System for operating and providing financial product by using martingale investment strategy

Abstract

A system for operating and providing a financial product by using a Martingale investment strategy, according to the present invention, may comprise: a data collection module for collecting investment-market-related data including price fluctuations and trading trends of an investment market and investor asset-status data including assets to be invested and investment direction of an investor; an AI-based analysis module which analyzes the investment-market-related data and the investor asset-status data on the basis of each piece of data collected by the data collection module, so as to automatically determine purchase of the assets to be invested according to a preset multiple-purchase rule when the assets to be invested is in a downtrend, and which determines, when the assets to be invested rebound, a sale time point of the assets to be invested; and an investment execution module for executing, on the basis of the determination of the AI-based analysis module, the purchase and sale of the assets to be invested.

Description

Financial product management and provision system utilizing the Martingale investment strategy

[0001] The present invention relates to a system for executing the trading of financial products by analyzing investment market data, and more specifically, to a system for implementing a Martingale investment strategy and automatically executing customized trading for investors by utilizing an AI-based analysis module.

[0002] The Martingale strategy is a betting method that originated in 18th-century French gambling houses. It features a structure where the bet amount is doubled upon a loss to recover all losses and secure a fixed profit with a single success. In the financial investment market, this strategy is based on the principle of mean reversion and is invested under the assumption that asset prices will return to their intrinsic value or mean in the long term.

[0003] However, the existing Martingale investment strategy has limitations due to the assumption of mean reversion. Not all assets revert to the mean, and some assets decline over the long term or fail to recover. There is a problem in that the strategy may not be effective in extreme situations, such as the global financial crisis, as market recovery is delayed.

[0004] In particular, a structure that doubles the investment amount upon every loss requires infinite capital. In reality, capital has limits, and a sustained market downturn can lead to excessive losses. Furthermore, because purchases are made simply based on the magnitude of the decline without analyzing the risk of individual assets, the portfolio can become severely distorted in extreme situations, and if asset prices do not rebound, the investor's losses accumulate.

[0005] The conventional Martingale strategy can be inefficient to execute because it is not based on quantitative data analysis or market volatility forecasting. It also has limitations in that it cannot provide customized investment strategies because it fails to reflect the individual circumstances of investors (asset size, risk preference, etc.).

[0006] If asset liquidity is low or trading volume is insufficient, buying and selling may not proceed smoothly, potentially delaying strategy execution. This issue is particularly pronounced in cases involving specific stocks or high market volatility. Existing strategies merely apply fixed rules repeatedly without flexibly responding to changes in the market environment; furthermore, since investors lack opportunities to receive feedback or make adjustments during the strategy process, it is difficult to maximize investment effectiveness.

[0007] Due to the limitations of these existing technologies, a new approach incorporating data-driven analysis and artificial intelligence is required for the effective utilization of the Martingale strategy in the investment market.

[0008] The present invention is designed to solve the problems of the aforementioned prior art and aims to provide a customized Martingale investment strategy that analyzes investment market data and investor-related data in real time to capture the optimal trading timing and dynamically adjusts according to the investor's asset situation and risk tolerance.

[0009] The problems of the present invention are not limited to those mentioned above, and other unmentioned problems will be clearly understood by those skilled in the art from the description below.

[0010] The financial product operation and provision system utilizing the Martingale investment strategy of the present invention for achieving the above-mentioned purpose may include: a data collection module that collects investment market-related data including price fluctuations and trading trends of the investment market and investor asset status data including the investor's investment target assets and investment direction; an AI-based analysis module that analyzes the investment market-related data and investor asset status data based on each data collected by the data collection module, automatically determines the purchase of the investment target assets according to a pre-set multiple purchase rule when the investment target assets are in a downtrend, and determines the sale point of the investment target assets when the investment target assets rebound; and an investment execution module that executes the purchase and sale of the investment target assets based on the determination of the AI-based analysis module.

[0011] In addition, the data collection module can perform an initial investment strategy setting algorithm including (a-1) a step of analyzing the price fluctuation pattern and trading volume trend of the investment target asset from the investment market-related data, (a-2) a step of calculating the investable amount and the diversification ratio of the investment target asset from the investor asset status data, and (a-3) a step of setting the purchase size and target selling level at each stage.

[0012] In addition, the AI-based analysis module can perform a bear market stage judgment algorithm including a step (b-1) of performing a first bear market judgment of the investment target asset and a step (b-2) of performing a final bear market judgment of the investment target asset.

[0013] At this time, the above step (b-1) may include a step (b-1-1) of calculating the divergence between the current price of the investment target asset and the N-day moving average line (N: a pre-set natural number), a step (b-1-2) of determining whether the current price of the investment target asset is located below the N-day moving average line, and a step (b-1-3) of determining an initial downward signal if, as a result of the determination in step (b-1-2), the price of the investment target asset is located below the N-day moving average line.

[0014] In addition, the above step (b-2) may include a step (b-2-1) of analyzing the level of divergence from the above N-day moving average line over a previously set past period of the above investment target asset to set a judgment criterion value for determining a bear market, a step (b-2-2) of determining whether the current divergence of the above investment target asset is lower than the judgment criterion value set in the above step (b-2-1), and a step (b-2-3) of determining that it is an investable bear market phase if, as a result of the judgment in the above step (b-2-2), the current divergence of the above investment target asset is lower than the judgment criterion value set.

[0015] In addition, the system may further include a strategy optimization module that analyzes the results of buying and selling the investment target asset by the investment execution module, evaluates the validity of the investment strategy derived by the AI-based analysis module, and optimizes the trading strategy according to the evaluation results.

