大到小的排序，再根据排序顺序将所有基金分成三个组合，计算每个组合中的所有基金的相对于第一时间点的索提诺比率的均值，分别为factor2_sortino1(1)、factor2_sortino2(1)、factor2_sortino3(1)，那么第一个候选因子在第一时间点的三档索提诺比率则为factor2_sortino1(1)、factor2_sortino2(1)、factor2_sortino3(1)。以此类推，在第一个时间点，将所有基金按照第十个候选因子的值进行从大到小的排序，再根据排序顺序将所有基金分成三个组合，计算每个组合中的所有基金的相对于第一时间点的索提诺比率的均值，分别为factor10_sortino1(1)、factor10_sortino2(1)、factor10_sortino3(1)，那么第一个候选因子在第一时间点的三档索提诺比率则为factor10_sortino1(1)、factor10_sortino2(1)、factor10_sortino3(1)。
根据上述方法计算出在第n个时间点，将所有基金按照第一个候选因子的值进行从大到小的排序，再根据排序顺序将所有基金分成三个组合，计算每个组合中的所有基金的相对于第一时间点的索提诺比率的均值，分别为factor1_sortino1(n)、factor1_sortino2(n)、factor1_sortino3(n)，那么第一个候选因子在第一时间点的三档索提诺比率则为factor1_sortino1(n)、factor1_sortino2(n)、factor1_sortino3(n)。在第n个时间点，将所有基金按照第十个候选因子的值进行从大到小的排序，再根据排序顺序将所有基金分成三个组合，计算每个组合中的所有基金的 相对于第一时间点的索提诺比率的均值，分别为factor10_sortino1(n)、factor10_sortino2(n)、factor10_sortino3(n)，那么第一个候选因子在第一时间点的三档索提诺比率则为factor10_sortino1(n)、factor10_sortino2(n)、factor10_sortino3(n)。
这样，就得到了每一候选因子在每一时间点的三档索提诺比率。
进一步地，步骤S125的执行顺序可以是在步骤S123执行完成之后、在步骤S128执行之前。
步骤S126，计算每一候选因子在每一时间点的相关系数在所有时间点的均值，得到对应每一候选因子的相关系数。
具体的，计算第一个候选因子在所有时间点的相关系数的均值，则具体可以是计算factor1_ic(1)、factor1_ic(2)、……、factor1_ic(60)的平均值，作为对应第一个候选因子的相关系数。
计算第二个候选因子在所有时间点的相关系数的均值，则具体可以是计算factor2_ic(1)、factor2_ic(2)、……、factor2_ic(60)的平均值，作为对应第二个候选因子的相关系数。
以此类推，计算第十个候选因子在所有时间点的相关系数的均值，则具体可以是计算factor10_ic(1)、factor10_ic(2)、……、factor10_ic(60)的平均值，作为对应第十个候选因子的相关系数。
步骤S127，根据每一候选因子在每一时间点的相关系数计算对应每一候选因子的信息比率。
信息比率的计算公式为：
Figure PCTCN2018078325-appb-000006
其中，IR为信息比率；E(ρ(x,y))为相关系数的均值；σ ρ(x,y)为相关系数的标准差。
具体的，可以是计算第一个候选因子在所有时间点的相关系数的均值，即factor1_ic(1)、factor1_ic(2)、……、factor1_ic(60)的平均值；再计算出第一个候选因子在所有时间点的相关系数的标准差，即factor1_ic(1)、factor1_ic(2)、……、factor1_ic(60)的标准差，再计 算平均值和标准差的比得到对应第一个候选因子的信息比率factor1_ir。
计算第二个候选因子在所有时间点的相关系数的均值，即factor2_ic(1)、factor2_ic(2)、……、factor2_ic(60)的平均值；再计算出第二个候选因子在所有时间点的相关系数的标准差，即factor2_ic(1)、factor2_ic(2)、……、factor2_ic(60)的标准差，再计算平均值和标准差的比得到对应第二个候选因子的信息比率factor2_ir。
