TWM581246U - Exposure management system of corporate finance - Google Patents

Abstract

An exposure management system of corporate finance includes at least one database, an input module, an information capture module, a machine learning module, an analysis module and an output module. The input module is configured for inputting a corporate activity information. The information capture module captures multiple financial market information and at least one event information. The machine learning module uses the past financial market information and event information to learn and build a predictive model. The analysis module calculates an estimated cash flow based on the corporate activity information, predicts a future trend of the financial market information according to the prediction model, calculates a profit and loss analysis result based on the estimated cash flow and the future trend and outputs the analysis result by the output module. The above-mentioned exposure management system of corporate finance can assist users in making better safe-haven operations.

Description

Corporate financial exposure management system

This creation is about an exposure management system, especially a corporate financial exposure management system.

The impact of exchange rate changes on business operations includes economic risk, transaction risk, and translation risk. The economic risk is caused by the rise of the exchange rate, which leads to changes in the competitive position of the company, which in turn changes the future cash flow. The trading risk is due to the difference between the settlement rate of the foreign currency transaction and the payment at two points, so that the actual cash flow received is expected to fall. The conversion risk is the inconsistency between the assets and liabilities of the overseas operating units of the enterprise and the exchange rate at the time of settlement, which leads to changes in the evaluation of the company's foreign currency financial statements. Therefore, for enterprises, exchange rate fluctuations are one of the problems that multinational corporations must face.

However, in addition to economic problems, exchange rate fluctuations have complex political problems that cause financial markets to change rapidly. Therefore, even experienced financial-related practitioners cannot accurately predict the trend of exchange rates to make appropriate hedging operations. In view of this, how to accurately predict the future trend of financial markets as the basis for safe-haven operations is the goal that is currently in great need of effort.

The present invention provides a corporate financial exposure management system, which is a machine learning module that uses the past financial market information and at least one event information to perform machine learning and establish a prediction model, and the analysis module can predict the financial market according to the prediction model. One of the future trends, and based on the calculation of the profit and loss analysis results of a hedging target in a specific period, as a reference for adjusting the hedging operation.

The enterprise financial exposure management system of the present embodiment includes at least one database, an input module, an information capture module, a machine learning module, an analysis module, and an output module. The input module is in communication with the database for inputting information about one of the user activities and storing it in the database. The information capture module is connected to the database for capturing multiple financial market information and at least one event information and storing it in the database. The machine learning module communicates with the database and uses the past financial market information and event information to conduct machine learning and build a predictive model. The analysis module is connected to the database and the machine learning module. The analysis module calculates the estimated cash flow of one of the plurality of currencies based on the enterprise activity information, predicts the future trend of one of the financial market information according to the prediction model, and calculates one of the users' holdings or simulations based on the estimated cash flow and the future trend. The result of a profit and loss analysis of a risk axe during a specific period. The output module is in communication with the analysis module for outputting profit and loss analysis results for the user to use as a reference for adjusting the risk aversion target.

In the following, the specific embodiments and the accompanying drawings are explained in detail, and it is easier to understand the purpose, technical content, characteristics and effects achieved by the present invention.

The various embodiments of the present invention will be described in detail below with reference to the drawings. In addition to the detailed description, the present invention may be widely practiced in other embodiments, and any alternatives, modifications, and equivalent changes of the described embodiments are included in the scope of the present invention. quasi. In the description of the specification, a number of specific details are provided for the reader to have a more complete understanding of the present invention; however, the present invention may be implemented without omitting some or all of the specific details. In addition, well-known steps or elements are not described in detail to avoid unnecessarily limiting the present invention. The same or similar elements in the drawings will be denoted by the same or similar symbols. It is to be noted that the drawings are for illustrative purposes only and do not represent the actual dimensions or quantities of the components. Some of the details may not be fully drawn in order to facilitate the simplicity of the drawings.

