[go: up one dir, main page]

WO2021224748A1 - Système et procédé de notation - Google Patents

Système et procédé de notation Download PDF

Info

Publication number
WO2021224748A1
WO2021224748A1 PCT/IB2021/053664 IB2021053664W WO2021224748A1 WO 2021224748 A1 WO2021224748 A1 WO 2021224748A1 IB 2021053664 W IB2021053664 W IB 2021053664W WO 2021224748 A1 WO2021224748 A1 WO 2021224748A1
Authority
WO
WIPO (PCT)
Prior art keywords
grading
data
market
condition
scenarios
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/IB2021/053664
Other languages
English (en)
Inventor
Rajesh Jaykrishan PATEL
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.)
Powerweave Heuristic Investment Technologies Private Ltd
Original Assignee
Powerweave Heuristic Investment Technologies Private 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 Powerweave Heuristic Investment Technologies Private Ltd filed Critical Powerweave Heuristic Investment Technologies Private Ltd
Publication of WO2021224748A1 publication Critical patent/WO2021224748A1/fr
Anticipated expiration legal-status Critical
Ceased legal-status Critical Current

Links

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
    • G06Q40/04—Trading; Exchange, e.g. stocks, commodities, derivatives or currency exchange

Definitions

  • the present subject matter relates generally to data information processing, and, particularly but not exclusively, to a method and system for grading.
  • security is financial asset of any kind which is tradable in the financial markets.
  • securities trading is done manually or by way of algorithms.
  • Algorithmic trading uses a computer program that follows a defined set of instructions (an algorithm) to place a trade.
  • the trade can generate profits at a speed and frequency that is impossible for a human trader.
  • the defined sets of instructions are based on timing, price, quantity, or any mathematical model.
  • algorithmic trading renders markets more liquid and trading more systematic by ruling out the impact of human emotions on trading activities.
  • the trading algorithms are typically tuned.
  • trading algorithm refinement and tuning technology relies on the Securities trader's personal market experience to ensure that the strategy performs well under varied market conditions. Additionally, the conventional systems are experiential and based on intuitive knowledge and beliefs, which does not have the precision and certainty of a data-driven process.
  • various embodiments herein may include one or more systems and methods for grading.
  • the method comprises obtaining, by a processor, a plurality of algorithm.
  • the algorithm comprises one or more computer readable instructions for execution of a trade of a security on a trading platform associated with a market.
  • the method comprises obtaining, by the processor, a plurality of scenarios.
  • each of plurality of scenarios are indicative of one or more condition of the market.
  • each of the plurality of scenarios comprises a set of time series data.
  • the method comprises generating, by the processor, output data based on execution of each of the plurality of algorithm on the plurality of scenarios.
  • the output data comprises one or more of a return on investment (ROI), an alpha, a beta, a Calmar ratio, a Sharpe ratio and a maximum draw down.
  • the method comprises grading, by the process, the plurality of algorithm based on the output data and a grading methodology.
  • the system includes computer implemented system for grading, the system comprises a memory, a processor coupled with the memory, and an execution module and a grading module coupled with the processor. Further, the execution module is configured to obtain a plurality of algorithm and obtain a plurality of scenarios.
  • the algorithm comprises one or more computer readable instructions for execution of a trade of a security on a trading platform associated with a market.
  • each of plurality of scenarios are indicative of one or more condition of the market, and each of the plurality of scenarios comprises a set of time series data.
  • the execution module is configured to generate output data based on execution of each of the plurality of algorithm on the plurality of scenarios.
  • the output data comprises one or more of a return on investment (ROI), an alpha, a beta, a Calmar ratio, a Sharpe ratio and a maximum draw down.
  • the grading module is configured to configured to grade the plurality of algorithm based on the output data and a grading methodology.
  • Figure 1A illustrates a block diagram depicting a network implementation of grading system, according to an exemplary implementation of the present subject matter.
  • Figure IB illustrates a block diagram depicting the computer implemented grading system, according to an exemplary implementation of the present subject matter.
  • Figure 2 illustrates a method for grading, according to an exemplary implementation of the present subject matter.
  • any block diagrams herein represent conceptual views of illustrative systems embodying the principles of the method and system for grading.
  • any flowcharts, flow diagrams, and the like represent various processes which may be substantially represented in computer readable medium and so executed by a computer or processor, whether or not such computer or processor is explicitly shown.