[0016] Meanwhile, the strategy optimization module can perform an investment strategy performance analysis and optimization algorithm comprising: a step (c-1) of analyzing the profitability of the trading results of the investment target asset by the investment execution module; a step (c-2) of deriving effective and inefficient strategic elements according to pre-set criteria based on the profitability analyzed in step (c-1); and a step (c-3) of updating the trading strategy based on the results derived in step (c-2).

[0017] In addition, it may further include a portfolio management module that constructs a portfolio by analyzing the correlation of the aforementioned investment target assets and performs rebalancing by monitoring the asset composition of the portfolio in real time.

[0018] In addition, the portfolio management module may perform an asset diversification and rebalancing algorithm comprising a step (d-1) of analyzing the correlation between a plurality of investment target assets, a step (d-2) of determining the diversification ratio based on the correlation analyzed in step (d-1), and a step (d-3) of constructing a portfolio according to the diversification ratio determined in step (d-2).

[0019] In addition, the portfolio management module can perform a liquidity analysis algorithm that monitors the liquidity of the investment target asset in real time to determine whether trading is possible and recommends alternative assets if the liquidity is below a threshold.

[0020] The financial product operation and provision system utilizing the Martingale investment strategy of the present invention, designed to solve the aforementioned problem, has the advantage of being able to implement a more sophisticated and systematic multiple buying strategy by improving existing simple repetitive trading methods through the real-time analysis of investment market-related data and investor asset status data by combining the Martingale investment strategy with artificial intelligence technology.

[0021] In addition, the present invention can provide customized strategies for each investor, prevent excessive risk exposure, and generate stable returns by executing trades while reflecting the investor's asset status and investment goals in real time.

[0022] Furthermore, the present invention enables the AI-based analysis module to automatically execute trades and respond immediately to market conditions, thereby excluding emotional judgments and maintaining consistent investment principles while flexibly adapting to market changes.

[0023] Furthermore, the present invention has the advantage of enabling the implementation of a stable and sustainable investment system by effectively controlling the limitations of the existing Martingale strategy, such as the need for infinite capital and the risk of extreme losses, through AI-based analysis and automated risk management.

[0024] The effects of the present invention are not limited to those mentioned above, and other unmentioned effects will be clearly understood by those skilled in the art from the description in the claims.

[0025] FIG. 1 is a schematic diagram showing the components constituting a financial product operation and provision system utilizing a Martingale investment strategy according to one embodiment of the present invention.

[0026] FIG. 2 is a diagram showing each process of an initial investment strategy setting algorithm performed by a data collection module in a financial product operation and provision system utilizing a Martingale investment strategy according to an embodiment of the present invention.

[0027] FIG. 3 is a diagram showing each process of a bear market stage judgment algorithm performed by an AI-based analysis module in a financial product operation and provision system utilizing a Martingale investment strategy according to one embodiment of the present invention.

[0028] FIG. 4 is a diagram showing the detailed process of step (b-1) of the bear market stage judgment algorithm performed by the AI-based analysis module in a financial product operation and provision system utilizing a Martingale investment strategy according to one embodiment of the present invention.

[0029] FIG. 5 is a diagram showing the detailed process of step (b-2) of the bear market stage judgment algorithm performed by the AI-based analysis module in a financial product operation and provision system utilizing a Martingale investment strategy according to one embodiment of the present invention.

[0030] FIG. 6 is a diagram illustrating the concept of a bear market stage judgment algorithm performed by an AI-based analysis module in a financial product operation and provision system utilizing a Martingale investment strategy according to one embodiment of the present invention.

[0031] FIG. 7 is a diagram showing each process of investment strategy performance analysis and optimization algorithms performed by a strategy optimization module in a financial product operation and provision system utilizing a Martingale investment strategy according to an embodiment of the present invention.

[0032] FIG. 8 is a diagram showing each process of an asset diversification investment and rebalancing algorithm performed by a portfolio management module in a financial product operation and provision system utilizing a Martingale investment strategy according to one embodiment of the present invention.

[0033] In this specification, where a component (or region, layer, part, etc.) is described as being "on," "connected," or "combined" with another component, it means that it may be directly placed / connected / combined with the other component, or that a third component may be placed between them.

[0034] Identical reference numerals denote identical components. Additionally, in the drawings, the thicknesses, proportions, and dimensions of the components are exaggerated for the effective illustration of the technical content.

[0035] "And / or" includes all one or more combinations that the associated configurations can define.

[0036] Terms such as "first," "second," etc., may be used to describe various components, but said components should not be limited by said terms. These terms are used solely for the purpose of distinguishing one component from another. For example, without departing from the scope of the present invention, the first component may be named the second component, and similarly, the second component may be named the first component. A singular expression includes a plural expression unless the context clearly indicates otherwise.

[0037] Additionally, terms such as "below," "lower side," "above," and "upper side" are used to describe the relationships between the components depicted in the drawings. These terms are relative concepts and are described based on the directions indicated in the drawings.

[0038] Unless otherwise defined, all terms used herein (including technical and scientific terms) have the same meaning as generally understood by those skilled in the art to which the present invention pertains. Additionally, terms such as those defined in commonly used dictionaries should be interpreted as having a meaning consistent with their meaning in the context of the relevant technology, and are explicitly defined herein unless interpreted in an ideal or overly formal sense.

[0039] Terms such as "include" or "have" are intended to indicate the existence of the features, numbers, steps, actions, components, parts, or combinations thereof described in the specification, and should be understood as not precluding the existence or addition of one or more other features, numbers, steps, actions, components, parts, or combinations thereof.

