התחל

Machinelearning

Machine Learning: Logistic RegressionMulti-timeframe Strategy based on Logistic Regression algorithm Description: This strategy uses a classic machine learning algorithm that came from statistics - Logistic Regression (LR). The first and most important thing about logistic regression is that it is not a 'Regression' but a 'Classification' algorithm. The name itself is somewhat misleading. Regression gives a continuous numeric output but most of the time we need the output in classes (i.e. categorical, discrete). For example, we want to classify emails into “spam” or 'not spam', classify treatment into “success” or 'failure', classify statement into “right” or 'wrong', classify election data into 'fraudulent vote' or 'non-fraudulent vote', classify market move into 'long' or 'short' and so on. These are the examples of logistic regression having a binary output (also called dichotomous). You can also think of logistic regression as a special case of linear regression when the outcome variable is categorical, where we are using log of odds as dependent variable. In simple words, it predicts the probability of occurrence of an event by fitting data to a logit function. Basically, the theory behind Logistic Regression is very similar to the one from Linear Regression, where we seek to draw a best-fitting line over data points, but in Logistic Regression, we don’t directly fit a straight line to our data like in linear regression. Instead, we fit a S shaped curve, called Sigmoid, to our observations, that best SEPARATES data points. Technically speaking, the main goal of building the model is to find the parameters (weights) using gradient descent. In this script the LR algorithm is retrained on each new bar trying to classify it into one of the two categories. This is done via the logistic_regression function by updating the weights w in the loop that continues for iterations number of times. In the end the weights are passed through the sigmoid function, yielding a prediction. Mind that some assets require to modify the script's input parameters. For instance, when used with BTCUSD and USDJPY, the 'Normalization Lookback' parameter should be set down to 4 (2,...,5..), and optionally the 'Use Price Data for Signal Generation?' parameter should be checked. The defaults were tested with EURUSD. Note: TradingViews's playback feature helps to see this strategy in action. Warning: Signals ARE repainting. Style tags: Trend Following, Trend Analysis Asset class: Equities, Futures, ETFs, Currencies and Commodities Dataset: FX Minutes/Hours/Days
אינדיקטור Pine Script™
מאת ‎capissimo‎
112
Machine Learning: Perceptron-based strategyPerceptron-based strategy Description: The Learning Perceptron is the simplest possible artificial neural network (ANN), consisting of just a single neuron and capable of learning a certain class of binary classification problems. The idea behind ANNs is that by selecting good values for the weight parameters (and the bias), the ANN can model the relationships between the inputs and some target. Generally, ANN neurons receive a number of inputs, weight each of those inputs, sum the weights, and then transform that sum using a special function called an activation function. The output of that activation function is then either used as the prediction (in a single neuron model) or is combined with the outputs of other neurons for further use in more complex models. The purpose of the activation function is to take the input signal (that’s the weighted sum of the inputs and the bias) and turn it into an output signal. Think of this activation function as firing (activating) the neuron when it returns 1, and doing nothing when it returns 0. This sort of computation is accomplished with a function called step function: f(z) = {1 if z > 0 else 0}. This function then transforms any weighted sum of the inputs and converts it into a binary output (either 1 or 0). The trick to making this useful is finding (learning) a set of weights that lead to good predictions using this activation function. Training our perceptron is simply a matter of initializing the weights to zero (or random value) and then implementing the perceptron learning rule, which just updates the weights based on the error of each observation with the current weights. This has the effect of moving the classifier’s decision boundary in the direction that would have helped it classify the last observation correctly. This is achieved via a for loop which iterates over each observation, making a prediction of each observation, calculating the error of that prediction and then updating the weights accordingly. In this way, weights are gradually updated until they converge. Each sweep through the training data is called an epoch. In this script the perceptron is retrained on each new bar trying to classify this bar by drawing the moving average curve above or below the bar. This script was tested with BTCUSD, USDJPY, and EURUSD. Note: TradingViews's playback feature helps to see this strategy in action. Warning: Signals ARE repainting. Style tags: Trend Following, Trend Analysis Asset class: Equities, Futures, ETFs, Currencies and Commodities Dataset: FX Minutes/Hours+/Days
אינדיקטור Pine Script™
מאת ‎capissimo‎
33
Machine Learning: kNN-based StrategykNN-based Strategy (FX and Crypto) Description: This strategy uses a classic machine learning algorithm - k Nearest Neighbours (kNN) - to let you find a prediction for the next (tomorrow's, next month's, etc.) market move. Being an unsupervised machine learning algorithm, kNN is one of the most simple learning algorithms. To do a prediction of the next market move, the kNN algorithm uses the historic data, collected in 3 arrays - feature1, feature2 and directions, - and finds the k-nearest neighbours of the current indicator(s) values. The two dimensional kNN algorithm just has a look on what has happened in the past when the two indicators had a similar level. It then looks at the k nearest neighbours, sees their state and thus classifies the current point. The kNN algorithm offers a framework to test all kinds of indicators easily to see if they have got any *predictive value*. One can easily add cog, wpr and others. Note: TradingViews's playback feature helps to see this strategy in action. Warning: Signals ARE repainting. Style tags: Trend Following, Trend Analysis Asset class: Equities, Futures, ETFs, Currencies and Commodities Dataset: FX Minutes/Hours+++/Days
