AI SuperTrend - Strategy [presentTrading]
█ Introduction and How it is Different
The AI Supertrend Strategy is a unique hybrid approach that employs both traditional technical indicators and machine learning techniques. Unlike standard strategies that rely solely on traditional indicators or mathematical models, this strategy integrates the power of k-Nearest Neighbors (KNN), a machine learning algorithm, with the tried-and-true SuperTrend indicator. This blend aims to provide traders with more accurate, responsive, and context-aware trading signals.
*The KNN part is mainly referred from @Zeiierman.
BTCUSD 8hr performance
ETHUSD 8hr performance
█ Strategy, How it Works: Detailed Explanation
SuperTrend Calculation
Volume-Weighted Moving Average (VWMA): A VWMA of the close price is calculated based on the user-defined length (len). This serves as the central line around which the upper and lower bands are calculated.
Average True Range (ATR): ATR is calculated over a period defined by len. It measures the market's volatility.
Upper and Lower Bands: The upper band is calculated as VWMA + (factor * ATR) and the lower band as VWMA - (factor * ATR). The factor is a user-defined multiplier that decides how wide the bands should be.
KNN Algorithm
Data Collection: An array (data) is populated with recent n SuperTrend values. Corresponding labels (labels) are determined by whether the weighted moving average price (price) is greater than the weighted moving average of the SuperTrend (sT).
Distance Calculation: The absolute distance between each data point and the current SuperTrend value is calculated.
Sorting & Weighting: The distances are sorted in ascending order, and the closest k points are selected. Each point is weighted by the inverse of its distance to the current point.
Classification: A weighted sum of the labels of the k closest points is calculated. If the sum is closer to 1, the trend is predicted as bullish; if closer to 0, bearish.
Signal Generation
Start of Trend: A new bullish trend (Start_TrendUp) is considered to have started if the current trend color is bullish and the previous was not bullish. Similarly for bearish trends (Start_TrendDn).
Trend Continuation: A bullish trend (TrendUp) is considered to be continuing if the direction is negative and the KNN prediction is 1. Similarly for bearish trends (TrendDn).
Trading Logic
Long Condition: If Start_TrendUp or TrendUp is true, a long position is entered.
Short Condition: If Start_TrendDn or TrendDn is true, a short position is entered.
Exit Condition: Dynamic trailing stops are used for exits. If the trend does not continue as indicated by the KNN prediction and SuperTrend direction, an exit signal is generated.
The synergy between SuperTrend and KNN aims to filter out noise and produce more reliable trading signals. While SuperTrend provides a broad sense of the market direction, KNN refines this by predicting short-term price movements, leading to a more nuanced trading strategy.
Local picture
█ Trade Direction
The strategy allows traders to choose between taking only long positions, only short positions, or both. This is particularly useful for adapting to different market conditions.
█ Usage
ToolTips: Explains what each parameter does and how to adjust them.
Inputs: Customize values like the number of neighbors in KNN, ATR multiplier, and moving average type.
Plotting: Visual cues on the chart to indicate bullish or bearish trends.
Order Execution: Based on the generated signals, the strategy will execute buy/sell orders.
█ Default Settings
The default settings are selected to provide a balanced approach, but they can be modified for different trading styles and asset classes.
Initial Capital: $10,000
Default Quantity Type: 10% of equity
Commission: 0.1%
Slippage: 1
Currency: USD
By combining both machine learning and traditional technical analysis, this strategy offers a sophisticated and adaptive trading solution. Strategy
AI Trend Navigator [K-Neighbor]█ Overview
In the evolving landscape of trading and investment, the demand for sophisticated and reliable tools is ever-growing. The AI Trend Navigator is an indicator designed to meet this demand, providing valuable insights into market trends and potential future price movements. The AI Trend Navigator indicator is designed to predict market trends using the k-Nearest Neighbors (KNN) classifier.
By intelligently analyzing recent price actions and emphasizing similar values, it helps traders to navigate complex market conditions with confidence. It provides an advanced way to analyze trends, offering potentially more accurate predictions compared to simpler trend-following methods.
