Financial data analysis system based on block chain

Abstract

The invention belongs to the technical field of financial data analysis, and provides a financial data analysis system based on a block chain, and the system comprises a data collection unit which is used for obtaining financial data; the data storage unit is used for storing the received financial data; the data processing unit preprocesses the collected financial data, predicts the market trend, evaluates the investment risk, and simulates different transaction strategies according to historical data and the current market condition; the security management unit adopts an encryption technology to ensure the security of a user identity, and limits the access and operation of sensitive data through permission setting; the interaction unit is used for generating visual charts and reports according to the data information, so that a user can query data through an interaction interface; the block chain technology is adopted, decentralized storage of the data is achieved through the distributed account book, each node stores a complete data copy, the processing capacity and speed of the system are improved, and the transparency of financial data analysis is improved.

Description

Technical Field

[0001] The present invention belongs to the technical field of financial data analysis, and specifically is a financial data analysis system based on blockchain. Background Art

[0002] In the context of today's rapid development of the digital economy, the generation and accumulation of financial data has shown an explosive growth trend. Traditional financial data analysis methods often rely on centralized databases and algorithms, leading to problems such as data leakage, tampering and opacity, limiting the credibility and security of data. In addition, participants in the financial field often face difficulties such as data silos and information asymmetry, which seriously affect decision-making efficiency and market competitiveness;

[0003] The emergence of blockchain technology provides a new approach to solving these problems. Blockchain is a distributed ledger technology that is decentralized, tamper-proof, transparent and traceable. This enables different financial institutions to share and collaboratively analyze data while ensuring data security and privacy. At the same time, smart contracts can automatically execute pre-set rules to improve the efficiency and reliability of financial transactions.

[0004] However, despite the huge potential of blockchain technology in financial data management, most applications are still in the exploratory stage and lack mature commercial implementation solutions.

[0005] To this end, technicians in this field have proposed a financial data analysis system based on blockchain. By introducing a more transparent and secure data processing mechanism, it can also effectively integrate data resources from all parties and provide accurate analysis support for financial decision-making, thereby promoting the digital transformation and innovative development of the financial industry. Summary of the invention

[0006] In order to solve the above technical problems, the present invention provides a financial data analysis system based on blockchain to solve the problems mentioned in the background technology.

[0007] A financial data analysis system based on blockchain, comprising:

[0008] A data collection unit, which is used to obtain financial data, includes a real-time transaction capture module, a historical data integration module, and an external data access module, and transmits the collected data to a data storage unit;

[0009] The data storage unit is used to store the received financial data and is provided with two storage modules, namely a blockchain storage module and a traditional database storage module, for separate storage;

[0010] The data processing unit pre-processes the collected financial data and uses machine learning and statistical models to predict market trends and assess investment risks. It also simulates different trading strategies based on historical data and current market conditions. It includes a risk assessment and prediction module and a trading strategy simulation module.

[0011] The security management unit uses encryption technology to ensure the security of user identities, prevent unauthorized access, and restrict access to and operations on sensitive data based on user roles and permission settings;

[0012] The interactive unit generates intuitive charts and reports based on the data information analyzed by the data processing unit, allowing users to query data through an interactive interface.

[0013] Preferably, the real-time transaction capture module receives transaction data in real time and monitors market conditions in real time through direct API connections with financial exchanges, banks and other financial institutions, and updates key indicators including but not limited to stock prices, exchange rates, and interest rates in real time, i.e., it is used to monitor and record real-time transaction data in the financial market.

[0014] Preferably, the historical data integration module collects and integrates historical transaction data from multiple financial databases and information sources, uses the APIs of financial data providers to obtain historical transaction data, and uses web crawler technology to capture historical transaction data displayed on web pages, and processes data sources from different financial databases, including but not limited to stock transaction data, bond transaction data, futures and options data, so as to unify the data formats from different data sources.

[0015] Preferably, the external data access module integrates non-transactional data, including but not limited to economic indicators and company financial reports, into the system through APIs or direct upload by third-party data providers, and supports upload and API access in multiple data formats, including but not limited to CSV, JSON, and XML formats. Apache Kafka is used to process real-time data streams, and ETL tools are used to extract, convert, and load batch uploaded data.

[0016] Preferably, the blockchain storage module uses a distributed ledger to store all verified transaction records and core information. Its blockchain network consists of multiple nodes, each of which maintains a complete copy of the ledger. The blockchain is constructed by each block containing transaction data and a hash value of the previous block to form a continuous chain structure. Each block in the blockchain generates a fixed-length string through a hash algorithm, which uniquely represents the content of the block. At the same time, the nodes in the blockchain network reach a consensus through a consensus mechanism, which includes proof of work and proof of equity.