  • the present disclosure will be described in the context of the method and system for grading, one of ordinary skill in the art will readily recognize that the method and system for grading can be utilized in any situation where there is need to provide the recommendations to the user in real- time by way of grading thereby optimizing resources, such as IT infrastructure, computing power, utilization for obtaining the best outcome.
  • resources such as IT infrastructure, computing power, utilization for obtaining the best outcome.
  • the present disclosure is not intended to be limited to the embodiments illustrated but is to be accorded the widest scope consistent with the principles and features described herein.
  • references to "one embodiment” or “an embodiment” mean that a particular feature, structure, characteristic, or function described in connection with the embodiment is included in at least one embodiment of the method and system for grading.
  • the appearances of the phrase “in one embodiment” in various places in the specification are not necessarily all referring to the same embodiment.
  • the present subject matter discloses grading.
  • a plurality of algorithm and a plurality of scenario are obtained.
  • the algorithm comprises one or more computer readable instructions for execution of a trade of a security on a trading platform associated with a market.
  • each of plurality of scenarios are indicative of one or more condition of the market and each of the plurality of scenarios comprises a set of time series data.
  • the plurality of scenarios comprises one or more of an uptrend high volatility condition, an uptrend low volatility condition, a downtrend high volatility condition, a downtrend low volatility condition, a sideways high volatility condition, a sideways low volatility condition, a market crash condition and a mixed market condition.
  • the set of time series data comprises at least one time series selected based on historic data, and at least one time series generated based on synthetic data
  • a set of instructions in a natural language are received; and plurality of algorithm are generated based on the set of instructions.
  • a security and associated historical data is selected and a move size and move direction for various time period is computed based on a difference between an open price and close price of the security.
  • an average true range (ATR) and normalized ATR is computed.
  • ATR is indicative of the volatility of the market.
  • a slope of a best fit linear regression line using least squares method on price data is computed.
  • one or more time series data from historic market data is selected based on the move size, the move direction, normalized ATR and slope.
  • one or more synthetic time series data not from historic market data is generated based on the move size, the move direction, normalized ATR and slope.
  • output data is generated based on execution of each of the plurality of algorithm on the plurality of scenarios.
  • the output data comprises one or more of a return on investment (ROI), an alpha, a beta, a Calmar ratio, a Sharpe ratio and a maximum draw down.
  • the plurality of algorithm is graded based on the output data and a grading methodology.
  • the grading methodology comprises computing median of the Calmar ratio for a combination of the plurality of scenarios and grading the plurality of algorithm based on
  • Figure 1A illustrates a network implementation of a computer implemented grading system (102), hear in after also referred as system (102), and Figure IB illustrates the grading system (102), according to an exemplary implementation of the present subject matter.
  • the computer implemented system (102) includes a network (104) a plurality of user devices 106 (106a, 106b, 106c, 106d, 106e), a database (108), a processor (112), I/O interfaces (114), a memory (110), a plurality of modules (116), and plurality of data (118).
  • the network (104) interconnects the user devices (106) and the database (108) with the grading system (102).
  • the network (104) includes wired and wireless networks.
  • Examples of the wired networks include a Wide Area Network (WAN) or a Local Area Network (LAN), a client-server network, a peer-to-peer network, and so forth.
  • Examples of the wireless networks include Wi-Li, a Global System for Mobile communications (GSM) network, and a General Packet Radio Service (GPRS) network, an enhanced data GSM environment (EDGE) network, 802.5 communication networks, Code Division Multiple Access (CDMA) networks, or Bluetooth networks.
  • GSM Global System for Mobile communications
  • GPRS General Packet Radio Service
  • EDGE enhanced data GSM environment
  • CDMA Code Division Multiple Access
  • the database 108 may be implemented as enterprise database, remote database, local database, and the like.
  • the database (108) may be located within the vicinity of the grading system (102) or may be located at different geographic locations as compared to that of the grading system (102). Further, the database (108) may themselves be located either within the vicinity of each other, or may be located at different geographic locations. Furthermore, the database (108) may be implemented inside the grading system (102) and the database (108) may be implemented as a single database.
  • the grading system (102) includes one or more processors (112).