█ Calculations
KNN Moving Average Calculation: The core of the algorithm is a KNN Moving Average that computes the mean of the 'k' closest values to a target within a specified window size. It does this by iterating through the window, calculating the absolute differences between the target and each value, and then finding the mean of the closest values. The target and value are selected based on user preferences (e.g., using the VWAP or Volatility as a target).
KNN Classifier Function: This function applies the k-nearest neighbor algorithm to classify the price action into positive, negative, or neutral trends. It looks at the nearest 'k' bars, calculates the Euclidean distance between them, and categorizes them based on the relative movement. It then returns the prediction based on the highest count of positive, negative, or neutral categories.
█ How to use
Traders can use this indicator to identify potential trend directions in different markets.
Spotting Trends: Traders can use the KNN Moving Average to identify the underlying trend of an asset. By focusing on the k closest values, this component of the indicator offers a clearer view of the trend direction, filtering out market noise.
Trend Confirmation: The KNN Classifier component can confirm existing trends by predicting the future price direction. By aligning predictions with current trends, traders can gain more confidence in their trading decisions.
█ Settings
PriceValue: This determines the type of price input used for distance calculation in the KNN algorithm.
hl2: Uses the average of the high and low prices.
VWAP: Uses the Volume Weighted Average Price.
VWAP: Uses the Volume Weighted Average Price.
Effect: Changing this input will modify the reference values used in the KNN classification, potentially altering the predictions.
TargetValue: This sets the target variable that the KNN classification will attempt to predict.
Price Action: Uses the moving average of the closing price.
VWAP: Uses the Volume Weighted Average Price.
Volatility: Uses the Average True Range (ATR).
Effect: Selecting different targets will affect what the KNN is trying to predict, altering the nature and intent of the predictions.
Number of Closest Values: Defines how many closest values will be considered when calculating the mean for the KNN Moving Average.
Effect: Increasing this value makes the algorithm consider more nearest neighbors, smoothing the indicator and potentially making it less reactive. Decreasing this value may make the indicator more sensitive but possibly more prone to noise.
Neighbors: This sets the number of neighbors that will be considered for the KNN Classifier part of the algorithm.
Effect: Adjusting the number of neighbors affects the sensitivity and smoothness of the KNN classifier.
Smoothing Period: Defines the smoothing period for the moving average used in the KNN classifier.
Effect: Increasing this value would make the KNN Moving Average smoother, potentially reducing noise. Decreasing it would make the indicator more reactive but possibly more prone to false signals.
█ What is K-Nearest Neighbors (K-NN) algorithm?
At its core, the K-NN algorithm recognizes patterns within market data and analyzes the relationships and similarities between data points. By considering the 'K' most similar instances (or neighbors) within a dataset, it predicts future price movements based on historical trends. The K-Nearest Neighbors (K-NN) algorithm is a type of instance-based or non-generalizing learning. While K-NN is considered a relatively simple machine-learning technique, it falls under the AI umbrella.
We can classify the K-Nearest Neighbors (K-NN) algorithm as a form of artificial intelligence (AI), and here's why:
Machine Learning Component: K-NN is a type of machine learning algorithm, and machine learning is a subset of AI. Machine learning is about building algorithms that allow computers to learn from and make predictions or decisions based on data. Since K-NN falls under this category, it is aligned with the principles of AI.
Instance-Based Learning: K-NN is an instance-based learning algorithm. This means that it makes decisions based on the entire training dataset rather than deriving a discriminative function from the dataset. It looks at the 'K' most similar instances (neighbors) when making a prediction, hence adapting to new information if the dataset changes. This adaptability is a hallmark of intelligent systems.
Pattern Recognition: The core of K-NN's functionality is recognizing patterns within data. It identifies relationships and similarities between data points, something akin to human pattern recognition, a key aspect of intelligence.
Classification and Regression: K-NN can be used for both classification and regression tasks, two fundamental problems in machine learning and AI. The indicator code is used for trend classification, a predictive task that aligns with the goals of AI.