Referring to FIG. 1 , the enterprise financial exposure management system of an embodiment of the present invention includes a database 10 , an input module 20 , an information capture module 30 , a machine learning module 40 , and an analysis module 50 . And an output module 60. It should be noted that the enterprise financial exposure management system of the creation can be set on a single server, a cluster server or a cloud platform. The basic architecture of the server is well known to those of ordinary skill in the art to which the author belongs. For example, the server includes an input/output unit, an arithmetic unit, a storage unit, and a bus bar electrically connected to the above components. The computing unit implements the enterprise financial exposure management system of the present creation by executing appropriate instructions. It can be understood that, in order to flexibly apply and expand computing resources, in a preferred embodiment, the enterprise financial exposure management system of the present invention is set on the cloud platform.

Following the above description, the input module 20 is communicatively coupled to the database 10. A user can input a business activity information CI through the input module 20 and store it in the database 10. For example, the input module 20 can generate a web interface or an application programming interface (API) for the user to input the enterprise activity information CI. In an embodiment, the enterprise activity information CI may be at least one of a corporate financial report and an operational information. For example, corporate earnings can be sales revenue, cost of goods sold, accounts receivable days, accounts payable days, outstanding shares outstanding, earnings per share, cash equivalents, short-term loans, short-term investments, inventory, At least one of the underwriting ratio, exchange gains and losses, and operating net profit; operational information can be reporting currency and functional currency, outsourcing ratio, export ratio, accounts receivable days, and accounts payable The age of the aging period, the past holding of each foreign currency currency, the proportion of accounting subjects and aging days, one-time cash changes, future financial projections (sales revenue, cost of goods sold), future foreign currency It is not limited to the proportion of accounting accounts and at least one of the aging days, the original material cost structure, the raw material payment date and the estimated hedge accounting.

The information capture module 30 is in communication with the database 10. The information capture module 30 can retrieve a plurality of financial market information FI and at least one event information EI and store the data in the database 10. In one embodiment, the financial market information FI includes at least one of a purchase price, a sale price, and a strike price and a date of the option, wherein the financial product may be foreign exchange, interest rates, stocks, commodities, credit markets, or The combination of the above. For example, financial commodities can be spot exchange rates, forward exchange rates, exchange rate options, exchange rate swaps, spot rates, forward rates, interest rate options, interest rate swaps, Basis swap, cross currency swaps ( Cross currency swap), spot commodity price, forward commodity price, commodity option, spot price, forward price, stock option, credit default swap or a combination of the above. Event information EI can be important news information, such as natural disasters, major work safety incidents, strike events or press releases of central banks. In an embodiment, the information capture module 30 can be a web crawler or a robotic process automation (RPA). Therefore, the financial market information FI or the event information EI can be accessed through a web crawler or a robot process. Automation (RPA) automatically captures automatically from the Internet or an internal corporate repository, but is not limited to this. In one embodiment, the information capture module 30 can be a user interface through which the user can enter the financial market information FI or the event information EI. It can be understood that the database 10 can be multiple. For example, the corporate activity information CI contains more sensitive information, which can be stored in the first database with strict access restrictions, and the financial market information FI and the event information EI can be stored in the logic of the first database or A second database that is physically different.

The machine learning module 40 is communicatively coupled to the database 10. The machine learning module 40 is capable of machine learning and establishing a predictive model PM from past financial market information FI and event information EI. In one embodiment, the machine learning module 40 can analyze the event information EI in Natural Language Processing (NLP) to obtain at least one feature vocabulary and one of the feature vocabulary occurrence frequencies. The machine learning module 40 reuses historical price trends of daily financial market information, such as high and low price, closing, opening price, and historical volume information, to perform machines with Long Short Term Memory Network (LSTM). Learning can establish a correlation between each financial market information relative to the characteristic vocabulary and the frequency of occurrence and the prediction model PM. Long- and Short-Term Memory Network (LSTM) is a time recurrent neural network. Due to its unique design structure, LSTM is suitable for processing and predicting important events with very long intervals and delays in time series. For example, the information capture module 30 can collect press releases, conference minutes, and statements of the central bank's presidents, and then use the machine learning module 40 to analyze the characteristic vocabulary of each period using natural language processing (NLP), for example, Rate hikes, interest rate cuts, inflation, easing, unemployment, employment, etc., to quantify the intensity of the tone of each market and correspond to the date of occurrence. Then, machine learning is performed with the long-term and short-term memory network (LSTM) to build the prediction model PM in conjunction with the accumulated financial market information FI.

