AU2021101320A4 - Bitcoin Price Predictor Using AI-Based Programming - Google Patents

Abstract

Our invention Bitcoin Price Predictor Using Al-Based Programming is a Systems and methods are provided for training an artificial intelligence system including the use of one or more human subject responses to stimuli as input to the artificial intelligence system. The Invention is a financial transaction between a customer and merchant wherein the customer can pay in any currency and the merchant can be paid in any currency and to supports payment using crypto currency, while improving such transactions in a way that takes advantage of benefits of such transactions while overcoming drawbacks such as delays in processing. The invention is to predict the Bitcoin price accurately taking into consideration various parameters that affect the Bitcoin value andby gathering information from different way and applying in real time. The invention is also Each and every way has its own set of methodologies of bitcoin price prediction and Many way has accurate price but some other don't, but the time complexity is higher in those predictions, so also to reduce the time complexity. The invention to use an algorithm linked to artificial intelligence named LASSO (least absolute shrinkage selection operator and the way used different algorithms like SVM(support vector machine), CoinMarketCap, Quandl, GLM, CNN (Convolutional Neural Networks) and RNN (Recurrent neural networks) etc. The Invented technology the Bitcoin market while gaining insight into optimal features surrounding Bitcoin price and our data set consists of various features relating to the Bitcoin price and payment network over the course of every year, recorded daily. The invented technology also a preprocessing the data's we apply some data mining techniques to reduce the noise of data and then the second moment of our invention using the available information we will predict the sign of the daily price change with highest possible accuracy. 18 MODULEFDR DATA 1DEEMN & ' :PREDICM0 DATA MDUL2 FOR - ERRORAND asA asgen i ECMN MOLE FORns PRinEO TIMO! (M SAPLES GROUP DATA PilEMSULY RESULT BY CTO DATA ANDPE 4imAD USE UTUTG LN PROCBEWMQ TARGN~~2 GROUPOF UPPER AND DATA DATA LOWER BOUlNDSOP CO0NIECE MODU0LE FOR LEVML. 54 ~ DATA M DATA FIG. 7 is a flow chart illustrating the universal time series prediction system

Description

MODULEFDR

DATA 1DEEMN

&' :PREDICM0 DATA MDUL2 FOR - ERRORAND asA asgen i ECMN MOLE FORns PRinEO TIMO! (M SAPLES GROUP DATA PilEMSULY RESULT BY CTO DATA ANDPE 4imAD USE UTUTG LN PROCBEWMQ TARGN~~2 GROUPOF UPPER AND DATA DATA LOWER BOUlNDSOP CO0NIECE MODU0LE FOR LEVML. 54 ~ DATA

MDATA

FIG. 7 is a flow chart illustrating the universal time series prediction system

Bitcoin Price Predictor Using A-Based Programming

FIELD OF THE INVENTION

Our Invention is related to a Bitcoin Price Predictor Using Al-Based Programming

BACKGROUND OF THE INVENTION

Bitcoin is a cryptographic money which is utilized worldwide for advanced installment or basically for speculation purposes. Bitcoin is decentralized for example it isn't possessed by anybody. Exchanges made by Bitcoins are simple as they are not attached to any nation. Speculation should be possible through different commercial centers known as "bitcoin trades". These enable individuals to sell/purchase Bitcoins utilizing various monetary forms. The biggest Bitcoin trade is Mt Gox.

Bitcoins are put away in an advanced wallet which is essentially similar to a virtual financial balance. The record of the considerable number of exchanges, the timestamp information is put away in a spot called Block chain. Each record in a block chain is known as a square. Each square contains a pointer to a past square of information. The information on block chain is scrambled. During exchanges the client's name isn't uncovered, however just their wallet ID is made open. The Bitcoin's worth fluctuates simply like a stock though in an unexpected way.

There are various calculations utilized on financial exchange information for value forecast. Notwithstanding, the parameters influencing Bitcoin are extraordinary. In this manner it is important to anticipate the estimation of Bitcoin so right venture choices can be made. The cost of Bitcoin doesn't rely upon the business occasions or mediating government not at all like securities exchange. Hence, to anticipate the worth we feel it is important to use Al innovation to foresee the cost of Bitcoin.

History shows that many trusted systems have evolved in order to provide for efficient functioning of society and business. Generally, these have involved central control of systems in order to ensure compliance with rules. Within the gaming space, examples include lotteries and regulated gaming. By way of example, the Nevada Gaming Control Board monitors institutions within the state for compliance with laws and regulations. and ensures the fair and efficient functioning of the industry.

Consider the entertainment and gaming system background. A lottery is a 'State' Function and serves as a form of 'trusted agent'. The classic definition of the elements of a lottery are prize, chance and consideration. When these elements are reordered into a more chronologically correct order, namely first, receipt and holding of the consideration (e.g., ticket purchases), chance (e.g., ensuring a fair and accurate random number generator) and prize (i.e., paying the prize to the true winner.)