  • the processor (112) may be implemented as one or more microprocessors, microcomputers, microcontrollers, digital signal processors, central processing units, state machines, logic circuitries, and/or any devices that manipulate signals based on operational instructions.
  • the at least one processor (112) is configured to fetch and execute computer-readable instructions stored in the memory (110).
  • the I/O interface (114) may include a variety of software and hardware interfaces, for example, a web interface, a graphical user interface, and the like. The I/O interface (114) may allow the grading system (102) to interact with a user directly or through the user devices (106).
  • the 1/ O interface (114) may enable the grading system (102) to communicate with other user devices or computing devices, such as web servers and external data servers (not shown).
  • the I/O interface (114) can facilitate multiple communications within a wide variety of networks and protocol types, including wired networks, for example, LAN, cable, etc., and wireless networks, such as WLAN, cellular, or satellite.
  • the I/O interface (114) may include one or more ports for connecting a number of devices to one another or to another server.
  • the memory (110) may be coupled to the processor (112).
  • the memory (110) can include any computer-readable medium known in the art including, for example, volatile memory, such as static random access memory (SRAM) and dynamic random access memory (DRAM), and/or non-volatile memory, such as read only memory (ROM), erasable programmable ROM, flash memories, hard disks, optical disks, and magnetic tapes.
  • volatile memory such as static random access memory (SRAM) and dynamic random access memory (DRAM)
  • non-volatile memory such as read only memory (ROM), erasable programmable ROM, flash memories, hard disks, optical disks, and magnetic tapes.
  • ROM read only memory
  • erasable programmable ROM erasable programmable ROM
  • flash memories hard disks
  • optical disks optical disks
  • magnetic tapes magnetic tapes
  • the grading system (102) includes modules (116).
  • the modules (116) include routines, programs, objects, components, data structures, etc., which perform particular tasks or implement particular abstract data types.
  • the module (116) includes a pre processing module (120), an execution module (124) and a grading module (126) and other modules (128).
  • the other modules (128) may include programs or coded instructions that supplement applications and functions of the grading system (102).
  • the data (118) amongst other things, serves as a repository for storing data processed, received, and generated by one or more of the modules.
  • the data (118) includes a pre- processed data (130 ), system data (132) and other data (134).
  • a user may use the device 104 to access the system (102) via the I/O interface.
  • the user may register themselves using the 1/ O interface in order to use the system 102.
  • the user may access the 1/ O interface of the system 102 for obtaining recommendations and grading .
  • the pre-processing module (120) may receive a set of instructions in a natural language and generate plurality of algorithm based on the set of instructions. Upon generating, the pre processing module (120) may select one or more security and multiple time series corresponding to each of the security for a plurality of scenarios. In embodiment, the pre-processing module (120) may classify time-series historical data for securities into clusters, such as year-based cluster, and then select, thereby reducing the time for selection.
  • each of plurality of scenarios are indicative of one or more condition of the market, such as an uptrend high volatility condition, an uptrend low volatility condition, a downtrend high volatility condition, a downtrend low volatility condition, a sideways high volatility condition, a sideways low volatility condition, a market crash condition and a mixed market condition.
  • condition of the market such as an uptrend high volatility condition, an uptrend low volatility condition, a downtrend high volatility condition, a downtrend low volatility condition, a sideways high volatility condition, a sideways low volatility condition, a market crash condition and a mixed market condition.
  • the pre-processing module (120) may compute a move size and move direction based on a difference between an open price and close price of the security and compute an average true range (ATR).
  • ATR is indicative of the volatility of the market.
  • the normalized ATR may be computed.
  • the normalized ATR Value signifies high volatility with all values above .025 and low volatility with values below .025. Further, the normalized ATR using equation 1
  • the pre-processing module (120) may compute a best fit linear regression line using least squares method on price data.
  • the pre-processing module (120) may select one or more time series data from historic market data based on the move size, the move direction, a slope and one of ATR or normalized ATR. Table 1 illustrates the section criteria. Additionally, the pre-processing module (120) may generate one or more synthetic time series data not from historic market data based on the move size, the move direction, a slope and one of ATR or normalized ATR. In one example, synthetic time series data may be understood as data that is artificially created, random and arbitrary within boundary condition of the move size, the move direction, a slope and one of ATR or normalized ATR and table 1 and has no historic reference. In all in example, 4 time series data from historical and 1 no historical (synthetic) time series data may be selected and generated respectively for each of the 8 scenarios. Further, the pre-processing module (120) may store all data in pre-processed data (130).