In an embodiment, the information capture module 30 can capture at least one overall economic leading indicator, such as Purchasing Managers' Index (PMI), inflation index, etc., while the machine learning module 40 uses the past Financial market information FI, overall economic leading indicators and event information EI for machine learning and the establishment of a predictive model PM. In one embodiment, the machine learning module 40 can use a regression analysis and a decision tree to analyze the model PM in addition to the long- and short-term memory network (LSTM). For example, the regression analysis can be Bayesian ridge regression, Lasso regression, or support vector machine regression; the decision tree can be a decision tree regressor. .

The analysis module 50 is communicatively coupled to the database 10 and the machine learning module 40. The analysis module 50 can calculate the estimated cash flow of one of the plurality of currencies according to the enterprise activity information CI input by the user, and predict the future trend of the financial market information FI according to the prediction model PM, so that the analysis module 50 can be estimated according to the estimation. The future trend of cash flow and financial market information FI calculates the profit and loss analysis result PL of one of the specific periods held by the user or to simulate one of the risk aversion targets, for example, the profit and loss analysis for each quarter of the coming year. In an embodiment, the risk aversion target may be a structured commodity (which includes a complex high-risk derivative financial product) of foreign exchange, interest rate, commodity, stock, credit market, or a combination thereof. For example, the risk aversion target may be spot exchange rate, forward exchange rate, exchange rate option, exchange rate exchange, spot rate, forward rate, interest rate option, interest rate exchange, basis exchange, cross currency swap, spot commodity A financial product consisting of one of a price, a forward commodity price, a commodity option, a spot price, a forward stock price, a stock option, and a credit default exchange, or a structured commodity consisting of the plurality of financial commodities. It can be understood that the structured goods can be structural goods with different characteristics such as linear combination, non-linear combination, path correlation, multi-period settlement or cross-market label. In an embodiment, in addition to the prediction model PM, the analysis module 50 may further predict the future trend of the financial market information FI according to at least one expert adjustment parameter. For example, the analysis module 50 may adjust the prediction model PM according to the algorithm written by the trader's trading experience, or first predict the future trend of the financial market information FI by using the prediction model PM, and then adjust the financial strategy by an appropriate algorithm or parameter. The future trend of market information FI.

It should also be noted that the risk aversion objects held by users may include open market financial products (such as exchange rates, interest rates, publicly issued shares) and financial products in the non-public market (such as exchange rate options, interest rate options, Structured goods, etc.). The transaction price of the open market financial products can be obtained from the open market through the information capture module 30, and the profit and loss of the risk aversion can be based on the open market transaction price. However, financial products in the non-public market lack reliable publicly traded prices as the basis for profit and loss analysis. Therefore, the analysis module 50 needs to further estimate the market price for financial products in the non-public market. In one embodiment, the analysis module 50 may select an evaluation model that conforms to financial product and market characteristics, and calibrate the evaluation model against financial products with better market liquidity. Then, the market price of the financial products in the non-public market is estimated by an appropriate numerical method, so that the analysis module 50 can analyze the profit and loss of the financial products in the non-public market for a specific period based on the estimated market price. For example, the evaluation model can be Black-Scholes Model, Bachelier Model, Local Volatility Model, Libor Market Model, International Exchange Trading and Derivatives Association (International Swap and Derivatives Association (ISDA) issued the ISDA Credit Default Swap Model (ISDA CDS Model); the numerical method can be Monte Carlo simulation or closed solution.