Therefore, the State acts as a 'trusted agent' as it holds the consideration, guarantees randomness of the 'chance', and pays out the prize (title transfer). 'Trust' is based on the Integrity and Trustworthiness of People Operating the System and the Regulators Who Oversee the System. Lotteries or State Regulators are often former law enforcement. The degree of trust in the Regulators is often based on time and track record, e.g., the State of Nevada Regulatory system is considered highly trustworthy and effective, based in part on a multi-decade long track record. Additionally, a State with the most business to lose from a loss of trust in the regulatory process is most motivated to provide regulation. Such systems are based on central control of the system.

A casino is a 'state regulated' function and a form of 'trusted agent' with 'verification'. They are licensed by the State and subject to state inspection.

Various advancements have been made in the gaming and entertainment environment. The following are assigned to the assignee of this, and are hereby incorporated by Reference as if fully set forth herein: Games, And Methods For Improved Game Play In Games Of Chance And Games Of Skill, U.S. Pat. No. 6,565,084, Games, and Methods and Apparatus for Game Play in Games of Chance, U.S. Pat. No. 6,488,280, Games, and Methods and Apparatus for Game Play in Games of Chance, U.S. Pat. No. 6,811,484, Apparatus and Method for Game Play in an Electronic Environment, U.S. Pat. No. 8,393,946, Apparatus, Systems and Methods for Implementing Enhanced Gaming and

Prizing Parameters in an Electronic Environment, U.S. Pat. No. 7,798,896, Apparatus, Systems and Methods for Implementing Enhanced Gaming and Prizing Parameters in an Electronic Environment, U.S. Pat. No. 8,241,110, Methods and Apparatus for Enhanced Play in Lottery and Gaming Environments, U.S. Pat. No. 8,727,853, Methods and Apparatus for Enhanced Interactive Game Play in Lottery and Gaming Environments, U.S. Pat. No. 8,241,100, Method and System for Electronic Interaction In A Multi-Player Gaming System. U.S. Pat. No. 8,535,134. Generally, they comprise a suite of tools to make systems more engaging, and to optimize results.

One vexing problem in larger systems results from systems incompatibility. Various components often come from various vendors. There is often a lack of interoperability and incompatibility. Various systems in the gaming ecosystem need to interoperate, including but not limited to: gaming operations, marketing, CRM (Customer Relationship Management), loyalty programs, Ancillary Points or Credits, System Analytics and Optimization, and account and audit functions.

Software Defined Systems are a collection of modules interoperated under a higher level of software control. These manage network services through abstraction of lower level functionality. Generally, there is an Application Plane, a Control Plane and a Data Plane. Examples include Software Defined Networks having a Control Plane which provides intelligent control of data plane composed of relatively less intelligent switches, routers, storage. Yet another example is software defined radio. The control plane monitors and supervises use of frequency bands in the data plane.

Virtual currencies and especially crypto currencies such as bitcoin, ethereum (ether), litecoin, etc. have been increasing in popularity in recent years. Holders of bitcoin and other crypto currencies are not tied to any government, are decentralized, and allow direct transactions, while still maintaining the trust and stability of fiat currencies. Bitcoin in particular appears to be more than a passing fad and with billions in total value in distribution, bitcoin stores significant economic potential.

However, despite the popularity of crypto currencies to date, all crypto currencies face the same drawback in that they are not widely accepted. Presently, crypto currencies, like bitcoin, are not accepted by most retail merchants, or even by most online merchants. The lack of mass adoption of crypto currencies thus far may be attributed to a number of different factors. For one, crypto currency exchange rates with fiat currencies can fluctuate widely, and this may be a risk that business owners don't want to take.

Furthermore, cryptocurrencies are known to be associated with long transaction times. It is not practical for a coffee shop to sell a coffee in a transaction that could take hours before the transaction is confirmed by recording the transaction to the block chain. A further deterrent to accepting cryptocurrencies by merchants is that cryptocurrencies are associated with anonymous identities. This feature of digital currency makes it susceptible to money laundering activities, and exposes merchants to increased chances of transacting with criminals, which may put them in violation of state and federal laws.

In the recent past, Recurrent Artificial Neural Networks have successfully improved the quality of forecasting of share movements in relation to its statistically based counterparts. The known recurrent neural networks (RNN) make a prediction of the appreciation potential of each stock based on the available historical data. The training process continues until at least one stopping criterion is met. Such criteria include the determination that the connections between the nodes of the net have reached a steady state, that the error between the predicted output and the actual target values is less than a certain threshold, or that a predefined time period has elapsed without any improvement in the net's performance.

Once the neural nets for each stock of the capital market have been trained and tested on the available historical data the neural nets are tied to surpass the underlying market benchmark by predicting, the task becomes one of holding a smaller subset of all stocks of the market, such that this subset has a higher expected return and about the same level of risk as the market index. Such a task requires one to focus on individual stocks and their performance in relation to the index that serves as the underlying performance benchmark.

Individual stocks usually have their own unique performance characteristics some of which can be quantified. Clearly, however, the relationships among such data are complicated and frequently non-linear, making them difficult to analyze. In summary, an investment decision in the modern capital markets requires processing of large volumes of data and taking into account a number of factors which may exhibit significant non-linear relationships among different components of the data.