[0040] Furthermore, when it is stated in this specification that a first component operates or is executed on (ON) a second component, it should be understood that the first component operates or is executed in an environment where the second component operates or is executed, or operates or is executed through direct or indirect interaction with the second component.

[0041] Where any component, device, or system is described as including a component consisting of a program or software, it should be understood that, even without explicit mention, that component, device, or system includes hardware (e.g., memory, CPU, etc.) or other programs or software (e.g., an operating system or drivers required to run the hardware) necessary for the execution or operation of that program or software.

[0042] Furthermore, unless otherwise specified regarding the implementation of a component, it should be understood that the component may be implemented in software, hardware, or both software and hardware.

[0043] Furthermore, the terms used herein are for describing the embodiments and are not intended to limit the invention. In this specification, the singular form includes the plural form unless specifically stated otherwise in the text. As used herein, 'comprises' and / or 'comprising' do not exclude the presence or addition of one or more other components to the mentioned components.

[0044] Additionally, in this specification, terms such as 'part', 'device', etc., may be intended to refer to a functional and structural combination of hardware and software driven by said hardware or for driving the hardware. For example, the hardware may be a data processing device including a CPU or other processor. Furthermore, the software driven by the hardware may refer to a running process, object, executable, thread of execution, program, etc.

[0045] Furthermore, it can be easily inferred by an average expert in the art of the present invention that the above terms may refer to a specific code and a logical unit of hardware resources for executing the said specific code, and do not necessarily refer to physically connected code or a single type of hardware.

[0046] FIG. 1 is a schematic diagram showing the components constituting a financial product operation and provision system (100) utilizing a Martingale investment strategy according to one embodiment of the present invention.

[0047] As illustrated in FIG. 1, the financial product operation and provision system (100) utilizing the Martingale investment strategy in this embodiment may include a data collection module (110), an AI-based analysis module (120), an investment execution module (130), a strategy optimization module (140), and a portfolio management module (150).

[0048] The data collection module (110) can collect investment market-related data including price fluctuations and trading trends in the investment market, and investor asset status data including the investor's investment target assets and investment direction.

[0049] The investor can input investor asset status data through the investor terminal (10), and the data collection module (110) is equipped to collect and analyze market data in real time.

[0050] And the data collection module (110) can collect real-time market data through APIs of various financial data providers or web crawling, and the collected data can be stored in a structured database or an unstructured data repository and used for analysis.

[0051] The AI-based analysis module (120) can perform analysis based on each data collected by the data collection module (110).

[0052] The AI-based analysis module (120) can learn patterns of past data through a machine learning algorithm and analyze similarities with the current market situation.

[0053] In addition, the AI-based analysis module (120) can analyze investment market-related data and investor asset status data to automatically determine the purchase of the investment target asset according to a pre-set multiple purchase rule when the investment target asset is in a declining market.

[0054] And the AI-based analysis module (120) can determine the selling point of the investment target asset at the point of rebound of the investment target asset. The AI-based analysis module (120) can be configured to utilize deep learning technology to identify the characteristics of time series data and to respond to non-linear market changes.

[0055] The investment execution module (130) can execute the purchase and sale of investment target assets based on the decision of the AI-based analysis module (120).

[0056] Specifically, the investment execution module (130) is equipped to capture the optimal trading time by referring to real-time market data and to execute orders. The investment execution module (130) can execute orders in splits to minimize market impact, and can select and execute various order types (limit order, market order, conditional order, etc.) according to the situation.

[0057] The strategy optimization module (140) analyzes the results of buying and selling the investment target asset by the investment execution module (130), evaluates the validity of the investment strategy derived by the AI-based analysis module (120), and can optimize the trading strategy according to the evaluation results.

[0058] Such a strategy optimization module (140) can learn investment results by utilizing a reinforcement learning algorithm and dynamically adjust the strategy according to changes in the market environment.

[0059] The portfolio management module (150) can analyze the correlation of investment target assets to construct a portfolio and monitor the asset composition of the portfolio in real time to perform rebalancing.

[0060] The portfolio management module (150) can perform optimal asset allocation based on modern portfolio theory and can apply various portfolio management strategies such as risk parity strategies or dynamic asset allocation strategies.

[0061] In addition, the portfolio management module (150) is equipped to monitor the liquidity of the investment target asset in real time to determine whether trading is possible, and to recommend alternative assets if the liquidity is below a threshold.

[0062] In addition, the portfolio management module (150) can manage systemic risk through diversified investment in various asset classes such as ETFs, stocks, and bonds.

[0063] Below, we will explain in detail the specific algorithms performed in each of these components.

[0064] FIG. 2 is a diagram showing each process of an initial investment strategy setting algorithm performed by a data collection module (110) in a financial product operation and provision system utilizing a Martingale investment strategy according to one embodiment of the present invention.

[0065] As illustrated in FIG. 2, in this embodiment, the data collection module (110) can perform three major analysis steps to set an initial investment strategy.

[0066] The data collection module (110) can analyze the price fluctuation patterns and trading volume trends of the investment target asset from investment market-related data in step (a-1). Specifically, various technical indicators such as moving averages, trend lines, and Relative Strength Index (RSI) can be used to analyze price fluctuation patterns, and market participation and liquidity can be identified through the analysis of trading volume trends.

[0067] At this time, the moving average line is a line connecting the average prices over a specific period, and trends can be determined through moving average lines of various periods, such as short-term (5 days, 10 days), medium-term (20 days, 60 days), and long-term (120 days, 240 days).

[0068] Furthermore, trend lines are indicators that identify the direction and strength of the current trend by connecting past price highs and lows, and the direction of the market can be analyzed through the slopes of upward and downward trend lines.