以此类推，计算第十个候选因子在所有时间点的相关系数的均值，即factor10_ic(1)、factor10_ic(2)、……、factor10_ic(60)的平均值；再计算出第十个候选因子在所有时间点的相关系数的标准差，即factor10_ic(1)、factor10_ic(2)、……、factor10_ic(60)的标准差，再计算平均值和标准差的比得到对应第十个候选因子的信息比率factor10_ir。
步骤S128，计算每一候选因子在每一时间点对应的三档索提诺比率在所有时间点的均值，得到对应每一候选因子的三档索提诺比率。
具体的，计算第一个候选因子在所有时间点的三档索提诺比率，即计算factor1_sortino1(1)、factor1_sortino1(2)、……、factor1_sortino1(60)的平均值得到factor1_sortino1_avg，计算factor1_sortino2(1)、factor1_sortino2(2)、……、factor1_sortino2(60)的平均值得到factor1_sortino2_avg，计算factor1_sortino3(1)、factor1_sortino3(2)、……、factor1_sortino3(60)的平均值得到factor1_sortino3_avg，那么，对应第一个候选因子的三档索提诺比率则为factor1_sortino1_avg、factor1_sortino2_avg、factor1_sortino3_avg。
计算第二个候选因子在所有时间点的三档索提诺比率，即计算factor2_sortino1(1)、factor2_sortino1(2)、……、factor2_sortino1(60)的平均值得到factor2_sortino1_avg，计算factor2_sortino2(1)、factor2_sortino2(2)、……、factor2_sortino2(60)的平均值得到factor2_sortino2_avg，计算factor2_sortino3(1)、factor2_sortino3(2)、……、factor2_sortino3(60)的平均值得到 factor2_sortino3_avg，那么，对应第二个候选因子的三档索提诺比率则为factor2_sortino1_avg、factor2_sortino2_avg、factor2_sortino3_avg。
以此类推，计算第十个候选因子在所有时间点的三档索提诺比率，即计算factor10_sortino1(1)、factor10_sortino1(2)、……、factor10_sortino1(60)的平均值得到factor10_sortino1_avg，计算factor10_sortino2(1)、factor10_sortino2(2)、……、factor10_sortino2(60)的平均值得到factor10_sortino2_avg，计算factor10_sortino3(1)、factor10_sortino3(2)、……、factor10_sortino3(60)的平均值得到factor10_sortino3_avg，那么，对应第十个候选因子的三档索提诺比率则为factor10_sortino1_avg、factor10_sortino2_avg、factor10_sortino3_avg。
步骤S130，根据每一候选因子对应的相关系数、信息比率及三档索提诺比率确定有效因子。
进一步地，有效因子筛选规则可以依据相关系数、三档索提诺比率的单调性、因子间的共线性、信息比率等统计指标综合判定。
在本申请的一个具体实施例中，可以是选择相关系数的绝对值大于第一设定值、三档索提诺比率具有单调性、且信息比率大于第二设定值的候选因子作为有效因子。
具体的，可以选择相关系数的均值的绝对值大于0.1的候选因子作为有效因子。
也可以选择三档索提诺比率具有单调性，并且首档和末档差距在10％以上的候选因子作为有效因子。以对应第十个候选因子的三档索提诺比率factor10_sortino1_avg、factor10_sortino2_avg、factor10_sortino3_avg为例，factor10_sortino1_avg、factor10_sortino2_avg、factor10_sortino3_avg为递增或者递减的顺序、且factor10_sortino1_avgfactor10_sortino3_avg之间的差距在10％以上时，选择第十个候选因子作为有效因子。
还可以是信息比率绝对值大于第二设定值的候选因子作为有效因子。
确定的有效因子例如可以包括基金规模、过去三年最大回撤、过去三年夏普比率、过去三年索提诺比率、过去三年选股能力。