Computers, in general, are very adept at dealing with large amounts of numerical information. However, sophisticated techniques are required to analyze and combine disparate information that can potentially impact security prices. Several expert computer systems have been deployed in the domain of finance, including some in the area of investment management.

In the past several years, recurrent neural networks (RNN) have become popular in solving a variety of problems. Neural nets mimic the ability of the human brain to recognize recurring patterns that are not just identical but similar. A neural net can predict the value of one variable based on input from several other variables that can impact it. The prediction is made on the basis of an inventory of patterns previously learned, seeking the most relevant in a particular situation. In summary, RNNs can "learn" by example and modify themselves by adjusting and adapting to changing conditions. Several applications of neural nets to the domain of finance are already known in the art. Typically, the RNN prediction systems are "self' trained by adjusting weights and biases as a result of numerous repetitions. What the known systems typically do not do is to calculate an error function so the system's output can be adjusted or controlled in accordance with the determined error.

U.S. Pat. No. 5,109,475 to Kosaka et al. discloses a neural network for selection of time series data. This process is illustrated in a particular application to the problem of stock portfolio selection. In the first step of the proposed process, certain characteristics for each security are calculated from time series data related to the security. The characteristics to be computed include the historical risk (variance and co-variance) and the return.

The following step involves the establishment of a performance function based on the calculated characteristics and, in the third step of the process, a Hopfield neural network is used to select a subset of securities from a predefined universe. Due to the fact that the Kosaka system only considers historical risk and return data, and implicitly assumes that the relationship between risk and return factors will remain stable in the future, in a typical rapidly changing market environment, it is unlikely to predict accurately price variations which are subject to complicated non-linear relationships.

U.K Pat. application 2 253 081 A to Hatano et al. discloses a neural net for stock selection using only price data as input. The main idea of the proposed system is to calculate runs (sequences) of price trends, increases and decreases, using a point-and figure chart and using the maximum and minimum values from the chart to make a time-series prediction using a neural network. As in the previous case, the Hatano system only uses historic price data which places limitation on the type and quality of predictions that may be achieved. Additionally, the use of only the external points of the price chart obscures even further information about any time dependencies that might be present in the original data.

The above-described financial systems do not fully utilize the potential of the neural nets for stock selection. Notably missing is the possibility to develop the standard adaptive training procedure of the RNN to determine a prediction error or function in accordance to which the RNN output can be controlled. Further, many of the known investment management systems have not been able to effectively output the upper and lower error bounds at a given confidence level. Further, the movements of the stock prices, as well as price movements of other financial instruments, generally present a deterministic trend superimposed with some "noise" signals, which are, in turn, composed of truly random and chaotic signals, as illustrated in FIG.1. Deterministic trends can be detected and assessed by some maximum-likelihood processes.

Although a truly random signal, often represented by a Brownian motion, is unpredictable, it can be estimated by its mean and standard deviation. The chaotic signal, seemingly random but with deterministic nature, proves predictable to some degree by means of several analysis techniques, among which the ANN techniques have proven most effective over the widest range of predictive variables. However, this trend is largely ignored by the above-discussed references. As a result, at least some of the known systems are fed with data including this deterministic trend that influences the training stage of the known systems. Overall, many of the known systems are limited for the prediction of specific types of securities and data, such as the price of a single stock and, thus, cannot be universally applied to any financial time series, price series and volatility series.

It is, therefore, desirable to provide a prediction system based on the recurrent Al Artificial Neural Network (ANN) architecture which is able to output upper and lower predictions bounds at any given confidence level. Also, an ANN prediction that can be applied to financial time series, price series and volatility series, for single securities and for portfolios of securities is desirable. A universal prediction system employing a pipeline recurrent neural network (PRNN), which provides the satisfactory accuracy of the nonlinear and adaptive prediction of no nstationary signal and time series processes is also desirable. Further, a universal ANN prediction system having high computation efficiency and multi-stage adaptive supervised training process is also desirable.

OBJECTIVES OF THE INVENTION

1. The objective of the invention is to a systems and methods are provided for training an artificial intelligence system including the use of one or more human subject responses to stimuli as input to the artificial intelligence system. 2. The other objective of the invention is to a financial transaction between a customer and merchant wherein the customer can pay in any currency and the merchant can be paid in any currency and to supports payment using crypto currency, while improving such transactions in a way that takes advantage of benefits of such transactions while overcoming drawbacks such as delays in processing.

3. The other objective of the invention is to a predict the Bitcoin price accurately taking into consideration various parameters that affect the Bitcoin value and by gathering information from different way and applying in real time. 4. The other objective of the invention is to a Each and every way has its own set of methodologies of bitcoin price prediction and Many way has accurate price but some other don't, but the time complexity is higher in those predictions, so also to reduce the time complexity. 5. The other objective of the invention is to a algorithm linked to artificial intelligence named LASSO (least absolute shrinkage selection operator and the way used different algorithms like SVM (support vector machine), CoinMarketCap, Quandl, GLM, CNN (Convolutional Neural Networks) and RNN (Recurrent neural networks) etc. 6. The other objective of the invention is to a technology the Bitcoin market while gaining insight into optimal features surrounding Bitcoin price and our data set consists of various features relating to the Bitcoin price and payment network over the course of every year, recorded daily. 7. The other objective of the invention is to a preprocessing the datas we apply some data mining techniques to reduce the noise of data and then the second moment of our invention using the available information we will predict the sign of the daily price change with highest possible accuracy.