[0069] In addition, the Relative Strength Index (RSI) is an indicator that compares the magnitude of the rise and fall over a certain period and is represented as a value between 0 and 100; generally, if it is 70 or higher, it is considered overbought, and if it is 30 or lower, it is considered oversold.

[0070] The data collection module (110) can calculate the investable amount and the diversification ratio of the investment target assets from the investor asset status data in step (a-2). The investable amount can be determined by considering the investor's total asset size and risk tolerance level, and the diversification ratio can be calculated based on portfolio theory.

[0071] This portfolio theory is based on Modern Portfolio Theory and can derive the optimal asset allocation ratio by considering the expected return and risk of individual assets, as well as the correlations between assets.

[0072] Additionally, the data collection module (110) can set the step-by-step purchase size and target selling level in step (a-3). The purchase size can be set as a multiple of the previous investment amount in the event of a loss, reflecting the characteristics of the Martingale strategy, and the target selling level can be determined by considering the investor's expected rate of return and risk preference.

[0073] Specifically, the multiple of the step-by-step purchase size can be set to 1.5 times, 2 times, 2.5 times, etc., and this can be adjusted according to the investor's capital size and risk tolerance level.

[0074] In addition, the target selling level can be set in the form of an absolute return (e.g., 10%, 15%, etc.) or a relative return (e.g., excess return relative to the market) and can be dynamically adjusted depending on market conditions.

[0075] This initial investment strategy setting algorithm can be re-executed not only at the start of the investment but also in the event of changes in the market environment or the investor's situation, thereby ensuring flexibility and adaptability of the investment strategy.

[0076] Specifically, the data collection module (110) can collect real-time market data by linking with various financial information provision systems and can immediately reflect changes in the investor's asset status or investment goals through the investor terminal (10).

[0077] In addition, the data collection module (110) can perform cross-verification of multiple data sources to verify the reliability of the collected data and can improve the accuracy of the analysis by filtering out outliers or noise.

[0078] FIG. 3 is a diagram showing each process of a bear market stage judgment algorithm performed by an AI-based analysis module (120) in a financial product operation and provision system utilizing a Martingale investment strategy according to one embodiment of the present invention.

[0079] As illustrated in FIG. 3, in this embodiment, the AI-based analysis module (120) can sequentially perform a two-step analysis process to determine a bear market.

[0080] Specifically, the AI-based analysis module (120) can perform a bear market stage judgment algorithm including a step (b-1) of performing a first bear market judgment of the investment target asset and a step (b-2) of performing a final bear market judgment.

[0081] The bear market stage judgment algorithm is equipped to systematically analyze the market's downturn phases and determine the buying timing for the Martingale strategy.

[0082] And the AI-based analysis module (120) can determine a market downturn on an individual stock basis rather than a decline in the entire market. This is configured so that each stock can be evaluated independently, as each stock has its own unique price flow and pattern.

[0083] In addition, the AI-based analysis module (120) can utilize various market indicators and technical analysis tools in combination when determining a bear market. For example, it can determine whether there is a bear market by comprehensively analyzing moving averages, Bollinger Bands, momentum indicators, etc.

[0084] In this context, Bollinger Bands are an indicator that sets upper and lower ranges using standard deviations centered on the moving average line; if the current price approaches or falls below the lower band, it can be judged as a downtrend.

[0085] Furthermore, momentum indicators represent the speed and direction of price changes and can assist in identifying buying opportunities in periods where downward momentum strengthens.

[0086] And the AI-based analysis module (120) can learn patterns in past data to analyze similarities with the current market situation. Through this, it can predict the probability of a successful rebound and the average rebound range in similar past downturn phases.

[0087] Additionally, the AI-based analysis module (120) can measure the intensity of a downtrend by analyzing market volatility and trading volume data together. A decline occurring with increasing trading volume can be judged to have a high probability of a trend reversal.

[0088] Such a bear market stage judgment algorithm can continuously perform re-evaluations based on real-time updated market data and is equipped to dynamically adjust judgment criteria according to changes in the market environment.

[0089] FIG. 4 is a diagram showing the detailed process of step (b-1) of a bear market stage judgment algorithm performed by an AI-based analysis module (120) in a financial product operation and provision system utilizing a Martingale investment strategy according to one embodiment of the present invention.

[0090] As illustrated in FIG. 4, step (b-1) may include step (b-1-1) of calculating the divergence between the current price of the investment asset and the N-day moving average line.

[0091] This divergence is an indicator showing how far the current price is from the moving average line; it is generally expressed as a percentage and can be calculated using the following formula: Divergence = (Current Price / N-Day Moving Average Price) × 100.

[0092] Specifically, the N-day moving average is the arithmetic mean of the closing prices over the past N days and can be used to identify the medium-to-long-term trend of an investment asset. In this case, the value of N can be set to various periods, such as 5 days, 20 days, 60 days, or 120 days.

[0093] And if the divergence is lower than 100, it means that the current price is located below the moving average line, and if it is higher than 100, it means that the current price is located above the moving average line.

[0094] Additionally, step (b-1) may include step (b-1-2) for determining whether the current price of the investment asset is located below the N-day moving average line. Here, N refers to a pre-set natural number that can be adjusted according to market conditions and the characteristics of the investment asset.

[0095] In addition, the value of N can be set considering the volatility of the investment asset and market characteristics. For example, in the case of highly volatile assets, a longer-period moving average can be used to filter out short-term noise.

[0096] And, step (b-1) may include step (b-1-3), which determines an initial bearish signal if the price of the investment target asset is located below the N-day moving average line as a result of the judgment in step (b-1-2).