  • the execution module (124) may obtain a plurality of algorithm, and obtain a plurality of scenarios and store in system data (132).
  • each of the plurality of scenarios comprises a set of time series data.
  • the execution module (124) may generate output data based on execution of each of the plurality of algorithm on the plurality of scenarios.
  • the output data comprises one or more of a return on investment (ROI), an alpha, a beta, a Calmar ratio, a Sharpe ratio and a maximum draw down.
  • the grading module (126) may grade the plurality of algorithm based on the output data and a grading methodology.
  • the grading methodology comprises computing median of the Calmar ratio for a combination of the plurality of scenarios, also referred to as categories.
  • the Calmar ratio is a comparison of the average annual compounded rate of return and the maximum drawdown risk of a trading strategy, portfolio or a fund. The lower the Calmar ratio, the worse algorithm performs on a risk- adjusted basis over the specified time period; the higher the Calmar ratio, the better algorithm performs.
  • the output data against scenario collected from above process is downloaded and a median value of Calmar Ratio in respective category is determined.
  • the plurality of algorithm is graded based on the median value of Calmar Ratio determined for each of the plurality of algorithm per category.
  • the categories may be as illustrated in the table 2. In on example, a median of a Sharpe ratio obtained from the output, may be determined for each of the plurality of algorithm per category and further utilized for grading individually or in combination with Calmar ratio
  • the grading module (126) may fine tune the algorithm based on the grading and output data and to ensure the strategy works as expected under all market conditions.
  • the grading module (126) may Automatically modify parameters associated with trading strategies based on the output data and grading for optimized working for various scenarios.
  • the grading module (126) may analyze the plurality of algorithm by holding a subset of parameters of the plurality of algorithm constant and view performance of the plurality of algorithm based on grading, thereby identifying and modify the critical parameter for optimized performance.
  • the grading module (126) may recommend the algorithm in turn the trading strategy to be utilized in real time from plurality of graded algorithms, to be utilized the current market condition in real time.
  • the grading module (126) may obtain Realtime market data, and compare the market data with time series data in the plurality of scenarios. Further, based on the comparison the grading module (126) may identify the current market scenario and identify from the graded algorithm the best suited algorithm to work in the current market scenario.
  • FIG. 2 a flowchart (200) of a method grading, according to an exemplary implementation of the present subject matter.
  • the method 200 may be described in the general context of computer executable instructions.
  • computer executable instructions can include routines, programs, objects, components, data structures, procedures, modules, functions, etc., that perform particular functions or implement particular abstract data types.
  • the method 200 may be practiced in a distributed computing environment where functions are performed by remote processing devices that are linked through a communications network.
  • computer executable instructions may be located in both local and remote computer storage media, including memory storage devices.
  • the order in which the method 200 is described is not intended to be construed as a limitation, and any number of the described method blocks can be combined in any order to implement the method 200 or alternate methods. Additionally, individual blocks may be deleted from the method 200 without departing from the spirit and scope of the disclosure described herein. Furthermore, the method can be implemented in any suitable hardware, software, firmware, or combination thereof. However, for ease of explanation, in the embodiments described below, the method 200 may be considered to be implemented in the above described in the system 102.
  • a plurality of algorithm is obtained.
  • the execution module (124) may obtain the plurality of algorithm and store in system data (132).
  • a plurality of scenarios is obtained.
  • the execution module (124) may obtain the plurality of scenarios and store in system data (132).
  • output data may be generated based on execution of each of the plurality of algorithm on the plurality of scenarios.
  • the execution module (124) may generate the output data and store in system data (132).
  • the plurality of algorithm may be graded based on the output data and a grading methodology.
  • the grading module (126) may grade the plurality of algorithm and store in system data (132).