SUMMARY OF THE INVENTION PREDICTION TECHNIQUES

Linear regression model In linear regression is a linear approach to modeling the relationship between a dependent variable and independent variables. The case of linear variable is called simple linear regression [8]. In this paper I am using the linear regression model for relationship between a dependent variable and one or more independent variables. B. K-Nearest Neighbor K-means creates k groups from a set of objects so that the members of a group are more similar and based on this data is clustered as normal, stressed or highly stressed.

We can compute the distance between two dependent and independent variables using some distance function d(x, y), where x,y are scenarios composed Number of features, such that x={x1,...,xN}, y={y1,...,yN} . Break the principal third of the information into all conceivable back to back interims of sizes 180s, 360s and 720s. Apply k-implies grouping to recover 100 bunch communities for every interim size, and afterward use test Entropy to limit these down to the 20 best/generally fluctuated and ideally best bunches. Utilize the second arrangement of costs to figure the comparing loads of highlights discovered utilizing the Bayesian relapse strategy.

The relapse fills in as pursues. At time t, assess three vectors of past costs of various time interims (180s, 360s and 720s). For each time interim, ascertain the comparability between these vectors and our 20 best kmeans designs with their realized value hop, to locate the probabilistic value change dp. Compute the loads, for each component utilizing a Differential Advancement enhancement work. [3]. The third arrangement of costs is utilized to assess the calculation, by running the equivalent Bayesian relapse to assess highlights, and consolidating those with the loads determined in stage 2 C. Naive Bayes Naive Bayes techniques are a great deal of coordinated learning figurings reliant on applying Bayes' speculation with the "honest" supposition of opportunity between each pair of features.

Overlooking their plainly over-improved suppositions, guiltless Bayes classifiers have worked very well in some genuine conditions. They require a limited measure of preparing information to survey the critical parameters. Honest Bayes understudies and classifiers can be unbelievably speedy appeared differently in relation to progressively present day systems. The decoupling of the class prohibitive component dispersals suggests that each movement can be uninhibitedly evaluated as a one dimensional scattering. This along these lines decreases issues originating from the scourge of dimensionality.

We used the execution gave by Scikit-make sense of how to this. D. Random Forests Random Forests get the outfit learning framework where distinctive weak understudies are merged to make a strong understudy. It is a meta estimator that fits various decision tree classifiers on various sub-primer of the enlightening assortment and use averaging to improve the farsighted accuracy and authority over fitting.

The sub-test size is reliably proportional to the rule data test. We used the use gave by Scikit-see how to this. 1) Build three-time arrangement informational indexes for 30, , and 120 minutes (180, 360, 720 information focuses individually) going before the present information point at all focuses in time separately. 2) Run GLM/Random Forest on each of the two-time series data sets separately. 3) We get two separate linear models: M1, M2 corresponding to each of the data sets. From M1, we can predict the price change at t, denoted AP1. Similarly, we have AP2 for M2. E. CoinMarketCap: CoinMarketCap keeps a track of all the cryptocurrencies available in the market. They keep a record of all the transactions by recording the amount of coins in circulation and the volume of coins traded in the last 24-hours.

They continuously update their records as they receive feeds from various crypto currency exchanges [1]. CoinMarketCap provides with historical data for Bitcoin price changes. 1) Log Normalization: In this method, the range is compressed and we get the values that were close to zero before normalization. The function is: A'= log(A)/log(max) 2) Standard deviation normalization: Here, we take into consideration the difference of every value with respect to the mean value.

The advantage of this technique is that we get the negative values as well due to proper compression of the Y axis. The formula is z = (x - t) / o-. 3) Z score normalization: This method uses technique similar to standard deviation method by considering the mean value. 5) Boxcox normalization: The function used is: data(X)=(dataAX-1)/X .... is not = 0 data(X)=log(data) . . X is = 0 The sudden changes in data are observed significantly in this type of normalization, so that the data can be processed more accurately.

Algorithm A. Least Absolute shrinkage selection operator(LASSO)

In estimations and Al, rope (least absolute shrinkage selection operator or LASSO) is a lose the faith assessment framework that performs both variable choice and regularization so as to refresh the check exactness and interpretability of the legitimate model it produces. Diverse tie assortments have been made so as to fix certain constraints of the fundamental strategy and to make the system dynamically huge for unequivocal issues. In every practical sense these emphases on as for or using various sorts of conditions among the co variates. Adaptable net regularization fuses an extra edge lose the faith like order which improves execution when the measure of markers is more noteworthy than the model size, enables the technique to pick ardently related factors together, and improves generally want accuracy.