步骤S140，根据有效因子、及有效因子对应的信息比率，从所有基金中选择投资标的。
具体的，根据每一基金每一有效因子的值、及每一有效因子对应的信息比率，计算每一基金的综合得分。
选择综合得分最高的设定数量的基金，作为投资标的。
计算每只基金综合得分的方法可以是计算出每只基金的所有效因子的值，再乘以对应有效因子的信息比率，最后累加，得到各基金的综合得分。
可以选择综合得分高的基金，作为投资标的。例如还可以是选择综合得分最大的N个股票类基金、N个债券类基金、N个货币类基金和N个黄金类基金作为投资标的。
综合得分的计算公式可以为：
Figure PCTCN2018078325-appb-000007
其中，FactorX i为每只基金的第i个有效因子值，
Figure PCTCN2018078325-appb-000008
为第i个有效因子对应的信息比率。
这样，根据本申请的方法选择的投资标的，就可以在显著降低风险的同时追求稳健的收益。
与上述方法相对应的，本申请还提供了一种投资标的的选择装置。图3为根据本申请一种投资标的的选择装置的一种实施结构的方框原理图。
根据图3所示，该选择装置还包括候选因子确定模块310、回归计算模块320、有效因子确定模块330和投资标的选择模块340，该候选因子确定模块310用于确定候选因子；该回归计算模块320用于对每一候选因子进行回归计算，得到对应每一候选因子的相关系数、信息比率及三档索提诺比率；该有效因子确定模块330用于根据每一候选因子对应的相关系数、信息比率及三档索提诺比率确定有效因子；该投资标的选择模块340用于根据有效因子、及有效因子对应的信息比率，从所有基金选择投资标的。
进一步地，如图4所示，回归计算模块320包括时间点选择单元321、 候选因子计算单元322、所提诺比率计算单元323、第一相关系数计算单元324、第一三档所提诺比率计算单元325、第二相关系数计算单元326、信息比率计算单元327和第二三档所提诺比率计算单元328。
上述时间点选择单元321用于选择一组过去的时间点。
上述候选因子计算单元322用于计算所有基金在每个时间点上的所有候选因子的值。
上述所提诺比率计算单元323用于计算所有基金相对于过去每一设定时间点在未来设定时间的索提诺比率。
上述第一相关系数计算单元324用于分别将每一候选因子的值与对应的索提诺比率做回归计算，得到每一候选因子在每一时间点的相关系数。
上述第一三档所提诺比率计算单元325用于根据索提诺比率和候选因子的值，计算每一候选因子在每一时间点的三档索提诺比率。
上述第二相关系数计算单元326用于计算每一候选因子在每一时间点的相关系数在所有时间点的均值，得到对应每一候选因子的相关系数。
上述信息比率计算单元327用于根据每一候选因子在每一时间点的相关系数计算对应每一候选因子的信息比率。
上述第二三档所提诺比率计算单元328用于计算每一候选因子在每一时间点对应的三档索提诺比率在所有时间点的均值，得到对应每一候选因子的三档索提诺比率。
在此基础上，第一三档所提诺比率计算单元325进一步包括分组子单元和计算子单元，该分组子单元，用于分别根据每一候选因子的值，将每一时间点的基金分成三个投资组合；该计算子单元，用于计算对应每一候选因子的三个投资组合在每一时间点的索提诺比率的均值，作为每一候选因子在每一时间点对应的三档索提诺比率。
具体的，有效因子确定模块330还用于选择相关系数的绝对值大于第一设定值、三档索提诺比率具有单调性、且信息比率大于第二设定值的候选因子作为有效因子。
投资标的选择模块340进一步包括得分计算单元和选择单元，该得分计算单元，用于根据每一基金每一有效因子的值、及每一有效因子对应的 信息比率，计算每一基金的综合得分；该选择单元，用于选择综合得分最高的设定数量的基金，作为投资标的。
本申请还提供了一种计算机可读存储介质，所述计算机可读存储介质存储有计算机可执行指令，所述计算机可执行指令用于使所述计算机执行前述的选择方法。
上述各实施例主要重点描述与其他实施例的不同之处，但本领域技术人员应当清楚的是，上述各实施例可以根据需要单独使用或者相互结合使用。
本说明书中的各个实施例均采用递进的方式描述，各个实施例之间相同相似的部分相互参见即可，每个实施例重点说明的都是与其他实施例的不同之处，但本领域技术人员应当清楚的是，上述各实施例可以根据需要单独使用或者相互结合使用。另外，对于装置实施例而言，由于其是与方法实施例相对应，所以描述得比较简单，相关之处参见方法实施例的对应部分的说明即可。以上所描述的系统实施例仅仅是示意性的，其中作为分离部件说明的模块可以是或者也可以不是物理上分开的。