[0097] Such an initial bearish signal indicates a point where further buying consideration is needed, and this can be used as a prerequisite for determining the final bear market in step (b-2).

[0098] In addition, the AI-based analysis module (120) can also analyze the slope of the moving average line to evaluate the strength of the downward trend. It can be determined that the downward trend is stronger when the slope of the moving average line is negative and its absolute value is large.

[0099] In addition, the AI-based analysis module (120) can monitor the rate of change in the divergence between the current price and the moving average line. In the section where the divergence decreases rapidly, the buying point can be adjusted by considering the possibility of further decline.

[0100] The judgment results of such (b-1) steps are updated in real time and are configured to be immediately reflected in response to changes in market conditions.

[0101] FIG. 5 is a diagram showing the detailed process of step (b-2) of the bear market stage judgment algorithm performed by the AI-based analysis module (120) in a financial product operation and provision system utilizing a Martingale investment strategy according to one embodiment of the present invention.

[0102] As illustrated in FIG. 5, step (b-2) may include step (b-2-1) of analyzing the level of divergence from the N-day moving average line over a previously set period of time of the investment asset to set a judgment criterion value for determining a bear market.

[0103] At this time, a specific past period can be set considering the periodicity of the market and the volatility of the investment target asset, and generally, periods such as 3 months, 6 months, or 1 year can be used.

[0104] Specifically, the AI-based analysis module (120) can analyze the divergence pattern of cases that succeeded in rebounding after falling in past data and set the divergence level of a statistically significant buying point as a judgment criterion value.

[0105] Furthermore, the judgment threshold can be dynamically adjusted based on the characteristics of the investment asset and market conditions. For example, in a highly volatile market, a lower deviation level can be set as the judgment threshold.

[0106] Additionally, step (b-2) may include step (b-2-2) for determining whether the current divergence of the investment target asset is lower than the judgment criterion value set in step (b-2-1).

[0107] In this judgment process, the AI-based analysis module (120) can analyze not only the absolute level of the deviation but also the speed and pattern of change of the deviation. If the deviation shows a tendency to stabilize near the judgment reference value, it can be judged that there is a high possibility of a rebound.

[0108] In addition, step (b-2) may include step (b-2-3), which determines that the current divergence of the investment target asset is lower than the set judgment threshold value as a result of the judgment in step (b-2-2), and determines that it is an investable downside phase.

[0109] And when the AI-based analysis module (120) determines that the market is in an investable downside phase, it can analyze past cases similar to the market conditions at that time to estimate the expected rebound range and the time required.

[0110] In addition, the AI-based analysis module (120) can supplement the reliability of the judgment of the downward phase by utilizing various auxiliary indicators such as trading volume, volatility, and market sentiment indicators.

[0111] Such a declining market stage judgment algorithm is executed in real time by an AI-based analysis module (120), and is equipped so that judgment criteria and analysis methods can be dynamically adjusted according to changes in market conditions.

[0112] In addition, the result of the market downturn judgment is transmitted to the investment execution module (130) and can be used to determine whether to execute an actual buy order, and can also be used to analyze and improve the performance of the investment strategy in the strategy optimization module (140).

[0113] FIG. 6 is a diagram illustrating the concept of a bear market stage judgment algorithm performed by an AI-based analysis module (120) in a financial product operation and provision system utilizing a Martingale investment strategy according to one embodiment of the present invention.

[0114] As illustrated in FIG. 6, this embodiment presents an example of the actual application of the Martingale investment strategy using graphs and numbers. The graph shows the relationship between the investment amount and the purchase price, and the resulting profit structure.

[0115] Specifically, the purchase amount for each investment stage is displayed on the left side of the graph, and it can be seen that it starts at $100 and increases by double to $200, $400, $800, and $1,600.

[0116] Furthermore, the purchase price for each stage is set to start at $10 and gradually decrease to $9, $8, $7, and $6. This reflects the core principle of the Martingale strategy, which involves investing a larger amount at lower prices whenever the asset price falls.

[0117] Also, the selling price, profit, and expected rate of return for each step are displayed on the right side of the graph. For example, in the first purchase, a profit of $10 and a rate of return of 3% can be obtained when the selling price is $11.0.

[0118] Furthermore, it shows that as the purchase amount increases, greater profits can be realized from the same price rebound. In the final stage, when the selling price is $6.6, a profit of $160 and a return of 52% can be achieved.

[0119]

[0120] In addition, the curves on the graph represent the price trends and rebound zones of the investment asset; the green curve indicates the actual price fluctuations of the asset, and the orange arrows indicate the expected profit range from each buying point to the target selling price.

[0121] Through such diagramming, the AI-based analysis module (120) is equipped to systematically set the purchase amount and target selling price for each stage and to adjust the strategy according to real-time market conditions.

[0122] Specifically, the buy-stage multiples and target rates of return can be flexibly adjusted according to the investor's capital size, risk preference, and market conditions, thereby enabling the simultaneous pursuit of risk management and profit maximization.

[0123] The content illustrated in FIG. 6 as described above is an exemplary embodiment to aid in understanding the present invention, and in actual operation, it may be modified and implemented into various forms of multiple and rate of return structures depending on market conditions and investor conditions.

[0124] FIG. 7 is a diagram showing each process of an investment strategy performance analysis and optimization algorithm performed by a strategy optimization module (140) in a financial product operation and provision system utilizing a Martingale investment strategy according to one embodiment of the present invention.