אינדיקטור Pine Script™
מאת ‎capissimo‎
148
Machine Learning / Longs [Experimental]Hello Traders/Programmers, For long time I thought that if it's possible to make a script that has own memory and criterias in Pine. it would learn and find patterns as images according to given criterias. after we have arrays of strings, lines, labels I tried and made this experimental script. The script works only for Long positions. Now lets look at how it works: On each candle it creates an image of last 8 candles. before the image is created it finds highest/lowest levels of 8 candles, and creates a string with the lengths 64 (8 * 8). and for each square, it checks if it contains wick, green or red body, green or red body with wicks. see the following picture: Each square gets the value: 0: nothing in it 1: only wick in it 2: only red body in it 3. only green body in it 4: red body and wick in it 5: green body and wick in it And then it checks if price went up equal or higher than user-defined profit. if yes then it adds the image to the memory/array. and I call this part as Learning Part. what I mean by image is: if there is 1 or more element in the memory, it creates image for current 8 candles and checks the memory if there is a similar images. If the image has similarity higher than user-defined similarty level then if show the label "Matched" and similarity rate and the image in the memory. if it find any with the similarity rate is equal/greater than user-defined level then it stop searching more. As an example matched image: and then price increased and you got the profit :) Options: Period: if there is possible profit higher than user-defined minimum profit in that period, it checks the images from 2. to X. bars. Min Profit: you need to set the minimum expected profit accordingly. for example in 1m chart don't enter %10 as min profit :) Similarity Rate: as told above, you can set minimum similarity rate, higher similarity rate means better results but if you set higher rates, number of images will decrease. set it wisely :) Max Memory Size: you can set number of images (that gives the profit equal/higher than you set) to be saved that in memory Change Bar Color: optionally it can change bar colors if current image is found in the memory Current version of the script doesn't check if the price reach the minimum profit target, so no statistics. This is completely experimental work and I made it for fun. No one or no script can predict the future. and you should not try to predict the future. P.S. it starts searching on last bar, it doesn't check historical bars. if you want you should check it in replay mode :) if you get calculation time out error then hide/unhide the script. ;) Enjoy!
אינדיקטור Pine Script™
מאת ‎LonesomeTheBlue‎
84
NAND PerceptronExperimental NAND Perceptron based upon Python template that aims to predict NAND Gate Outputs. A Perceptron is one of the foundational building blocks of nearly all advanced Neural Network layers and models for Algo trading and Machine Learning. The goal behind this script was threefold: To prove and demonstrate that an ACTUAL working neural net can be implemented in Pine, even if incomplete. To pave the way for other traders and coders to iterate on this script and push the boundaries of Tradingview strategies and indicators. To see if a self-contained neural network component for parameter optimization within Pinescript was hypothetically possible. NOTE: This is a highly experimental proof of concept - this is NOT a ready-made template to include or integrate into existing strategies and indicators, yet (emphasis YET - neural networks have a lot of potential utility and potential when utilized and implemented properly). Hardcoded NAND Gate outputs with Bias column (X0): // NAND Gate + X0 Bias and Y-true // X0 // X1 // X2 // Y // 1 // 0 // 0 // 1 // 1 // 0 // 1 // 1 // 1 // 1 // 0 // 1 // 1 // 1 // 1 // 0 Column X0 is bias feature/input Column X1 and X2 are the NAND Gate Column Y is the y-true values for the NAND gate yhat is the prediction at that timestep F0,F1,F2,F3 are the Dot products of the Weights (W0,W1,W2) and the input features (X0,X1,X2) Learning rate and activation function threshold are enabled by default as input parameters Uncomment sections for more training iterations/epochs: Loop optimizations would be amazing to have for a selectable length for training iterations/epochs but I'm not sure if it's possible in Pine with how this script is structured. Error metrics and loss have not been implemented due to difficulty with script length and iterations vs epochs - I haven't been able to configure the input parameters to successfully predict the right values for all four y-true values for the NAND gate (only been able to get 3/4; If you're able to get all four predictions to be correct, let me know, please). // //---- REFERENCE for final output // A3 := 1, y0 true // B3 := 1, y1 true // C3 := 1, y2 true // D3 := 0, y3 true PLEASE READ: Source article/template and main code reference: towardsdatascience.com towardsdatascience.com towardsdatascience.com
אינדיקטור Pine Script™
מאת ‎auroagwei‎
14
CBOE PCR Factor Dependent Variable Odd Generator This script is the my Dependent Variable Odd Generator script : with the Put / Call Ratio ( PCR ) appended, only for CBOE and the instruments connected to it. For CBOE this script is more accurate and faster than Dependent Variable Odd Generator. And the stagnant market odds are better and more realistic. Do not use for timeframe periods less than 1 day. Because PCR data may give repaint error. My advice is to use the 1-week bars to gain insight into your analysis. This code is open source under the MIT license. If you have any improvements or corrections to suggest, please send me a pull request via the github repository github.com I hope it will help your work.Best regards!