本申请可以是装置、方法和/或计算机程序产品。计算机程序产品可以包括计算机可读存储介质，其上载有用于使处理器实现本申请的各个方面的计算机可读程序指令。
计算机可读存储介质可以是可以保持和存储由指令执行设备使用的指令的有形设备。计算机可读存储介质例如可以是――但不限于――电存储设备、磁存储设备、光存储设备、电磁存储设备、半导体存储设备或者上述的任意合适的组合。计算机可读存储介质的更具体的例子(非穷举的列表)包括：便携式计算机盘、硬盘、随机存取存储器(RAM)、只读存储器(ROM)、可擦式可编程只读存储器(EPROM或闪存)、静态随机存取存储器(SRAM)、便携式压缩盘只读存储器(CD-ROM)、数字多功能盘(DVD)、记忆棒、软盘、机械编码设备、例如其上存储有指令的打孔卡或凹槽内凸起结构、以及上述的任意合适的组合。这里所使用的计算机可读存储介质不被解释为瞬时信号本身，诸如无线电波或者其他自由传播的电磁波、通 过波导或其他传输媒介传播的电磁波(例如，通过光纤电缆的光脉冲)、或者通过电线传输的电信号。
这里所描述的计算机可读程序指令可以从计算机可读存储介质下载到各个计算/处理设备，或者通过网络、例如因特网、局域网、广域网和/或无线网下载到外部计算机或外部存储设备。网络可以包括铜传输电缆、光纤传输、无线传输、路由器、防火墙、交换机、网关计算机和/或边缘服务器。每个计算/处理设备中的网络适配卡或者网络接口从网络接收计算机可读程序指令，并转发该计算机可读程序指令，以供存储在各个计算/处理设备中的计算机可读存储介质中。
用于执行本申请操作的计算机程序指令可以是汇编指令、指令集架构(ISA)指令、机器指令、机器相关指令、微代码、固件指令、状态设置数据、或者以一种或多种编程语言的任意组合编写的源代码或目标代码，所述编程语言包括面向对象的编程语言—诸如Smalltalk、C++等，以及常规的过程式编程语言—诸如“C”语言或类似的编程语言。计算机可读程序指令可以完全地在用户计算机上执行、部分地在用户计算机上执行、作为一个独立的软件包执行、部分在用户计算机上部分在远程计算机上执行、或者完全在远程计算机或服务器上执行。在涉及远程计算机的情形中，远程计算机可以通过任意种类的网络—包括局域网(LAN)或广域网(WAN)—连接到用户计算机，或者，可以连接到外部计算机(例如利用因特网服务提供商来通过因特网连接)。在一些实施例中，通过利用计算机可读程序指令的状态信息来个性化定制电子电路，例如可编程逻辑电路、现场可编程门阵列(FPGA)或可编程逻辑阵列(PLA)，该电子电路可以执行计算机可读程序指令，从而实现本申请的各个方面。
这里参照根据本申请实施例的方法、装置(系统)和计算机程序产品的流程图和/或框图描述了本申请的各个方面。应当理解，流程图和/或框图的每个方框以及流程图和/或框图中各方框的组合，都可以由计算机可读程序指令实现。
这些计算机可读程序指令可以提供给通用计算机、专用计算机或其它可编程数据处理装置的处理器，从而生产出一种机器，使得这些指令在通 过计算机或其它可编程数据处理装置的处理器执行时，产生了实现流程图和/或框图中的一个或多个方框中规定的功能/动作的装置。也可以把这些计算机可读程序指令存储在计算机可读存储介质中，这些指令使得计算机、可编程数据处理装置和/或其他设备以特定方式工作，从而，存储有指令的计算机可读介质则包括一个制造品，其包括实现流程图和/或框图中的一个或多个方框中规定的功能/动作的各个方面的指令。
也可以把计算机可读程序指令加载到计算机、其它可编程数据处理装置、或其它设备上，使得在计算机、其它可编程数据处理装置或其它设备上执行一系列操作步骤，以产生计算机实现的过程，从而使得在计算机、其它可编程数据处理装置、或其它设备上执行的指令实现流程图和/或框图中的一个或多个方框中规定的功能/动作。
附图中的流程图和框图显示了根据本申请的多个实施例的系统、方法和计算机程序产品的可能实现的体系架构、功能和操作。在这点上，流程图或框图中的每个方框可以代表一个模块、程序段或指令的一部分，所述模块、程序段或指令的一部分包含一个或多个用于实现规定的逻辑功能的可执行指令。在有些作为替换的实现中，方框中所标注的功能也可以以不同于附图中所标注的顺序发生。例如，两个连续的方框实际上可以基本并行地执行，它们有时也可以按相反的顺序执行，这依所涉及的功能而定。也要注意的是，框图和/或流程图中的每个方框、以及框图和/或流程图中的方框的组合，可以用执行规定的功能或动作的专用的基于硬件的系统来实现，或者可以用专用硬件与计算机指令的组合来实现。对于本领域技术人员来说公知的是，通过硬件方式实现、通过软件方式实现以及通过软件和硬件结合的方式实现都是等价的。