Systems and methods are provided for training an artificial intelligence system including the use of one or more human subject responses to stimuli as input to the artificial intelligence system. One or more displays are oriented toward the human subjects to present the stimuli to the human subjects. One or more detectors serve to monitor the reaction of the human subjects to the stimuli, the detectors including at least motion detectors, the detectors providing an output.

An analysis system is coupled to receive the output of the detectors, the analysis system providing an output corresponding to whether the reaction of the human subjects was positive or negative. A neural network utilizes the output of the analysis system to provide a positive weighting for training of the neural network when the output of the analysis system was positive, and a negative weighting for training of the neural network when the output of the analysis system was negative.

Accordingly, an inventive universal ANN prediction system motivated in its design by the human nervous system is capable of learning by training to generalize from special cases and outputting a three-line band to forecast short-term movements of stock prices.

Referring to one aspect of the invention, a supervised training and prediction system is so trained that the online investors are presented with the forecast of short-term movements of stock prices in a scientific way. Particularly, a three-line presentation that defines a confidence range or level, within which a price stock is predicted to fluctuate, enables the online investors to obtain a good understanding of the possible stock prices in a probability sense.

Such presentation becomes possible due a training procedure of a Al-based ANN prediction system in accordance with the invention. Particularly, a training set, which includes the input data for the ANN to "see" and the known target data for ANN to learn to output, is first collected. For stock price predictions, for example, the training set and target data would naturally be historical stock prices.

A vector of 100 consecutive historical stock prices, for instance, can constitute a training data and the 101st stock price can be a target datum. The inventive process further is characterized by feeding the input data to ANN; compare ANN output with the known target, and adjust ANN's internal parameters (weights and biases) so that ANN output and the known target are close to one another-more precisely, so that a certain error function is minimized. Further, the process is characterized by feeding ANN some future input data (not seen by ANN); if ANN is well trained and if the input data is predictable, then ANN will give accurate predictions.

The inventive system is essentially an Artificial Neural Network trained for adaptive prediction of stock prices. During the prediction process, the inventive system (TradetrekTm Neuro-Predictorm) determines whether a particular stock is predictable with the accuracy required for a statistically significant prediction. This is accomplished, essentially, by comparing the ANN validation error against stock price fluctuations. We know that stocks with larger chaotic components and smaller truly random components tend to be more predictable than others.

In accordance with still another aspect of the invention, the deterministic or expected trend of the chaotic component of a signal representing the evaluated time-series data is determined in accordance with log-linear chisquared linear least squares based on the Black-Scholes stock price formula. The Black-Scholes formula, or other option pricing formula, is used to determine expected option costs in determining necessary hedging and pricing. The Black-Scholes formula provides an option cost based upon index price, exercise price, option term and assumptions of risk free rates of return, average dividend yield, and volatility of returns (standard deviation of returns). The trend is removed before feeding the data to the ANN engine and added back to the data in the post processing stage of the inventive process.

Overall, the simplified ANN (supervised) training and prediction process can be illustrated by the following steps.

Stage One:

Collect the training set, which includes the input data for the ANN to "see" and the known target data for ANN to learn to output. For stock price predictions, for example, the training set and target data would naturally be historical stock prices. A vector of 100 consecutive historical stock prices, for instance, can constitute training data and with the 101st stock price as a target datum.

Stage Two:

Feed the input data to ANN; compare ANN output with the known target, and adjust ANN's internal parameters (weights and biases) so that ANN output and the known target are close to one another-more precisely, so that a certain error function is determined and further minimized.

Step Three:

Feed ANN some future input data (not seen by ANN); if ANN is well trained and if the input data are predictable, then ANN will give accurate predictions.

The inventive system has managed to yield prediction refinements well beyond those of other systems by employing a pipelined recurrent ANN architecture (best for time series prediction) and an adaptive supervised training procedure.

It is, accordingly, an object of the present invention to provide an artificial neural network system operating with a determined error function for data processing and predicting stock prices at a given confidence level.

It is yet another object of the present invention to develop a process for stock prediction on the basis of evaluation of the collected data using a neural network system.

Yet another object of the present invention is to provide a data processing system based on an artificial neural network employing a pipelined recurrent ANN architecture to provide the satisfactory accuracy of the nonlinear and adaptive prediction of time series process.

A further object of the invention relates to a component object module (COP) technique allowing any COM support computer languages and applications to call the inventive prediction system.

BRIEF DESCRIPTION OF THE DIAGRAM

FIG. 1 is a diagrammatic view of a prior art centralized system.

FIG. 2 is a diagrammatic view of a prior art centralized system.

FIG. 3 is a system level block diagram of the program defined entertainment state system (PD-ESS) showing the application plane, the control plane and the state data plane.

FIG. 4 is a system level block diagram explosion of the application state plane layer of the PD-ESS).

FIG. 5 is a system level block diagram explosion of the control plane layer of the PD ESS).

FIG. 6 is a system level block diagram explosion of the state data plane layer of the PD ESS). FIG. 7 is a flow chart illustrating the universal time series prediction system.