  • Some embodiments of the system and the method enable selection of pre-defined market scenarios from financial market data.
  • Some embodiments of the system and the method enable manufacture of synthetic market data to conform to various market conditions.
  • Some embodiments of the system and the method enable categorization of market scenarios into hierarchical levels.
  • Some embodiments of the system and the method enable selection of financial metrics to judge a strategy under each market scenario and its aggregation to decide an overall score.
  • Some embodiments of the system and the method enable automatic parameter tuning of trading strategies [0047] Some embodiments of the system and the method enable clustering of historical price time series of securities
  • Some embodiments of the system and the method enable automatic scenario-based grading of algorithmic trading strategies
  • Some embodiments of the system and the method enable multi- instrument, Multi- Asset Class and Multi-Time Frequency Security Analysis and Execution
  • Exemplary embodiments and features discussed above may provide certain advantage. Some of the advantages may comprise illustrating the user on the quality of the trading strategies.
  • the gradation of algorithm and the trading strategies helps a securities trader to observe how the strategy works under each market condition and fine tune the parameters of the strategy to ensure that it performs well under all market conditions and is not skewed towards any particular market condition.
  • the gradation of algorithm and the trading strategies enables a user to prepare different strategies for different market condition and apply the strategies selectively. Further, this prevent financial losses that may be faced when the financial market abruptly changes character. Also, it helps to discover the correct balance of risk and reward for each of trading strategy and the financial portfolio.
  • system and method help adopt a data-driven systematic approach leading to novel trading and trade execution ideas and sharp reduction in manual effort and errors.
  • the system and method enable grading of any set of algorithms for a diverse variety of financial market conditions.
  • the clustering of historical data of securities into a small set of self-similar groups facilitates the faster fine tuning of trading algorithm parameters.
  • automatic parameter tuning of trading strategies by the system will save significant manual labor of the trader/ strategy designer and lead to reduction of manual errors.
  • the system (102) may generate plurality of algorithm based on the set of instructions. Upon generating, the system (102) may select one or more security and multiple time series corresponding to each of the security for a plurality of scenarios. In embodiment, the system (102) may classify time-series historical data for securities into clusters, such as year-based cluster, and then select, thereby reducing the time for selection.
  • each of plurality of scenarios are indicative of one or more condition of the market, such as an uptrend high volatility condition, an uptrend low volatility condition, a downtrend high volatility condition, a downtrend low volatility condition, a sideways high volatility condition, a sideways low volatility condition, a market crash condition and a mixed market condition.
  • the system (102) may compute a move size and move direction based on a difference between an open price and close price of the security and compute an average true range (ATR).
  • ATR is indicative of the volatility of the market.
  • the normalized ATR may be computed.
  • the normalized ATR Value signifies high volatility with all values above .025 and low volatility with values below .025.
  • the system (102) may compute a slope of a best fit linear regression line.
  • the linear regression line may be computed suing least squares method based on price data.
  • the system (102) may select one or more time series data from historic market data based on the move size, the move direction, and one of ATR or normalized ATR and the slope. Additionally, the system (102) may generate one or more synthetic time series data not from historic market data based on the move size, the move direction, and the ATR. Table 2 illustrates an example, of the selected time series from historic data.
  • Table 3 Selected time series from historical data
  • the system (102) may obtain a plurality of algorithm, and obtain a plurality of scenarios.
  • each of the plurality of scenarios comprises a set of time series data.
  • the system (102) may generate output data based on execution of each of the plurality of algorithm on the plurality of scenarios.
  • the output data comprises one or more of a return on investment (ROI), an alpha, a beta, a Calmar ratio, a Sharpe ratio and a maximum draw down.
  • ROI return on investment
  • the system (102) may grade the plurality of algorithm based on the output data and a grading methodology.
  • the grading methodology comprises computing median of the Calmar ratio for a combination of the plurality of scenarios, where the combination is referred to as categories.
  • a median of a Sharpe ratio computed based obtained from the output may be determined for each of the plurality of algorithm per category and further utilized for grading individually or in combination with Calmar ratio