[0017] Preferably, the traditional database storage module is used to store non-core but frequently queried data, including risk analysis data, customer management data, fraud detection data, personalized service data and algorithmic trading data; the risk analysis data is data generated by the risk assessment and prediction module; the customer management data includes the customer's basic information, transaction records, and behavioral data; the fraud detection data includes credit card transactions and account login records; the personalized service data is provided by financial institutions through analysis of customer historical data and behavior to provide personalized services and products; the algorithmic trading data is used to develop and test trading strategies through rapid query and processing of real-time market data and historical transaction data.

[0018] Preferably, the risk assessment and prediction module selects historical prices, trading volumes and technical indicators as features from the acquired data to construct a prediction model. The technical indicators include moving averages and relative strength indexes (RSI), and feature extraction is performed through principal component analysis, which is expressed as:

[0019] X new =W T X

[0020] Among them, X represents the original data set after centering, W represents the matrix composed of principal components, and W T represents the transposed matrix of W, X new Represents the dataset after dimensionality reduction, converting a set of correlated variables into a set of linearly uncorrelated variables through orthogonal transformation, so that each sample in the original dataset is projected onto the low-dimensional space defined by W through matrix multiplication;

[0021] A decision tree is used to build a prediction model. For each node, the feature that can minimize the uncertainty of the data set is selected as the division criterion. The information gain is expressed as:

[0022]

[0023] Where D represents the data set, a represents the feature, V represents the number of values ​​of feature a, and D v Represents the sub-dataset when feature a takes the vth value; divide the data set into multiple subsets according to the selected features and their thresholds, and recursively repeat the above process for each subset until the number of samples in the node is less than the preset minimum value or all samples belong to the same category; predict the market trend through the constructed prediction model, that is, by inputting new data into the tree, judging according to the rules of each node, and finally obtaining the prediction result.

[0024] Preferably, the trading strategy simulation module determines the assumptions of the trading strategy, including trend tracking and reversal trading, sets trading rules, including buying and selling conditions, position management, stop loss and take profit points, uses historical data and current market conditions, and simulates trading according to the set trading strategy, including generating trading signals, executing trading instructions, and updating the value of the investment portfolio. It also performs historical backtesting of the trading strategy through the integrated historical trading data and adjusts the strategy parameters to optimize performance indicators.

[0025] Preferably, a risk assessment is conducted on each trading strategy, and the trading strategy is adjusted based on the results of the risk assessment, including changing the trading rules and adjusting the position size. At the same time, when the trading strategy is executed in real time, the system performance and market changes are monitored in real time; by establishing a feedback loop from data collection, strategy design to transaction execution, market data and transaction results are continuously collected for strategy iteration and optimization.

[0026] Preferably, the security management unit uses API Gateway as the only entrance to the system in the external data access module and implements the JWT security authentication mechanism so that only authorized third parties can access the data. The third-party data provider obtains a Token through authentication and carries this Token for identity verification each time the API is called. All data transmitted through the API is encrypted using the SSL / TLS encryption protocol.

[0027] Compared with the prior art, the present invention has the following beneficial effects:

[0028] 1. The present invention uses blockchain technology to achieve decentralized storage of data through distributed ledgers. Each node stores a complete copy of the data, so that even if some nodes are attacked or fail, it will not affect the security and stability of the entire system; and through the consensus mechanism set up to verify and record data, reduce human errors and fraud, and further ensure the integrity of the data.

[0029] 2. The present invention greatly improves the processing capacity and speed of the system by distributing data processing tasks to multiple nodes simultaneously in a decentralized network; at the same time, the data on the blockchain is open and transparent and can be viewed by anyone, which increases the transparency of financial data analysis and helps to establish a more trusted market environment. BRIEF DESCRIPTION OF THE DRAWINGS

[0030] Figure 1 This is a block diagram of the blockchain-based financial data analysis system of the present invention. DETAILED DESCRIPTION

[0031] The following embodiments of the present invention are described in further detail in conjunction with the accompanying drawings and examples. The following examples are used to illustrate the present invention, but are not intended to limit the scope of the present invention.

[0032] As attached Figure 1 As shown:

[0033] Embodiment 1: The present invention provides a financial data analysis system based on blockchain, comprising: a data acquisition unit, used to obtain financial data, which includes a real-time transaction capture module, a historical data integration module, and an external data access module, and transmits the collected data to the data storage unit; a data storage unit, used to store the received financial data, and provided with two storage modules, namely a blockchain storage module and a traditional database storage module, for separate storage; a data processing unit, which performs pre-processing operations on the collected financial data, and uses machine learning and statistical models to predict market trends and evaluate investment risks, and simulates different trading strategies based on historical data and current market conditions, which includes a risk assessment and prediction module and a trading strategy simulation module; a security management unit, which uses encryption technology to ensure the security of user identity, prevent unauthorized access, and restrict access and operation to sensitive data according to user roles and authority settings; an interactive unit, which generates intuitive charts and reports from the data information analyzed by the data processing unit, so that users can query data through an interactive interface.