[0125] As illustrated in FIG. 7, in this embodiment, the strategy optimization module (140) can evaluate the validity of the investment strategy derived by the AI-based analysis module (120) and perform the process of optimizing the trading strategy according to the evaluation result.

[0126] The strategy optimization module (140) can perform step (c-1) of analyzing the profitability of the trading results of the investment target asset by the investment execution module (130). Specifically, the profitability analysis of the trading results may include various performance indicators such as the realized rate of return, maximum loss range, investment period, and recovery speed.

[0127] And the strategy optimization module (140) can perform step (c-2) of deriving effective strategy elements and inefficient elements according to pre-set criteria based on the profitability analyzed in step (c-1).

[0128] In this context, effective strategic elements can refer to the common characteristics of trading cases that have achieved or exceeded target returns. For example, this may include buying timing in specific market conditions, setting multiples, and stop-loss criteria.

[0129] Furthermore, inefficient factors can refer to strategic decisions that lead to reduced returns or increased risk. For example, this may include setting excessive multiples, selecting inappropriate sell points, or applying strategies that do not align with market conditions.

[0130] In addition, the strategy optimization module (140) can perform step (c-3) of updating the trading strategy based on the results derived in step (c-2).

[0131] Specifically, updates to trading strategies may include adjusting criteria for identifying a bear market, optimizing buy multiples, and resetting sell target levels. These updates may be made to reflect changes in the market environment and investors' risk preferences.

[0132] And the strategy optimization module (140) can learn successful strategy patterns from past trading data using a machine learning algorithm and use them to establish new trading strategies.

[0133] In addition, the strategy optimization module (140) can dynamically adjust the risk management criteria of the strategy according to the level of market volatility. In a highly volatile market, conservative multiple settings and strict stop-loss criteria can be applied.

[0134] Such investment strategy performance analysis and optimization algorithms are equipped to adapt to changes in the market environment through continuous learning and improvement, and to achieve stable investment performance.

[0135] And the strategy optimization module (140) feeds the optimized strategy to the AI-based analysis module (120) so that it can be used to improve the accuracy of future investment decisions.

[0136] FIG. 8 is a diagram showing each process of an asset diversification investment and rebalancing algorithm performed by a portfolio management module (150) in a financial product operation and provision system utilizing a Martingale investment strategy according to one embodiment of the present invention.

[0137] As illustrated in FIG. 8, in this embodiment, the portfolio management module (150) analyzes the correlation of a plurality of investment target assets and constructs a portfolio based thereon, and can perform rebalancing by monitoring the asset composition in real time.

[0138] The portfolio management module (150) can perform step (d-1) of analyzing the correlation between multiple investment target assets. Specifically, the correlation between assets can be analyzed through the similarity of price fluctuations, the correlation coefficient of returns, the degree of synchronization of volatility, etc.

[0139] Furthermore, correlation analysis can be performed across various timeframes and market phases to identify relationships between assets in diverse market conditions. For example, correlations may differ between bull and bear markets, and these characteristics can be reflected in portfolio construction.

[0140] Additionally, the portfolio management module (150) can perform step (d-2) of determining the diversification ratio based on the correlation analyzed in step (d-1). At this time, the diversification ratio can be derived through an optimization algorithm based on modern portfolio theory.

[0141] In addition, various characteristics of each asset, such as expected return, volatility, and liquidity, can be considered when determining the diversification ratio. In particular, since securing sufficient liquidity is important due to the nature of the Martingale strategy, a ratio allocation can be made to minimize liquidity risk.

[0142] And the portfolio management module (150) can perform step (d-3) of constructing a portfolio according to the diversification ratio determined in step (d-2). When constructing the portfolio, orders can be executed in a way that minimizes transaction costs and market impact.

[0143] In addition, the portfolio management module (150) can automatically perform rebalancing when the portfolio weight deviates from the target ratio due to changes in market conditions or fluctuations in asset prices.

[0144] Specifically, rebalancing may be performed when a weighting difference exceeding a set threshold occurs, and the decision to execute can be made by comparing transaction costs with the profit improvement effect resulting from the rebalancing.

[0145] In addition, the portfolio management module (150) can perform immediate weight adjustments in addition to regular rebalancing when detecting sudden changes in the market or risk signals of specific assets.

[0146] In addition, continuous monitoring and adjustments can be made to ensure that the overall risk level of the portfolio does not exceed the investor's risk tolerance.

[0147] Such asset diversification and rebalancing algorithms are equipped to diversify the risk of the Martingale strategy and maintain a portfolio structure capable of responding flexibly to market changes.

[0148] Additionally, in this embodiment, the portfolio management module (150) can perform a liquidity analysis algorithm that monitors the liquidity of an investment target asset in real time to determine whether trading is possible and recommends an alternative asset if the liquidity is below a threshold.

[0149] Specifically, liquidity analysis can be performed through various indicators such as trading volume, bid-ask spreads, and market depth. Trading volume represents the market trading activity of the asset in question, while the bid-ask spread, the difference between the bid and ask prices, can serve as an indicator to assess the immediacy of transactions.

[0150] And market depth refers to the order volume by bid price, through which price shocks that may occur during large-scale trading can be predicted. The portfolio management module (150) can evaluate liquidity risk by comprehensively analyzing these indicators.

[0151] Additionally, the portfolio management module (150) can set appropriate liquidity thresholds for each asset. The thresholds can be determined by considering the size of the investment amount, the expected trading frequency, and the multiple buying characteristics of the Martingale strategy.

[0152] In addition, if liquidity decreases below a threshold, the portfolio management module (150) can search for and recommend an alternative asset that has sufficient liquidity while having price volatility and return characteristics similar to the asset.