Landscapes

  • Business, Economics & Management (AREA)
  • Accounting & Taxation (AREA)
  • Finance (AREA)
  • Engineering & Computer Science (AREA)
  • Development Economics (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

La présente invention concerne un procédé de notation mis en œuvre par ordinateur, comprenant les étapes d'obtention, par un processeur, d'une pluralité d'algorithmes et d'une pluralité de scénarios. Lors de l'obtention, le procédé comprend la génération, par le processeur, de données de sortie sur la base de l'exécution de chaque algorithme de la pluralité d'algorithmes sur la pluralité de scénarios. Dans un exemple, les données de sortie comprennent un ou plusieurs paramètres parmi un retour sur investissement (ROI), un alpha, un bêta, un ratio de Calmar, un ratio de Sharpe et un appel de fonds maximal. En outre, le procédé comprend la notation, par le processeur, de la pluralité d'algorithmes sur la base des données de sortie et d'une méthodologie de notation.
PCT/IB2021/053664 2020-05-03 2021-05-03 Système et procédé de notation Ceased WO2021224748A1 (fr)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
IN202021018868 2020-05-03
IN202021018868 2020-05-03

Publications (1)

Publication Number Publication Date
WO2021224748A1 true WO2021224748A1 (fr) 2021-11-11

Family

ID=78467897

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/IB2021/053664 Ceased WO2021224748A1 (fr) 2020-05-03 2021-05-03 Système et procédé de notation

Country Status (1)

Country Link
WO (1) WO2021224748A1 (fr)

Citations (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20140279695A1 (en) * 2013-03-15 2014-09-18 National Cheng Kung University System and method for rating and selecting models
US20180182037A1 (en) * 2014-03-28 2018-06-28 Jeffrey S. Lange Systems and methods for crowdsourcing of algorithmic forecasting

Patent Citations (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20140279695A1 (en) * 2013-03-15 2014-09-18 National Cheng Kung University System and method for rating and selecting models
US20180182037A1 (en) * 2014-03-28 2018-06-28 Jeffrey S. Lange Systems and methods for crowdsourcing of algorithmic forecasting

Similar Documents

Publication Publication Date Title
US10152752B2 (en) Methods and systems for computing trading strategies for use in portfolio management and computing associated probability distributions for use in option pricing
Dimov et al. Determinants of the incidence and scale of seed capital investments by venture capital firms
US8352347B2 (en) Investment classification and tracking system using diamond ratings
Garcia et al. Multiobjective approach to portfolio optimization in the light of the credibility theory
US11476669B2 (en) Method and system for building reinforcement learning (RL) based model for generating bids
US20140279697A1 (en) System and method for optimizing collateral management
US20230186385A1 (en) Computer-implemented system and method of facilitating artificial intelligence based lending strategies and business revenue management
Mysaka et al. Corporate financial performance and Tobin’s Q in dividend and growth investing
US20220027814A1 (en) Environmental, social, and governance (esg) performance trends
US20240070527A1 (en) Digital twin based evaluation, prediction, and forecasting for agricultural products
Degife et al. Efficient predictive model for determining critical factors affecting commodity price: The case of coffee in Ethiopian commodity exchange (ECX)
US12079752B2 (en) System and method for scenario-driven optimization of sourcing cost
CN112016765A (zh) 一种基于量化投资风险偏好的资产配置方法、装置及终端
Fiorini et al. A simple reinforcement learning algorithm for stock trading
WO2021224748A1 (fr) Système et procédé de notation
US12417498B2 (en) Methods for selecting assets suitable for trading consideration and visual presentations thereof
US12360820B1 (en) Dynamic multifactor resource distribution among coarse buckets
Naz et al. Impact of inventory leanness on financial performance of firms with mediating effect of risk-taking
CN119379222B (zh) 企业项目信息化管理方法、装置、系统以及存储介质
Shamsudin et al. Clustering Shariah-Compliant Stocks In The Construction Sector On Bursa Malaysia
Reis et al. Mavis: A multiagent value investing system
Lin et al. Optimal portfolio selection by CVaR based sharpe ratio--Genetic algorithm approach.
Surulivel et al. Leveraging Machine Learning to Analyze the Impact of ESG Criteria on Firm Valuation and Financial Performance: A Comparative Study
Wei et al. Building the model of artificial stock market based on JASA
Jiang et al. Optimized Artificial Intelligence and Econometric Model Empowered Virtual-Fiat Settled Price Prediction in Green Cryptocurrency Networks

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: 21800830

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 21800830

Country of ref document: EP

Kind code of ref document: A1