DESCRIPTION OF THE INVENTION

The following description is primarily in connection with FIGS. 3, 4, 5 and 6, but may apply to other figures as well. An architecture is provided for a program defined entertainment state system. This preferably serves to decouple the system that controls the overall experience from the underlying systems that define states. The first plane, the application plane provides an interface, primarily for system side users, e.g., developers, organizers of events, contests, lotteries.

The second plane, the control plane, provides for intelligent control, especially cognitive computing, including artificial intelligence and/or machine learning, including artificial intelligence where the system learns over time. This preferably provides an intelligent control layer above modules. The third plane, the state data plane, provides for entertainment 'state modules' with various mechanics, preferably including 'core loop', meta states and provides interfaces for end users, as well as inputs and outputs.

FIG. 3 provides a block Diagram Program Defined Entertainment State System (PD ESS). FIG. 4 is an Explosion of PD-ESS Application Plane Layer, including an application layer GUI (facing the Developers, Affiliates, and Charities). FIG. 5 provides an Explosion PD-ESS controller plane layer. FIG. 6 provides an explosion PD-ESS state data plane layer. Also included are an explosion of entertainment state network element layer, a user interface GUI, an explosion of value/title transfer network element and explosion of other functional blocks.

Turning first to the Application Plane Layer, a program serves to communicate requirements and desired behavior to the PD-ESS Controller. It provides communication between the PD-ESS Application and PD-ESS Controller via the PD-ESS Application Controller Interface (ACI). Application Logic and Drivers are optionally provided. The application layer may receive an abstracted view of State Data Plane Actions. The PD-ESS Applications may interface with higher levels of abstracted control. The system includes an interface, the PD-ESS Application Controller Interface (ACI). The management and administration preferably provides the following: (1) To/From Application Plane, it provides contracts and SLAs, (2) To/from Control Plane Configure Policy, Monitor Performance, and (3) To/From Data Plane Element Setup.

Turning second to the Control Plane Layer, the PD-ESS Controller is ideally logically centralized entity, preferably serves to translate the requirements of the PD-ESS Application to the State Data Plane layer, and provides the Application layer with actions in the State Data Plane (e.g., event information and statistical information). The control plane may provide statistics, events and states from the Data Plane to the Application Plane. The control plane preferably enforces behavior at a low level control in the data plane, provides capability discovery, and monitors statistics and faults. The control plane advantageously includes cognitive computing, such as artificial intelligence (AI) and machine learning (ML), to be described in greater detail, below.

The control plane may optionally include analytics, including but not limited to pattern recognition. Analytics may be performed on a population, preferably a relevant population, or on a subset. Preferably, the subset has similar characteristics of a target user. Data may be binned according to subset. The scope of primary data may be analyzed. Predictive modeling may be included. Responsible Gaming Control may be implemented at the control plane level, especially if there are use rate limits and global limits.

Turning thirdly to the state data plane layer, it preferably includes main subcomponents and Functional Network Elements. Optionally, the functional network elements include some or all of the following. 1. Entertainment State Network Elements, 2. Value/Title Transfer Network Element, 3. Game Library, such as Casino, VLT, Video Gaming, Tournament, Amusement with Prize (AWP), Game Mechanics, Core Loop, Skill, Skill with Reveal, Second Chance, Social, Gamification, Prizing, vGLEPs and Prize Board, 4. Systems, Marketing, Promotions, CRM, Operations, Logistics, Interactive, Mobile/Apps and Responsive Design, 5. Platforms, 6. Channels, 7. Lottery, including Retail and Central Systems, 8. Loyalty, 9. Responsible Gaming Control, optionally including use rate limits and global limits (may be done in the control plane layer as well). 10. Sports, including real world, fantasy and eSports, 11. Other Live Data Entertainment, 12. Networks, including Network communications and web services and 13. Management, including Records, Player Account Management, Reporting, Compliance, including regulatory compliance, security, including cybersecurity, fraud and risk management, including preferably audit and payment.

The Entertainment State Network Elements provide an interface for interaction with a user of the system. An input receives information from user selection. Sensors may be of various forms, including sound sensors, motion sensors, whether 2-d or 3-d, such as including the Microsoft Kinect system. 'Internal Data' consists of data related primarily to game operations. 'External' Data sources to combine with Primary Data Source. These may include 1. Location, 2. Current Activity such as Driving (provided by vehicle, provided by tracked phone) or Exercising (provided by FitBit or similar), 3. Economic Conditions, 4. Weather, 5. Recent Events/News, e.g., a recent Large Powerball win, 6. Marketing Information, 7. e-mail scans, e.g., Google scanning of gmail for content, 8. Social Media, and 9. the Internet of Things (IoT). The Internet of Things (IoT) provide various forms of connected devices such as data sensors. The sensors generate data input "stimuli" to system. By utilizing any form of input, the system is able to provide for massive parallelism. All data "stimuli" to system permits the system to be adaptive and reactive to all data stimuli.

An Output provides stimulation to user. Forms may include: 1. images, such on a display, or via a GUI, or VR system, AR system, 2. Thin Client display with remote computing power, 3. Projections and Holograms, 4. sounds, 5. tactile stimuli, 6. olfactory stimuli, or 7. direct electrical stimuli, neural or otherwise.