[0153] In this case, alternative asset recommendations can be made across various financial product groups such as ETFs, futures, and options, and the optimal alternative can be selected by comprehensively considering the price correlation with the original investment target asset, volatility characteristics, and transaction costs.

[0154] And the portfolio management module (150) can perform phased position adjustments on assets where liquidity risk has been detected. This can minimize market shock caused by sudden position changes and enable orderly asset replacement.

[0155] Such a liquidity analysis algorithm is equipped to enable stable investment operations by verifying the feasibility of the Martingale strategy in real time and preemptively managing liquidity risk.

[0156] The components and algorithms of a financial product operation and provision system utilizing a Martingale investment strategy according to one embodiment of the present invention have been described in detail above. Below, additional components and algorithms that may be applied in the present invention will be described.

[0157] Additionally, in this embodiment, the AI-based analysis module (120) can implement a hybrid risk management system that combines an option strategy and a Martingale strategy.

[0158] The AI-based analysis module (120) can execute a put option buying strategy for the asset when a downward phase of the investment target asset is detected. Here, a put option refers to the right to sell a specific asset at a predetermined price and is a derivative product that can generate profit when the asset price falls.

[0159] At this time, the strike price (the price at which the option buyer can sell the underlying asset) and the expiration date (the period for exercising the option's rights) of the put option can be selected by considering the average purchase price and expected investment period of the Martingale strategy.

[0160] And the AI-based analysis module (120) can adjust the size of the option position by monitoring volatility indicators in real time, such as the VIX index (volatility index of the Chicago Options Exchange) or implied volatility (market expected volatility reflected in the option price). The option hedge ratio can be increased during periods when volatility rises rapidly, and lowered during periods when volatility stabilizes.

[0161] Additionally, the AI-based analysis module (120) can analyze and manage the risk of a position by utilizing Greek indicators of the option. Among the Greek indicators, Delta represents the rate of change of the option price in relation to changes in the underlying asset price, Gamma represents the rate of change of Delta, and Vega represents the sensitivity of the option price to changes in volatility. Through these indicators, the sensitivity of the option position to changes in price and volatility can be measured and utilized for risk management of the Martingale strategy.

[0162] In addition, the investment execution module (130) can automatically build an appropriate level of option hedge position whenever a step-by-step purchase of the Martingale strategy is executed. At this time, the hedge ratio and option type can be optimized by considering the option premium (cost required to purchase options).

[0163] Such an option hedging strategy is designed to limit the risks of the Martingale strategy that may occur in extreme downturns, while preserving the possibility of realizing profits in upturns.

[0164] And the strategy optimization module (140) can continuously analyze the cost-effectiveness of the Martingale strategy and the option hedging strategy to derive the optimal hedging ratio (the ratio of option positions set to hedge against risk) according to market conditions.

[0165] In addition, the portfolio management module (150) can comprehensively manage the risk of the entire portfolio, including option positions. It is equipped to adjust the risk level of the entire portfolio by considering the correlation between the option and the underlying asset (the source asset that is the subject of the option).

[0166] Next, in this embodiment, the AI-based analysis module (120) can implement a market volatility prediction algorithm utilizing information entropy theory.

[0167] Specifically, the AI-based analysis module (120) can quantify the price fluctuation of an investment asset as information entropy. Here, information entropy is an indicator that quantifies the disorder or uncertainty of a system and can be calculated based on Shannon's information theory.

[0168] And the AI-based analysis module (120) can measure the rate of change of information entropy over time. At this time, the rate of change of entropy indicates how predictable the pattern of price fluctuation is, and a section where the rate of change increases rapidly can be interpreted as a section where market uncertainty increases.

[0169] Additionally, the AI-based analysis module (120) can learn the correlation between information entropy and actual price volatility. Through this, when the entropy indicator exceeds a specific threshold, it can predict the range of price volatility that may occur in the future.

[0170] In addition, the investment execution module (130) can adjust the buying phase of the Martingale strategy by utilizing predicted volatility information. For example, the buying interval can be set wide in the high-entropy range and narrow in the stable-entropy range.

[0171] In this case, entropy calculations can be performed across various time frames, and the complex uncertainty structure of the market can be identified through a combination of short-term, medium-term, and long-term entropy indicators.

[0172] And the strategy optimization module (140) can continuously evaluate the accuracy of the entropy-based prediction and dynamically adjust the entropy calculation parameters according to market conditions. These parameters may include the entropy calculation interval, threshold level, weight, etc.

[0173] In addition, the portfolio management module (150) can evaluate the level of uncertainty of the entire portfolio by comprehensively analyzing the entropy indicators of various assets. Through this, the asset allocation ratio within the portfolio can be adjusted, and the risk of the entire portfolio can be managed.

[0174] Unlike existing statistical volatility indicators, such an entropy-based volatility prediction system is equipped to enable a more fundamental assessment of market risk by analyzing market disorder and uncertainty from an information-theoretic perspective.

[0175] In addition, in this embodiment, the AI-based analysis module (120) may utilize the information entropy-based volatility prediction algorithm described above to complement the bear market judgment and buy decision of the Martingale strategy.

[0176] Specifically, the AI-based analysis module (120) can perform information entropy analysis along with moving average-based analysis when performing steps (b-1) and (b-2) of the bear market stage judgment algorithm. Here, information entropy is an indicator that quantifies the disorder or uncertainty of a system and can be calculated based on Shannon's information theory.

[0177] In addition, the AI-based analysis module (120) can consider the rate of change in information entropy during the corresponding period when analyzing the divergence from the N-day moving average line. Sections where the divergence increases and the entropy rises rapidly at the same time can be judged to have a high probability of a significant rebound in the future.