The output module 60 is communicatively coupled to the analysis module 50. The profit and loss analysis result PL analyzed by the analysis module 50 can be output through the output module 60 for the user to use as a reference for adjusting the risk aversion target, thereby making a more appropriate hedging operation. It should be noted that the enterprise financial exposure management system of this creation is based on the profit and loss analysis result of the risk aversion period in a specific period (for example, one compared with the operation method of recommending to buy or sell a specific financial product in the past. The profit and loss analysis of each quarter of the year is used as a reference for adjusting the risk aversion target. Therefore, this creation can not only present the long-term profit and loss results for the user's reference, but also avoid frequent adjustment of the risk aversion target in the short term. In an embodiment, the output module 60 can be a display device. It can be understood that, in the cloud platform architecture, the output module 60 can be a communication interface, such as a wired or wireless network interface, a mobile communication network interface, etc., to transmit the profit and loss analysis result PL to the remote user device. .

In an embodiment, the analysis module 50 may calculate the profit and loss analysis result PL of the at least one recommended risk aspiration period according to the estimated cash flow and the future trend of the financial market information FI, and output the recommended risk avoidance by the output module 60. The profit and loss analysis result PL of the target is used as a reference for the user to adjust the risk aversion target, that is, the analysis module 50 proposes a safe-haven operation, thus facilitating the user to make a decision on the safe-haven operation.

Referring to FIG. 2, in an embodiment, the enterprise financial exposure management system of the present invention further includes a monitoring module 70, which is communicatively coupled to the analysis module 50. The monitoring module 70 can monitor the impact of the event information EI on the risk aspirations held by the user and provide an early warning. For example, the monitoring module 70 monitors the current or recent feature vocabulary and the frequency of occurrence, and when the frequency of occurrence of the feature vocabulary is greater than or equal to a predicted value of the monitoring, the analysis module 50 is required to recalculate the evasion held by the user. The result of the profit and loss analysis of the risk indicator for a specific period of time. When the recalculated profit and loss analysis result PL is excessively fluctuating, the user may be notified to prompt the user to adjust the risk aversion target. For example, when the recalculated risk aversion has a one-day reward volatility greater than or equal to one of the predetermined multiples of historical volatility, the user is notified. In an embodiment, the preset multiple may be 1.5 times or 1.96 times. It can be understood that the preset multiple can be set by the user according to the requirements. It should also be noted that the monitored expected value can be a variable value. For example, when a major event occurs, the corresponding characteristic vocabulary appears less frequently, and the monitored predicted value can be relatively small. As the time of occurrence of this major event increases, the frequency of occurrence of the corresponding characteristic vocabulary may gradually increase, and the reaction of the financial market relative to this significant event may be inactivated, and the predicted value of the monitoring may be relatively large at this time.

It can be understood that the characteristic vocabulary of the single event information EI and its frequency of occurrence do not necessarily affect the profit and loss of all risk aversion targets. Therefore, if a single major event information occurs, the profit and loss analysis result PL of recalculating all risk aversion targets may occupy more Computing resources. In order to reduce the computing resources required, in an embodiment, the machine learning module 40 can utilize the feature vocabulary, the frequency of occurrence, and the past financial market information FI to perform machine learning to establish a specific risk acuity relative to a particular feature vocabulary and One of the frequencies of its frequency of sensitivity. At this time, when the frequency of occurrence of the specific feature vocabulary is greater than or equal to the predicted value of the monitoring, it is only necessary to recalculate the profit and loss analysis result PL of the risk aversion target with the sensitivity of the specific feature vocabulary being greater than or equal to a sensitivity prediction value.

The following examples illustrate the implementation of the corporate financial exposure management system of this creation. Taking the foreign exchange market as an example, the UK unexpectedly passed the referendum on June 30, 2016, causing the pound to fall sharply against the dollar. The corporate financial exposure management system of this creation analyzes the past financial market information to judge the possible reaction of the financial market after the sterling, and reviews the exchange rate of each currency and the historical trend of interest rates to confirm the possible trend. For example, based on past experience, the sterling of the pound will cause a sharp appreciation of the yen. Therefore, the company's corporate financial exposure management system not only reviews the risk-averse targets of upstream and downstream customers related to the pound, but also reviews the risk-related targets associated with each currency that interacts with the pound. If the fluctuation of the risk aversion target is large, the user is notified to take appropriate hedging operations. For example, the company's corporate financial exposure management system informs manufacturers from Japan to purchase the risk of higher costs in the next month, and advises customers to carry out relevant hedging. In addition, the corporate financial exposure management system of this creation continuously monitors the possible reaction and impact of Brexit on the subsequent financial markets.