A Value/Title Transfer Network Element serves to receive and transfer value (money, coins, and other items of value). Value may refer to fungible liquid asset or other store of value. Title generally refers to ownership of real, personal, or virtual property. A detailed discussion of block chain, trust-less, and crypto currency systems is provided, below.

Artificial Intelligence (Al) is broadly that branch of computer science dealing in automating intelligent behavior. They are systems whose objective is to use machines to emulate and simulate human intelligence and corresponding behavior. This may take many forms, including symbolic or symbol manipulation Al. It may address analyzing abstract symbols and/or human readable symbols. It may form abstract connections between data or other information or stimuli. It may form logical conclusions. Artificial intelligence is the intelligence exhibited by machines, programs or software. It is having been defined as the study and design of intelligent agents, in which an intelligent agent is a system that perceives its environment and takes actions that maximize its chances of success. Yet others have defined it as the science and engineering of making intelligent machines.

Artificial Intelligence often involves use of neural networks. In various embodiments, a multi-layer stack of neural network nodes is utilized. The lowest level comprises granular elements. By way of example in a gaming application, in the order of higher level understanding, the levels would progress from instances of individual action (granular), to core loop detection, to session play, to multi-session play. Optionally, a parsing engine serves to break down or subdivide a larger set, such as a data set or image, into more discrete or granular elements.

Al may have various attributes. It may have deduction, reasoning, and problem solving. It may include knowledge representation or learning. Systems may perform natural language processing (communication). Yet others perform perception, motion detection and information manipulation. At higher levels of abstraction, it may result in social intelligence, creativity and general intelligence. Various approaches are employed including cybernetics and brain simulation, symbolic, sub-symbolic, and statistical, as well as integrating the approaches.

Various tools may be employed, either alone or in combinations. They include search and optimization, logic, probabilistic methods for uncertain reasoning, classifiers and statistical learning methods, neural networks, deep feed forward neural networks, deep recurrent neural networks, deep learning, control theory and languages.

Al advantageously utilizes parallel processing and even massively parallel processing in their architectures. Graphics Processing Units (GPUs) provide for parallel processing. Current versions of GPUs are available from various sources, e.g., Nvidia, Nervana Systems.

Machine Learning is defined as a system that builds up knowledge from experience. Machine learning serves to detect patterns and laws.

Deep Learning uses Neural Al. It is easily scalable, and typically involves more layers or neural Networks (NNs). Neural Networks may be of various forms, including: efficient NN, vectorized NN, vectorized logistic regression, vectorized logistic regression gradient output, binary classification, logistic regression, logistic regression cost function, gradient descent, derivatives, computation graph and logistic regression gradient descent.

Deep neural networks (DNN) often involve Hyperparameters tuning. Typically, they utilize regularization and optimization. Sometimes they are referred to as Deep Belief Network (DBN)

Other forms of neural networks include Convolutional Neural Networks (CNN) or Recurrent Neural Networks (RNN). Examples of available systems include: LSTM, Adam, Caffe, Dropout, Batch Norm, Xavier/He, Python, Scikit-Learn and Tensor Flow.

Al may operate on various forms of data sets. The data set may comprise images, whether video images, 2D Data and/or 3D Data. Sequential data may be analyzed. Examples include, but are not limited to, natural language, audio, autonomous driving decisions, game states and game decisions.

Various industry applications advantageously benefit from application of Al. They include imaging and object detecting, serving to identify, classify, mining and optionally provide sentiment analysis. Other applications include autonomous driving. Yet other applications include robots and robotics. Within healthcare, functions include imaging analysis, diagnosing and gamification. Various forms of sequential data analysis may be enhanced, such as speech recognition, and natural language processing. Music applications include both recognition and synthesis. Within the gaming field, applications include game state sequences detection, analysis, formation, combination optimization, and game optimization. Chat bots and machine translation advantageously employ these systems.

FIG. 7 shows the constituent function blocks within an entertainment or gaming ecosystem. Affiliates serve to acquire customers. Affiliates receive a commission, such as based on the number of users acquired or a percent (%) of revenue. Optionally, there is a link to a credit card function (to be discussed, below).

Next are charities and other organizations that plan to operate a lottery, game or other entertainment event. They provide for customer acquisitions. They are the recipient of the event (game, lottery or entertainment). They also collect a fee.

Next are the developers, who provide for game design. In return for game design, they receive multi-jurisdictional use and payment for use. An enhanced application or app store may be provided wherein the game design may be viewed, selected and downloaded.

Next, consumers provide registration and identification information. The registration data may optionally include identification, age, address and verification. Optionally, the data is sufficient that the system can comply with Know Your Customer (KYC) rules, with optional levels of identity verification. This is stored as persistent history. The customer receives a chance to play, win, and receive entertainment.

Next is the regulator or trust verifying agent. They provide testing, approval for game fairness, overall approval, ensure compliance with regulations and security. The regulator or trust verifying agent is granted access permission by the system to monitoring of every transaction, (analytics dashboard), player accounts, parameters, prize amounts and payouts, and to the complete history. The regulator or trust verifying agent receives compensation, whether a fee or as a percentage of the transaction amounts.