Claims (14)

  1. 一种投资标的的选择方法，其特征在于，包括：
    确定候选因子；
    对每一候选因子进行回归计算，得到对应每一候选因子的相关系数、信息比率及三档索提诺比率；
    根据所述每一候选因子对应的相关系数、信息比率及三档索提诺比率确定有效因子；
    根据所述有效因子、及所述有效因子对应的信息比率，从所有基金选择投资标的。
  2. 根据权利要求1所述的选择方法，其特征在于，所述对每一候选因子进行回归计算，得到每一回归因子的相关系数、信息比率及三档索提诺比率包括：
    选择一组过去的时间点；
    计算所有基金在每个时间点上的所有候选因子的值；
    计算所有基金相对于过去每一设定时间点在未来设定时间的索提诺比率，所述所提诺比率的计算公式为：
    Figure PCTCN2018078325-appb-100001
    Figure PCTCN2018078325-appb-100002
    其中，SoR为索提诺比率；R p-R f为基金的超额收益率；DD EX为下行标准差；R i为每月的收益率；n为所述时间点的数量；
    分别将每一所述候选因子的值与对应的索提诺比率做回归计算，得到每一候选因子在每一时间点的相关系数，所述相关系数的计算公式为：
    Figure PCTCN2018078325-appb-100003
    其中，ρ(x,y)为任一候选因子在对应时间点的相关系数；Cov(x,y)为所述任一候选因子和任一基金的索提诺比率在对应时间点的协方差；
    Figure PCTCN2018078325-appb-100004
    为所述任一候选因子在对应时间点的标准差，
    Figure PCTCN2018078325-appb-100005
    为所述任一基金的索提诺比率在对应时间点的标准差；
    根据所述索提诺比率和所述候选因子的值，计算每一所述候选因子在每一时间点的三档索提诺比率；
    计算所述每一候选因子在每一时间点的相关系数在所有时间点的均值，得到对应每一候选因子的相关系数；
    根据所述每一候选因子在每一时间点的相关系数计算对应每一候选因子的信息比率，所述信息比率的计算公式为：
    Figure PCTCN2018078325-appb-100006
    其中，IR为对应所述任一候选因子的信息比率；E(ρ(x,y))为对应所述任一候选因子的所有相关系数的均值；σ ρ(x,y)为对应所述任一候选因子的所有相关系数的标准差；
    计算每一候选因子在每一时间点对应的三档索提诺比率在所有时间点的均值，得到对应每一候选因子的三档索提诺比率。
  3. 根据权利要求2所述的选择方法，其特征在于，所述根据所述索提诺比率和所述候选因子的值，计算每一所述候选因子在每一时间点的三档索提诺比率包括：
    分别根据每一所述候选因子的值，将每一所述时间点的基金分成三个投资组合；
    计算对应每一候选因子的三个投资组合在每一所述时间点的索提诺比率的均值，作为所述每一候选因子在每一时间点对应的三档索提诺比率。
  4. 根据权利要求1所述的选择方法，其特征在于，所述根据所有所述候选因子对应的相关系数、信息比率及三档索提诺比率确定有效因子包括：
    选择相关系数的绝对值大于第一设定值、三档索提诺比率具有单调性、且信息比率大于第二设定值的候选因子作为所述有效因子。
  5. 根据权利要求1所述的选择方法，其特征在于，所述根据所述有效因子、及所述有效因子对应的信息比率，选择投资标的包括：
    根据每一基金每一有效因子的值、及每一有效因子对应的信息比率，计算每一基金的综合得分，所述综合得分的计算公式为：
    Figure PCTCN2018078325-appb-100007
    Figure PCTCN2018078325-appb-100008
    其中，FactorX i为任一基金的第i个有效因子值，
    Figure PCTCN2018078325-appb-100009
    为第i个有效因子对应的信息比率；
    选择所述综合得分最高的设定数量的基金，作为所述投资标的。
  6. 一种投资标的的选择装置，其特征在于，包括：
    候选因子确定模块，用于确定候选因子；