Take the commodity market as an example, large copper mines produce 8% of the world's copper-producing ore. When the copper mines went on strike, the copper commodity market immediately responded. The corporate financial exposure management system of this creation reviews the impact of the sharp increase in copper prices on the cost of upstream and downstream manufacturers. When the profit and loss analysis result PL is large, the relevant manufacturers (for example, copper foil substrate manufacturers, copper wire factories, etc.) are notified to perform better safe-haven operations. Similarly, the corporate financial exposure management system of this creation monitors the duration of the strike, the possible response to the subsequent copper commodity market, and the timing of the impact.

In summary, the enterprise financial exposure management system of the present invention uses a machine learning module to utilize the past financial market information and at least one event information to perform machine learning and establish a prediction model, and the analysis module can predict the financial market according to the prediction model. One of the future trends, and based on the calculation of the profit and loss analysis results of a hedging target in a specific period, as a reference for adjusting the hedging operation and making appropriate hedging operations.

The embodiments described above are only for explaining the technical idea and characteristics of the present invention, and the purpose thereof is to enable those skilled in the art to understand the contents of the present invention and implement them according to the scope of the patent. That is, the equivalent changes or modifications made by the people in accordance with the spirit revealed by this creation should still be covered by the scope of the patent of this creation.

10‧‧‧Database  20‧‧‧Input module  30‧‧‧Information Capture Module  40‧‧‧ machine learning module  50‧‧‧Analysis module  60‧‧‧Output module  70‧‧‧Monitor module  CI‧‧‧Corporate Activity Information  EI‧‧‧Event Information  FI‧‧‧Financial Market Information  PM‧‧‧ forecasting model  PL‧‧‧ profit and loss analysis results  

FIG. 1 is a schematic diagram showing an enterprise financial exposure management system according to an embodiment of the present invention.  2 is a schematic diagram showing an enterprise financial exposure management system of another embodiment of the present creation.  

Claims (23)