אינדיקטור Pine Script™
מאת ‎Noldo‎
26
ANN MACD (BTC) Logic is correct. But I prefer to say experimental because the sample set is narrow. (300 columns) Let's start: 6 inputs : Volume Change , Bollinger Low Band chg. , Bollinger Mid Band chg., Bollinger Up Band chg. , RSI change , MACD histogram change. 1 output : Future bar change (Historical) Training timeframe : 15 mins (Analysis TF > 4 hours (My opinion)) Learning cycles : 337 Training error: 0.009999 Input columns: 6 Output columns: 1 Excluded columns: 0 Grid Training example rows: 301 Validating example rows: 0 Querying example rows: 0 Excluded example rows: 0 Duplicated example rows: 0 Network Input nodes connected: 6 Hidden layer 1 nodes: 8 Hidden layer 2 nodes: 0 Hidden layer 3 nodes: 0 Output nodes: 1 Learning rate : 0.6 Momentum : 0.8 More info : EDIT : This code is open source under the MIT License. If you have any improvements or corrections to suggest, please send me a pull request via the github repository github.com
אינדיקטור Pine Script™
מאת ‎Noldo‎
13
ANN MACD Future Forecast (SPY 1D) NOTE : Deep learning was conducted in a narrow sample set for testing purposes. So this script is Experimental . This system is based on the following article and is inspired by an external program: hackernoon.com None of the artificial neural networks in Tradingview work and are not based on completely correct logic. Unlike others in this system: IMPORTANT NOTE: If the tangent activation function is used, the input data must also have tangent values (compared to the previous values of 1 bar). Inputs were prepared according to this judgment. 1. The tangent function which is the activation function is written correctly. (The tangent function in the article: ActivationFunctionTanh (v) => (1 - exp (-2 * v)) / (1 + exp (-2 * v))) 2. Missing bias parts in the formulas were added. 3. The output function is taken from the next day (historical), so that the next bar can be predicted, which is the truth. 4.The forecast value of the next bar is subtracted from the current bar change and the market direction is determined. 5.When the future forecast and the current close are added together, the resulting data is called seed. The seed carries data both from the present and from yesterday and from the future. 6.And this seed was subjected to the MACD method. Thus, due to exponential averages, more importance will be given to recent developments and The acceleration situations will show us the direction. However, a short position should be taken for crossover and a long position for crossunder . Because the predicted values ​​work in reverse.Even though we use the same period (9,12,26) it is much faster! 7. There is no future code that can cause Repaint. However, the color after closing should be checked. The system is completely correct. However, a very narrow sample was selected. 100 data: Tangent diffs ; volume change, bollinger bands values changes (Upband , Midband , Lowband) and LazyBear's Squeeze Momentum Indicator (SQZMOM_LB) change and the next bar data (historical) price change were put into the deep learning test. IMPORTANT NOTE : The larger the sample set and the more effective dependent variables, the higher the hit rate of the deep learning test! EDIT : This code is open source under the MIT License. If you have any improvements or corrections to suggest, please send me a pull request via the github repository github.com Stay tuned. Best regards!
אינדיקטור Pine Script™
מאת ‎Noldo‎
15
Dependent Variable Odd Generator For Machine Learning TechniquesCAUTION : Not suitable for strategy, open to development. If can we separate the stagnant market from other markets, can we be so much more accurate? This project was written to research it. It is just the tiny part of the begining. And this is a very necessary but very small side function in the main function. Lets start : Hi users, I had this idea in my mind for a long time but I had a hard time finding the parameters that would make the market stagnant. This idea is my first original command system. Although it is very difficult to make sense of the stagnant market, I think that this command system can achieve realistic proportions. With 's money flow index, I opened the track to determine the level. On the other hand, the prices were also using a money flow index, and it forced me to make the limitations between the levels in a logical way. But the good thing is that since the bollinger bandwidth uses a larger period, we are able to print normal values ​​at extreme buy and sell values. In terms of price, we can define excessive purchase and sale values ​​as the period is smaller. I have repeatedly looked at the limit values ​​that determine the bull, bear, and bollinger bandwidth (mfi), and I think this is the right one. Then I have included these values ​​in the probability set. The bull and bear market did not form the intersection of the cluster, and because there are connected events, the stagnant market, which is the intersection, will be added to the other markets with the same venn diagram logic and the sum of the probability set will be 1. is equal to. I hope that we can renew the number generators in the very important parameters of machine learning such as Markov Process with generators dependent on dependent variables, which bring us closer to reality. This function is open to development and can be made of various ideas on machine learning. Best wishes. This code is open source under the MIT license. If you have any improvements or corrections to suggest, please send me a pull request via the github repository github.com
אינדיקטור Pine Script™
מאת ‎Noldo‎
3