[0178] In addition, when applying multiple purchases of the Martingale strategy, the AI-based analysis module (120) can dynamically adjust the purchase size according to the entropy level. A basic multiple can be applied in a stable section with low entropy, and a conservative multiple can be applied in an unstable section with high entropy.

[0179] In addition, the strategy optimization module (140) can analyze the correlation between the entropy level and the rate of return at each trading point when analyzing the profitability of the investment results. Through this, the optimal entropy threshold and trading strategy parameters can be derived.

[0180] And the portfolio management module (150) can consider the entropy level of each asset when determining the asset diversification investment ratio. The portfolio can be adjusted by lowering the investment weight of assets showing high entropy and increasing the weight of assets showing stable entropy.

[0181] Such entropy-based analysis can complement the existing Martingale strategy's bear market judgment and buy decision-making, enabling more stable investment execution that takes market uncertainty into account.

[0182] Preferred embodiments according to the present invention have been described above, and it is obvious to those skilled in the art that, in addition to the embodiments described above, the present invention may be embodied in other specific forms without departing from the spirit or scope thereof. Therefore, the embodiments described above should be regarded as illustrative rather than restrictive, and accordingly, the present invention is not limited to the description above but may be modified within the scope of the appended claims and their equivalents.

Claims

1. A data collection module that collects investment market-related data, including price fluctuations and trading trends in the investment market, and investor asset status data, including the investor's target assets and investment direction; An AI-based analysis module that analyzes the investment market-related data and the investor asset status data based on each data collected by the data collection module, automatically determines the purchase of the investment target asset according to a pre-set multiple purchase rule when the investment target asset is in a bear market, and determines the sale point of the investment target asset when the investment target asset rebounds; and An investment execution module that executes the purchase and sale of the investment target asset based on the decision of the AI-based analysis module; including, Financial product management and provision system utilizing the Martingale investment strategy.

2. In Paragraph 1, The above data collection module is, Step (a-1) of analyzing the price fluctuation pattern and trading volume trend of the investment target asset from the investment market data; (a-2) step of calculating the investable amount from the above investor asset status data and the diversification ratio of the above investment target assets; and Step (a-3) for setting step-by-step buying volume and selling target levels; Performing an initial investment strategy setting algorithm including, Financial product management and provision system utilizing the Martingale investment strategy.

3. In Paragraph 1, The above AI-based analysis module is, Step (b-1) of performing a first bear market determination of the above investment target asset; and Step (b-2) of performing a final bear market determination of the above investment target asset; Performing a bear market stage judgment algorithm including, Financial product management and provision system utilizing the Martingale investment strategy.

4. In Paragraph 3, The above step (b-1) is, (b-1-1) step of calculating the divergence between the current price of the above-mentioned investment target asset and the N-day moving average line (N: a pre-set natural number); (b-1-2) step of determining whether the current price of the above investment target asset is located below the above N-day moving average line; and Step (b-1-3) in which, as a result of the judgment in Step (b-1-2) above, the price of the investment target asset is located below the N-day moving average line, it is determined as an initial bearish signal; including, Financial product management and provision system utilizing the Martingale investment strategy.

5. In Paragraph 4, The above step (b-2) is, Step (b-2-1) of analyzing the level of divergence from the N-day moving average line of the above investment target asset during a previously set past period to set a judgment criterion value for determining a bear market; Step (b-2-2) for determining whether the current divergence of the above-mentioned investment target asset is lower than the judgment criterion value set in step (b-2-1); and Step (b-2-3) in which, as a result of the judgment in Step (b-2-2) above, the current divergence of the investment target asset is lower than the set judgment criterion value, and it is determined to be an investable downside phase; including, Financial product management and provision system utilizing the Martingale investment strategy.

6. In Paragraph 1, A strategy optimization module further comprising analyzing the results of buying and selling the investment target asset by the investment execution module, evaluating the validity of the investment strategy derived by the AI-based analysis module, and optimizing the trading strategy according to the evaluation result. Financial product management and provision system utilizing the Martingale investment strategy.

7. In Paragraph 6, The above strategy optimization module is, (c-1) step of analyzing the profitability of the trading results of the investment target asset by the investment execution module; Step (c-2) for deriving effective strategic elements and inefficient elements based on pre-established criteria, based on the profitability analyzed in Step (c-1) above; and Step (c-3) of updating the trading strategy based on the results derived in Step (c-2) above; Performing investment strategy performance analysis and optimization algorithms including, Financial product management and provision system utilizing the Martingale investment strategy.

8. In Paragraph 1, A portfolio management module further comprising an analysis of the correlations of the aforementioned investment target assets to construct a portfolio, and real-time monitoring of the asset composition of the said portfolio to perform rebalancing, Financial product management and provision system utilizing the Martingale investment strategy.

9. In Paragraph 8, The above portfolio management module is, Step (d-1) of analyzing the correlation between the plurality of the above-mentioned investment target assets; Step (d-2) for determining the diversified investment ratio based on the correlation analyzed in the above step (d-1); and Step (d-3) of constructing a portfolio according to the diversification ratio determined in Step (d-2) above; Performing an asset diversification and rebalancing algorithm including, Financial product management and provision system utilizing the Martingale investment strategy.

10. In Paragraph 8, The above portfolio management module is, A liquidity analysis algorithm that monitors the liquidity of the above-mentioned investment target asset in real time to determine whether trading is possible, and recommends alternative assets if the liquidity is below a threshold, Financial product management and provision system utilizing the Martingale investment strategy.

Images