[0034] The real-time transaction capture module receives transaction data in real time and monitors market conditions in real time through direct API connections with financial exchanges, banks and other financial institutions. It updates key indicators including but not limited to stock prices, exchange rates and interest rates in real time, which is used to monitor and record real-time transaction data in the financial market. Real-time data collection ensures that the trading system obtains and processes market data in a timely manner, improves trading speed and efficiency, and investors can quickly get notifications of market changes and adjust investment strategies based on real-time data, thereby improving trading efficiency and profitability.

[0035] The historical data integration module collects and integrates historical transaction data from multiple financial databases and information sources, uses the APIs of financial data providers to obtain historical transaction data, and uses web crawler technology to capture historical transaction data displayed on web pages, and processes data sources from different financial databases, including but not limited to stock transaction data, bond transaction data, futures and options data, so that the data formats from different data sources are unified. Through the integrated historical transaction data, historical backtesting of trading strategies can be carried out to help investors evaluate the performance of strategies and optimize trading decisions. At the same time, historical data can be used to analyze the long-term trends and cyclical changes in the financial market and provide a basis for investment decisions; the historical data integration submodule collects historical transaction data from various financial databases and information sources to ensure the timeliness, completeness and accuracy of the data. This not only improves the efficiency and reliability of financial data analysis, but also provides financial institutions with more in-depth market insights and decision-making support.

[0036] The external data access module integrates non-transactional data, including but not limited to economic indicators and company financial reports, into the system through APIs or direct upload by third-party data providers, and supports upload and API access in multiple data formats, including but not limited to CSV, JSON, and XML formats. At the same time, Apache Kafka is used to process real-time data streams. For batch uploaded data, ETL tools are used to extract, convert, and load operations. The accessed data is verified, including data integrity check, format check, and logical consistency check, and problematic data is cleaned to ensure data accuracy and reliability.

[0037] The blockchain storage module uses a distributed ledger to store all verified transaction records and core information. Its blockchain network consists of multiple nodes, each of which maintains a complete copy of the ledger. The construction of the blockchain forms a continuous chain structure by including transaction data and the hash value of the previous block in each block. Each block in the blockchain generates a fixed-length string through a hash algorithm, which uniquely represents the content of the block. At the same time, the nodes in the blockchain network reach a consensus through a consensus mechanism, which includes proof of work and proof of equity. Each block contains a timestamp that records the time when the block was created. All transaction records are permanently stored on the blockchain in chronological order, which allows any data to be traced back to the specific time point when it was generated and modified. Since all transaction records on the blockchain are open to all participants, anyone can verify the authenticity of the transaction and trace the historical records, which improves the transparency and trust of the system. The blockchain storage module achieves the immutability and traceability of data through the above method, and improves the reliability and security of the financial data analysis system.

[0038] The traditional database storage module is used to store non-core but frequently queried data, including risk analysis data, customer management data, fraud detection data, personalized service data and algorithmic trading data; the risk analysis data is data generated by the risk assessment and prediction module; customer management data includes basic customer information, transaction records, and behavioral data; fraud detection data includes credit card transactions and account login records; personalized service data is provided by financial institutions through analyzing customer historical data and behavior to provide personalized services and products; algorithmic trading data is used to develop and test trading strategies through rapid query and processing of real-time market data and historical trading data.

[0039] The risk assessment and prediction module selects historical prices, trading volumes and technical indicators as features from the acquired data to build a prediction model. The technical indicators include moving averages and relative strength indexes (RSI). The features are extracted through principal component analysis, which is expressed as:

[0040] X new =W T X

[0041] Among them, X represents the original data set after centering, W represents the matrix composed of principal components, and W T represents the transposed matrix of W, X new Represents the dataset after dimensionality reduction, converting a set of correlated variables into a set of linearly uncorrelated variables through orthogonal transformation, so that each sample in the original dataset is projected onto the low-dimensional space defined by W through matrix multiplication;

[0042] A decision tree is used to build a prediction model. For each node, the feature that can minimize the uncertainty of the data set is selected as the division criterion. The information gain is expressed as:

[0043]

[0044] Where D represents the data set, a represents the feature, V represents the number of values ​​of feature a, and D v Represents the sub-dataset when feature a takes the vth value; divide the data set into multiple subsets according to the selected features and their thresholds, and recursively repeat the above process for each subset until the number of samples in the node is less than the preset minimum value or all samples belong to the same category; predict the market trend through the constructed prediction model, that is, by inputting new data into the tree, judging according to the rules of each node, and finally obtaining the prediction result.