Next, the lotteries serve as the trusted agent, and receive a percentage of the transaction amount. Optionally, the historical functions of the lottery may be eliminated or vaporized from the system when those functions are performed by another entity within the ecosystem.

Hyper parameters and parameters may be used in the Al or machine learning systems. Model parameters are estimated from data automatically. A configuration variable internal to the model can be estimated from data. This can be required by the model when making predictions. Values define the skill of the model. They may be estimated or learned from data.

FIG. 7, a set of M consecutive stock prices is selected and pre-processed at 54 in accordance with the pre-processed process described and fed to ANN which is comprised of a plurality of modules 56, 58 and 62. Each of modules is basically a cell processing a uniform number N<M of the consecutive stock prices and a target data which is a stock price N+1. Thus, a first module 56 is adapted to process a first 1 through N stock prices, generating an output and compare it to the target price, which typically necessitates a certain correction in order to bring the output closer to the target data.

Once the result is satisfactory, a next set of 2 through N+1 stock prices is fed and processed in order to be compared with the target value N+2, after which internal parameters once again are adjusted to minimize a function error of ANN. This process continues until the target data is the last M stock price of the first training set. Subsequently, a second training set previously unseen by ANN is processed at 64 analogously to the first set, but in addition to adjusting the internal ANN parameters, an average prediction error is determined at 66, as will be explained in detail herein below, and any future result transmitted through the communication link as explained.

Claims (8)

WE CLAIM

1. Our invention Bitcoin Price Predictor Using Al-Based Programming is a Systems and methods are provided for training an artificial intelligence system including the use of one or more human subject responses to stimuli as input to the artificial intelligence system. The Invention is a financial transaction between a customer and merchant wherein the customer can pay in any currency and the merchant can be paid in any currency and to supports payment using crypto currency, while improving such transactions in a way that takes advantage of benefits of such transactions while overcoming drawbacks such as delays in processing. The invention is to predict the Bitcoin price accurately taking into consideration various parameters that affect the Bitcoin value and by gathering information from different way and applying in real time. The invention is also Each and every way has its own set of methodologies of bitcoin price prediction and Many way has accurate price but some other don't, but the time complexity is higher in those predictions, so also to reduce the time complexity. The invention to use an algorithm linked to artificial intelligence named LASSO (least absolute shrinkage selection operator and the way used different algorithms like SVM (support vector machine), CoinMarketCap, Quandl, GLM, CNN (Convolutional Neural Networks) and RNN (Recurrent neural networks) etc. The Invented technology the Bitcoin market while gaining insight into optimal features surrounding Bitcoin price and our data set consists of various features relating to the Bitcoin price and payment network over the course of every year, recorded daily. The invented technology also a preprocessing the datas we apply some data mining techniques to reduce the noise of data and then the second moment of our invention using the available information we will predict the sign of the daily price change with highest possible accuracy.

2. According to claims# the invention is to a systems and methods are provided for training an artificial intelligence system including the use of one or more human subject responses to stimuli as input to the artificial intelligence system.

3. According to claim,2# the invention is to a financial transaction between a customer and merchant wherein the customer can pay in any currency and the merchant can be paid in any currency and to supports payment using crypto currency, while improving such transactions in a way that takes advantage of benefits of such transactions while overcoming drawbacks such as delays in processing.

4. According to claiml,2,3# the invention is to predict the Bitcoin price accurately taking into consideration various parameters that affect the Bitcoin value and by gathering information from different way and applying in real time.

5. According to claim,2,3,4# the invention is to Each and every way has its own set of methodologies of bitcoin price prediction and Many way has accurate price but some other don't, but the time complexity is higher in those predictions, so also to reduce the time complexity.

6. According to claim,2,4# the invention is to a algorithm linked to artificial intelligence named LASSO (least absolute shrinkage selection operator and the way used different algorithms like SVM (support vector machine), Coin Market Cap, Quandl, GLM, CNN (Convolutional Neural Networks) and RNN (Recurrent neural networks) etc.

7. According to claim,2,6# the invention is to a technology the Bitcoin market while gaining insight into optimal features surrounding Bitcoin price and our data set consists of various features relating to the Bitcoin price and payment network over the course of every year, recorded daily.

8. According to claim,2,4,6# the invention is to a preprocessing the datas we apply some data mining techniques to reduce the noise of data and then the second moment of our invention using the available information we will predict the sign of the daily price change with highest possible accuracy.

FIG. 1 is a diagrammatic view of a prior art centralized system.

FIG. 2 is a diagrammatic view of a prior art centralized system.

FIG. 3 is a system level block diagram of the program defined entertainment state system (PD-ESS) showing the application plane, the control plane and the state data plane.

FIG. 4 is a system level block diagram explosion of the application state plane layer of the PD-ESS).

FIG. 5 is a system level block diagram explosion of the control plane layer of the PD-ESS).

FIG. 6 is a system level block diagram explosion of the state data plane layer of the PD-ESS).

FIG. 7 is a flow chart illustrating the universal time series prediction system