    回归计算模块，用于对每一候选因子进行回归计算，得到对应每一候选因子的相关系数、信息比率及三档索提诺比率；
    有效因子确定模块，用于根据所述每一候选因子对应的相关系数、信息比率及三档索提诺比率确定有效因子；
    投资标的选择模块，用于根据所述有效因子、及所述有效因子对应的信息比率，从所有基金选择投资标的。
  7. 根据权利要求6所述的选择装置，其特征在于，所述回归计算模块包括：
    时间点选择单元，用于选择一组过去的时间点；
    候选因子计算单元，用于计算所有基金在每个时间点上的所有候选因子的值；
    所提诺比率计算单元，用于计算所有基金相对于过去每一设定时间点在未来设定时间的索提诺比率，所述所提诺比率的计算公式为：
    Figure PCTCN2018078325-appb-100010
    其中，SoR为索提诺比率；R p-R f为基金的超额收益率；DD EX为下行标准差；R i为每月的收益率；n为所述时间点的数量；
    第一相关系数计算单元，用于分别将每一所述候选因子的值与对应的索提诺比率做回归计算，得到每一候选因子在每一时间点的相关系数，所述相关系数的计算公式为：
    Figure PCTCN2018078325-appb-100011
    其中，ρ(x,y)为任一候选因子在对应时间点的相关系数；Cov(x,y)为所述任一候选因子和任一基金的索提诺比率在对应时间点的协方差；
    Figure PCTCN2018078325-appb-100012
    为所述任一候选因子在对应时间点的标准差，
    Figure PCTCN2018078325-appb-100013
    为所述任一基金的索提诺比率在对应时间点的标准差；
    第一三档所提诺比率计算单元，用于根据所述索提诺比率和所述候选因子的值，计算每一所述候选因子在每一时间点的三档索提诺比率；
    第二相关系数计算单元，用于计算所述每一候选因子在每一时间点的 相关系数在所有时间点的均值，得到对应每一候选因子的相关系数；
    信息比率计算单元，用于根据所述每一候选因子在每一时间点的相关系数计算对应每一候选因子的信息比率，所述信息比率的计算公式为：
    Figure PCTCN2018078325-appb-100014
    其中，IR为对应所述任一候选因子的信息比率；E(ρ(x,y))为对应所述任一候选因子的所有相关系数的均值；σ ρ(x,y)为对应所述任一候选因子的所有相关系数的标准差；
    第二三档所提诺比率计算单元，用于计算每一候选因子在每一时间点对应的三档索提诺比率在所有时间点的均值，得到对应每一候选因子的三档索提诺比率。
  8. 根据权利要求7所述的选择装置，其特征在于，所述第一三档所提诺比率计算单元包括：
    分组子单元，用于分别根据每一所述候选因子的值，将每一所述时间点的基金分成三个投资组合；
    计算子单元，用于计算对应每一候选因子的三个投资组合在每一所述时间点的索提诺比率的均值，作为所述每一候选因子在每一时间点对应的三档索提诺比率。
  9. 根据权利要求6所述的选择装置，其特征在于，所述投资标的选择模块包括：
    得分计算单元，用于根据每一基金每一有效因子的值、及每一有效因子对应的信息比率，计算每一基金的综合得分，所述综合得分的计算公式为：
    Figure PCTCN2018078325-appb-100015
    其中，FactorX i为任一基金的第i个有效因子值，
    Figure PCTCN2018078325-appb-100016
    为第i个有效因子对应的信息比率；
    选择单元，用于选择所述综合得分最高的设定数量的基金，作为所述投资标的。
  10. 一种计算机可读存储介质，其特征在于，所述计算机可读存储介质存储有计算机可执行指令，所述计算机可执行指令用于使所述计算机执行以下步骤：
    确定候选因子；
    对每一候选因子进行回归计算，得到对应每一候选因子的相关系数、信息比率及三档索提诺比率；
    根据所述每一候选因子对应的相关系数、信息比率及三档索提诺比率确定有效因子；
    根据所述有效因子、及所述有效因子对应的信息比率，从所有基金选择投资标的。