A corporate financial exposure management system comprising:  At least one database;  An input module, which is in communication with the database, for inputting information about one of the users' business activities, and storing the information in the database;  An information capture module is connected to the database for capturing a plurality of financial market information and at least one event information, and storing the information in the database;  a machine learning module, which is communicatively connected with the database, and performs machine learning and establishes a prediction model by using the financial market information and the event information in the past;  An analysis module, which is in communication with the database and the machine learning module, and calculates an estimated cash flow of one of the plurality of currencies based on the enterprise activity information, and predicts a future trend of the financial market information according to the prediction model, And calculating, according to the estimated cash flow and the future trend, a profit and loss analysis result of the one of the risk periods held by the user or to be simulated;  An output module is communicatively coupled to the analysis module for outputting the profit and loss analysis result for the user to use as a reference for adjusting the risk aversion target.   The enterprise financial exposure management system of claim 1, wherein the analysis module calculates the profit and loss analysis result of the at least one recommended risk aspiration target during the specific period according to the estimated cash flow and the future trend, and uses the output The module outputs the profit and loss analysis result of the recommended risk aversion target for the user to use as a reference for adjusting the risk aversion target. The enterprise financial exposure management system of claim 1, wherein the analysis module further estimates a market price of one of the financial products in the non-public market, and based on the estimated cash flow, the future trend, and The market price calculates the profit and loss analysis result of the risk target for the specific period. The enterprise financial exposure management system of claim 1, wherein the machine learning module analyzes the event information by natural language processing to obtain at least one feature vocabulary and a frequency of occurrence of one of the feature vocabulary. The enterprise financial exposure management system of claim 4, wherein the machine learning module learns and establishes each of the financial market information relative to the characteristic vocabulary with the characteristic vocabulary, the frequency of occurrence, and the past financial market information, and One of the frequencies of occurrence is related. The enterprise financial exposure management system of claim 4, wherein the machine learning module learns and establishes the risk vocabulary relative to the characteristic vocabulary and the appearance with the characteristic vocabulary, the frequency of occurrence, and the past financial market information One of the frequencies is sensitive. The enterprise financial exposure management system as described in claim 4 further includes:  a monitoring module, which is in communication with the analysis module, and monitors the current characteristic vocabulary and the frequency of occurrence, and when the frequency of occurrence is greater than or equal to a predicted value of the monitoring, the analysis module is required to recalculate the risk avoidance The result of the profit and loss analysis of the target period.   The enterprise financial exposure management system according to claim 7, wherein the user is notified when the recalculated risk volatility of the one of the risk avoidance targets is greater than or equal to one of the predetermined multiples of historical volatility. The enterprise financial exposure management system according to claim 7, wherein the risk aversion target having a sensitivity greater than or equal to a sensitivity prediction value is recalculated. The enterprise financial exposure management system of claim 1, wherein the information capture module further captures at least one overall economic leading indicator, and the machine learning module uses the financial market information in the past, the overall economic leading indicator. And the event information for machine learning and building the predictive model. The enterprise financial exposure management system of claim 1, wherein the machine learning module performs machine learning with a long-term and short-term memory network and establishes the prediction model. The enterprise financial exposure management system according to claim 1, wherein the machine learning module performs machine learning and establishes the prediction model by using a long-term and short-term memory network, a regression analysis, and a decision tree. The enterprise financial exposure management system of claim 1, wherein the analysis module predicts a future trend of the financial market information according to the prediction model and the at least one expert adjustment parameter. The enterprise financial exposure management system of claim 1, wherein the enterprise activity information comprises at least one of a corporate financial report and an operational information. The enterprise financial exposure management system of claim 14, wherein the enterprise financial report includes at least an accounts receivable period and an account payable period. The enterprise financial exposure management system according to claim 14, wherein the enterprise financial report includes sales revenue, cost of goods sold, accounts receivable days, accounts payable days, outstanding shares outstanding, earnings per share, approximately At least one of cash, short-term borrowings, short-term investments, inventories, ratios, exchange gains and losses, and net profit. The enterprise financial exposure management system of claim 14, wherein the operational information includes at least an account receivable period and an aging age of the accounts payable period. The enterprise financial exposure management system as claimed in claim 14, wherein the operation information includes an accounting currency and a functional currency, an outsourcing ratio, an export ratio, an account receivable period, and an aging period of the accounts payable period. , the past holding of foreign exchange currency and the proportion of accounting subjects and aging days, one-time cash changes, future financial projections, future foreign exchange currency and accounting account ratio projections and aging days, raw materials At least one of the cost structure, the original material payment date, and the estimated hedge accounting. The enterprise financial exposure management system of claim 1, wherein the information capture module comprises a web crawler, a robot process automation or a user interface. The enterprise financial exposure management system of claim 1, wherein the financial market information comprises at least one of a purchase price, a sale price, and a strike price of the financial product and a date. The enterprise financial exposure management system of claim 20, wherein the financial commodity comprises a foreign exchange, an interest rate, a stock, a commodity, a credit market, or a combination thereof. The enterprise financial exposure management system according to claim 20, wherein the financial commodity comprises a spot exchange rate, a forward exchange rate, an exchange rate option, an exchange rate exchange, a spot rate, a forward rate, an interest rate option, an interest rate exchange, and a basis. Poor exchange, cross currency swap, spot commodity price, forward commodity price, commodity option, spot stock price, forward stock price, stock option, credit default swap or a combination of the above. The enterprise financial exposure management system according to claim 1, wherein the risk avoidance target includes a spot exchange rate, a forward exchange rate, an exchange rate option, an exchange rate exchange, a spot rate, a forward rate, an interest rate option, an interest rate exchange, Structured goods with basis exchange, cross currency swap, spot commodity price, forward commodity price, commodity option, spot price, forward price, stock option, credit default exchange or a combination of the above.