[0045] The trading strategy simulation module determines the assumptions of the trading strategy, including trend tracking and reversal trading, sets trading rules, including buy and sell conditions, position management, stop loss and take profit points, uses historical data and current market conditions, and simulates trading according to the set trading strategy, including generating trading signals, executing trading instructions, and updating the value of the investment portfolio. It also conducts historical backtesting of trading strategies through integrated historical trading data and adjusts strategy parameters to optimize performance indicators.

[0046] Conduct risk assessment on each trading strategy, and adjust the trading strategy based on the results of the risk assessment, including changing trading rules and adjusting position size. At the same time, monitor system performance and market changes in real time when executing the trading strategy in real time; by establishing a feedback loop from data collection, strategy design to transaction execution, continuously collect market data and transaction results for strategy iteration and optimization. The trading strategy module integrates historical data and current market conditions, simulates different trading strategies, and conducts evaluation and optimization to assist investment decisions. Evaluate the performance of trading strategies, including calculating yield, win rate, maximum drawdown, Sharpe ratio, alpha value, and beta value indicators;

[0047] Among them, the annualized rate of return is to convert the returns of the strategy in different backtest periods into the rate of return for a period of one year for fair comparison, which is expressed as:

[0048] The win rate is the proportion of profitable transactions in all transactions, expressed as:

[0049] The maximum retracement represents the maximum decline from a high point to a low point, expressed as:

[0050]

[0051] The Sharpe ratio is the excess return for each unit of risk taken, taking into account both return and risk, and is expressed as:

[0052] The alpha value represents the difference between the actual return and the average expected return, and measures the non-systematic risk of the strategy, expressed as: A = (account annualized return - risk-free return) - Beta*(benchmark annualized return - risk-free return);

[0053] The Beta value measures the sensitivity of the strategy's return rate to market changes and represents systematic risk, expressed as:

[0054]

[0055] Through the calculation and analysis of the above indicators, the performance and risk level of the trading strategy can be comprehensively evaluated. It not only helps investors understand the historical performance of the strategy, but also helps predict the potential risks and returns in the future. In practical applications, investors should choose a trading strategy that suits them according to their investment goals and risk tolerance, and review and adjust the strategy regularly.

[0056] The security management unit uses API Gateway as the only entrance to the system in the external data access module and implements the JWT security authentication mechanism so that only authorized third parties can access the data. Third-party data providers obtain Tokens through authentication and carry this Token for identity verification every time the API is called. All data transmitted through the API is encrypted using the SSL / TLS encryption protocol.

[0057] Additionally, in order to provide a concise description of exemplary embodiments, all features of an actual embodiment (ie, those features that are not relevant to the best mode presently contemplated for carrying out the invention or those that are not relevant to implementing the invention) may not be described.

[0058] It should be understood that in the development of any actual implementation, as in any engineering or design project, numerous implementation-specific decisions may be made. Such a development effort may be complex and time-consuming, but for those of ordinary skill having the benefit of this disclosure, without undue experimentation, the development effort will be a routine task of design, fabrication, and production.

[0059] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.

Claims

1. A financial data analysis system based on blockchain, characterized in that: include: A data collection unit, which is used to obtain financial data, includes a real-time transaction capture module, a historical data integration module, and an external data access module, and transmits the collected data to a data storage unit; The data storage unit is used to store the received financial data and is provided with two storage modules, namely a blockchain storage module and a traditional database storage module, for separate storage; The data processing unit pre-processes the collected financial data and uses machine learning and statistical models to predict market trends and assess investment risks. It also simulates different trading strategies based on historical data and current market conditions. It includes a risk assessment and prediction module and a trading strategy simulation module. The security management unit uses encryption technology to ensure the security of user identities, prevent unauthorized access, and restrict access to and operations on sensitive data based on user roles and permission settings; The interactive unit generates intuitive charts and reports based on the data information analyzed by the data processing unit, allowing users to query data through an interactive interface.

2. A blockchain-based financial data analysis system as claimed in claim 1, characterized in that: The real-time transaction capture module receives transaction data in real time and monitors market conditions in real time through direct API connections with financial exchanges, banks and other financial institutions, and updates key indicators including but not limited to stock prices, exchange rates, and interest rates in real time, that is, it is used to monitor and record real-time transaction data in the financial market.