  11. 根据权利要求1所述的计算机可读存储介质，其特征在于，所述对每一候选因子进行回归计算，得到每一回归因子的相关系数、信息比率及三档索提诺比率包括：
    选择一组过去的时间点；
    计算所有基金在每个时间点上的所有候选因子的值；
    计算所有基金相对于过去每一设定时间点在未来设定时间的索提诺比率，所述所提诺比率的计算公式为：
    Figure PCTCN2018078325-appb-100017
    Figure PCTCN2018078325-appb-100018
    其中，SoR为索提诺比率；R p-R f为基金的超额收益率；DD EX为下行标准差；R i为每月的收益率；n为所述时间点的数量；
    分别将每一所述候选因子的值与对应的索提诺比率做回归计算，得到每一候选因子在每一时间点的相关系数，所述相关系数的计算公式为：
    Figure PCTCN2018078325-appb-100019
    其中，ρ(x,y)为任一候选因子在对应时间点的相关系数；Cov(x,y)为所述任一候选因子和任一基金的索提诺比率在对应时间点的协方差；
    Figure PCTCN2018078325-appb-100020
    为所述任一候选因子在对应时间点的标准差，
    Figure PCTCN2018078325-appb-100021
    为所述任一基金的索提诺比率在对应时间点的标准差；
    根据所述索提诺比率和所述候选因子的值，计算每一所述候选因子在每一时间点的三档索提诺比率；
    计算所述每一候选因子在每一时间点的相关系数在所有时间点的均值，得到对应每一候选因子的相关系数；
    根据所述每一候选因子在每一时间点的相关系数计算对应每一候选因 子的信息比率，所述信息比率的计算公式为：
    Figure PCTCN2018078325-appb-100022
    其中，IR为对应所述任一候选因子的信息比率；E(ρ(x,y))为对应所述任一候选因子的所有相关系数的均值；σ ρ(x,y)为对应所述任一候选因子的所有相关系数的标准差；
    计算每一候选因子在每一时间点对应的三档索提诺比率在所有时间点的均值，得到对应每一候选因子的三档索提诺比率。
  12. 根据权利要求2所述的计算机可读存储介质，其特征在于，所述根据所述索提诺比率和所述候选因子的值，计算每一所述候选因子在每一时间点的三档索提诺比率包括：
    分别根据每一所述候选因子的值，将每一所述时间点的基金分成三个投资组合；
    计算对应每一候选因子的三个投资组合在每一所述时间点的索提诺比率的均值，作为所述每一候选因子在每一时间点对应的三档索提诺比率。
  13. 根据权利要求1所述的计算机可读存储介质，其特征在于，所述根据所有所述候选因子对应的相关系数、信息比率及三档索提诺比率确定有效因子包括：
    选择相关系数的绝对值大于第一设定值、三档索提诺比率具有单调性、且信息比率大于第二设定值的候选因子作为所述有效因子。
  14. 根据权利要求1所述的计算机可读存储介质，其特征在于，所述根据所述有效因子、及所述有效因子对应的信息比率，选择投资标的包括：
    根据每一基金每一有效因子的值、及每一有效因子对应的信息比率，计算每一基金的综合得分，所述综合得分的计算公式为：
    Figure PCTCN2018078325-appb-100023
    Figure PCTCN2018078325-appb-100024
    其中，FactorX i为任一基金的第i个有效因子值，
    Figure PCTCN2018078325-appb-100025
    为第i个有效因子对应的信息比率；
    选择所述综合得分最高的设定数量的基金，作为所述投资标的。
PCT/CN2018/078325 2017-10-26 2018-03-07 一种投资标的的选择方法、装置及计算机可读介质 Ceased WO2019080434A1 (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN201711029351.5A CN108510392A (zh) 2017-10-26 2017-10-26 一种投资标的的选择方法、装置及计算机可读介质
CN201711029351.5 2017-10-26

Publications (1)

Publication Number Publication Date
WO2019080434A1 true WO2019080434A1 (zh) 2019-05-02

Family

ID=63375314

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2018/078325 Ceased WO2019080434A1 (zh) 2017-10-26 2018-03-07 一种投资标的的选择方法、装置及计算机可读介质

Country Status (2)

Country Link
CN (1) CN108510392A (zh)
WO (1) WO2019080434A1 (zh)

Families Citing this family (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN109697205A (zh) * 2018-12-14 2019-04-30 北京向上一心科技有限公司 数据排序方法、数据展示方法、装置、设备和存储介质
WO2025236216A1 (en) * 2024-05-15 2025-11-20 Zhao Shengli System and method for measuring performance of investment

Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US8751357B1 (en) * 2011-02-23 2014-06-10 University Court Of The University Of St Andrews Investment performance measurement
CN106462898A (zh) * 2014-01-23 2017-02-22 洛卡有限公司 投资证券的分层综合投资组合
CN106651578A (zh) * 2016-11-25 2017-05-10 北京工商大学 一种股价走势预测方法和系统

Patent Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US8751357B1 (en) * 2011-02-23 2014-06-10 University Court Of The University Of St Andrews Investment performance measurement
CN106462898A (zh) * 2014-01-23 2017-02-22 洛卡有限公司 投资证券的分层综合投资组合
CN106651578A (zh) * 2016-11-25 2017-05-10 北京工商大学 一种股价走势预测方法和系统

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
XU, LIN ET AL.: "The Structure of Evaluation System and Empirical Analysis of Chinese Hedge Fund", JOURNAL OF BEIJING INSTITUTE OF TECHNOLOGY (SOCIAL SCIENCES EDITION, vol. 18, no. 3, 31 May 2016 (2016-05-31) *

Also Published As

Publication number Publication date
CN108510392A (zh) 2018-09-07

Similar Documents

Publication Publication Date Title
US12045747B2 (en) Talent platform exchange and recruiter matching system
Shahzad et al. Is Bitcoin a better safe-haven investment than gold and commodities?
US20120254063A1 (en) Researching exchange-listed products using sentiment
CN107391545B (zh) 一种对用户进行分类的方法、输入方法及装置
US20250005533A1 (en) Talent platform exchange and rating system
CN114090601B (zh) 一种数据筛选方法、装置、设备以及存储介质
Liang et al. A robust multivariate sign control chart for detecting shifts in covariance matrix under the elliptical directions distributions
WO2019080434A1 (zh) 一种投资标的的选择方法、装置及计算机可读介质
Jara-Ferreira et al. The metallicity gradients of star-forming regions store information of the assembly history of galaxies
Akyildirim et al. Connectedness of cryptocurrency-related stocks and the cryptocurrency market: Evidence from the United States
Gong et al. Forecasting stock volatility with a large set of predictors: A new forecast combination method
EP2992494A1 (en) Calculating a probability of a business being delinquent
Sivri et al. An adaptive and enhanced framework for daily stock market prediction using feature selection and ensemble learning algorithms
Leung et al. Social-media sentiment, portfolio complexity, and stock returns
Berentsen et al. Modelling clusters of corporate defaults: Regime-switching models significantly reduce the contagion source
Tang et al. Predicting standardized absolute returns using rolling-sample textual modelling
WO2019134579A1 (zh) 投资标的的选择方法、电子装置及计算机可读存储介质
Mirashk et al. News Sentiment and Liquidity Risk Forecasting: Insights from Iranian Banks
CN107025494A (zh) 数据预测方法、理财推荐方法、装置以及终端设备
Yildirim et al. Key drivers of volatility in BIST100 firms using machine learning segmentation
US11941593B2 (en) Blockchain payment notification system
Kim Social media and analytics: A case study of tweets data
US11138664B1 (en) Identification of loss risk candidates for financial institutions
Du et al. Inversion of option prices for implied risk-neutral probability density functions: general theory and its applications to the natural gas market
US10546350B2 (en) Performance projection

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: 18869771

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

32PN Ep: public notification in the ep bulletin as address of the adressee cannot be established

Free format text: NOTING OF LOSS OF RIGHTS PURSUANT TO RULE 112(1) EPC (EPO FORM 1205A DATED 14/09/2020)

122 Ep: pct application non-entry in european phase

Ref document number: 18869771

Country of ref document: EP

Kind code of ref document: A1