3. A blockchain-based financial data analysis system as claimed in claim 1, characterized in that: The historical data integration module collects and integrates historical transaction data from multiple financial databases and information sources, uses the APIs of financial data providers to obtain historical transaction data, and uses web crawler technology to capture historical transaction data displayed on web pages, and processes data sources from different financial databases, including but not limited to stock transaction data, bond transaction data, futures and options data, to unify the data formats from different data sources.

4. A blockchain-based financial data analysis system as claimed in claim 1, characterized in that: The external data access module integrates non-transactional data, including but not limited to economic indicators and company financial reports, into the system through APIs or direct upload by third-party data providers, and supports upload and API access in multiple data formats, including but not limited to CSV, JSON, and XML formats. Apache Kafka is used to process real-time data streams, and ETL tools are used to extract, convert, and load batch uploaded data.

5. A blockchain-based financial data analysis system as claimed in claim 1, characterized in that: The blockchain storage module uses a distributed ledger to store all verified transaction records and core information. Its blockchain network consists of multiple nodes, each of which maintains a complete copy of the ledger. The construction of the blockchain forms a continuous chain structure by including transaction data and the hash value of the previous block in each block. Each block in the blockchain generates a fixed-length string through a hash algorithm, which uniquely represents the content of the block. At the same time, the nodes in the blockchain network reach a consensus through a consensus mechanism, which includes proof of work and proof of equity.

6. A blockchain-based financial data analysis system as claimed in claim 1, characterized in that: The traditional database storage module is used to store non-core but frequently queried data, including risk analysis data, customer management data, fraud detection data, personalized service data and algorithmic trading data; the risk analysis data is data generated by the risk assessment and prediction module; the customer management data includes the customer's basic information, transaction records, and behavior data; the fraud detection data includes credit card transactions and account login records; the personalized service data is provided by financial institutions through analysis of customer historical data and behavior to provide personalized services and products; the algorithmic trading data is used to develop and test trading strategies through rapid query and processing of real-time market data and historical trading data.

7. A blockchain-based financial data analysis system as claimed in claim 1, characterized in that: The risk assessment and prediction module selects historical prices, trading volumes and technical indicators as features from the acquired data to build a prediction model. The technical indicators include moving averages and relative strength indexes (RSI), and feature extraction is performed through principal component analysis, which is expressed as: X new =W T X Among them, X represents the original data set after centering, W represents the matrix composed of principal components, and W T represents the transposed matrix of W, X new Represents the dataset after dimensionality reduction, converting a set of correlated variables into a set of linearly uncorrelated variables through orthogonal transformation, so that each sample in the original dataset is projected onto the low-dimensional space defined by W through matrix multiplication; A decision tree is used to build a prediction model. For each node, the feature that can minimize the uncertainty of the data set is selected as the division criterion. The information gain is expressed as: Where D represents the data set, a represents the feature, V represents the number of values ​​of feature a, and D v Represents the sub-dataset when feature a takes the vth value; divide the data set into multiple subsets according to the selected features and their thresholds, and recursively repeat the above process for each subset until the number of samples in the node is less than the preset minimum value or all samples belong to the same category; predict the market trend through the constructed prediction model, that is, by inputting new data into the tree, judging according to the rules of each node, and finally obtaining the prediction result.

8. A blockchain-based financial data analysis system as claimed in claim 1, characterized in that: The trading strategy simulation module determines the assumptions of the trading strategy, including trend tracking and reversal trading, sets trading rules, including buy and sell conditions, position management, stop loss and take profit points, uses historical data and current market conditions, and simulates trading according to the set trading strategy, including generating trading signals, executing trading instructions, and updating the value of the investment portfolio. It also conducts historical backtesting of the trading strategy through the integrated historical trading data and adjusts the strategy parameters to optimize performance indicators.

9. A blockchain-based financial data analysis system as claimed in claim 8, characterized in that: Conduct risk assessment on each trading strategy and adjust the trading strategy based on the results of risk assessment, including changing trading rules and adjusting position size. At the same time, monitor system performance and market changes in real time when executing trading strategies in real market; By establishing a feedback loop from data collection, strategy design to transaction execution, we continuously collect market data and transaction results for strategy iteration and optimization.

10. A blockchain-based financial data analysis system as claimed in claim 1, characterized in that: The security management unit uses API Gateway as the only entrance to the system in the external data access module and implements the JWT security authentication mechanism so that only authorized third parties can access the data. The third-party data provider obtains a Token through authentication and carries this Token for identity verification each time the API is called. All data transmitted through the API is encrypted using the SSL / TLS encryption protocol.

Images