Simplicity Doesn't Exclude AI: While K-NN is often considered a simpler algorithm compared to deep learning models, simplicity does not exclude something from being AI. Many AI systems are built on simple rules and can be combined or scaled to create complex behavior.
No Explicit Model Building: Unlike traditional statistical methods, K-NN does not build an explicit model during training. Instead, it waits until a prediction is required and then looks at the 'K' nearest neighbors from the training data to make that prediction. This lazy learning approach is another aspect of machine learning, part of the broader AI field.
-----------------
Disclaimer
The information contained in my Scripts/Indicators/Ideas/Algos/Systems does not constitute financial advice or a solicitation to buy or sell any securities of any type. I will not accept liability for any loss or damage, including without limitation any loss of profit, which may arise directly or indirectly from the use of or reliance on such information.
All investments involve risk, and the past performance of a security, industry, sector, market, financial product, trading strategy, backtest, or individual's trading does not guarantee future results or returns. Investors are fully responsible for any investment decisions they make. Such decisions should be based solely on an evaluation of their financial circumstances, investment objectives, risk tolerance, and liquidity needs.
My Scripts/Indicators/Ideas/Algos/Systems are only for educational purposes!
Indicator
Machine Learning : Torben's Moving Median KNN BandsWhat is Median Filtering ?
Median filtering is a non-linear digital filtering technique, often used to remove noise from an image or signal. Such noise reduction is a typical pre-processing step to improve the results of later processing (for example, edge detection on an image). Median filtering is very widely used in digital image processing because, under certain conditions, it preserves edges while removing noise (but see the discussion below), also having applications in signal processing.
The main idea of the median filter is to run through the signal entry by entry, replacing each entry with the median of neighboring entries. The pattern of neighbors is called the "window", which slides, entry by entry, over the entire signal. For one-dimensional signals, the most obvious window is just the first few preceding and following entries, whereas for two-dimensional (or higher-dimensional) data the window must include all entries within a given radius or ellipsoidal region (i.e. the median filter is not a separable filter).
The median filter works by taking the median of all the pixels in a neighborhood around the current pixel. The median is the middle value in a sorted list of numbers. This means that the median filter is not sensitive to the order of the pixels in the neighborhood, and it is not affected by outliers (very high or very low values).
The median filter is a very effective way to remove noise from images. It can remove both salt and pepper noise (random white and black pixels) and Gaussian noise (randomly distributed pixels with a Gaussian distribution). The median filter is also very good at preserving edges, which is why it is often used as a pre-processing step for edge detection.
However, the median filter can also blur images. This is because the median filter replaces each pixel with the value of the median of its neighbors. This can cause the edges of objects in the image to be smoothed out. The amount of blurring depends on the size of the window used by the median filter. A larger window will blur more than a smaller window.
The median filter is a very versatile tool that can be used for a variety of tasks in image processing. It is a good choice for removing noise and preserving edges, but it can also blur images. The best way to use the median filter is to experiment with different window sizes to find the setting that produces the desired results.
What is this Indicator ?
K-nearest neighbors (KNN) is a simple, non-parametric machine learning algorithm that can be used for both classification and regression tasks. The basic idea behind KNN is to find the K most similar data points to a new data point and then use the labels of those K data points to predict the label of the new data point.
Torben's moving median is a variation of the median filter that is used to remove noise from images. The median filter works by replacing each pixel in an image with the median of its neighbors. Torben's moving median works in a similar way, but it also averages the values of the neighbors. This helps to reduce the amount of blurring that can occur with the median filter.
KNN over Torben's moving median is a hybrid algorithm that combines the strengths of both KNN and Torben's moving median. KNN is able to learn the underlying distribution of the data, while Torben's moving median is able to remove noise from the data. This combination can lead to better performance than either algorithm on its own.
To implement KNN over Torben's moving median, we first need to choose a value for K. The value of K controls how many neighbors are used to predict the label of a new data point. A larger value of K will make the algorithm more robust to noise, but it will also make the algorithm less sensitive to local variations in the data.
Once we have chosen a value for K, we need to train the algorithm on a dataset of labeled data points. The training dataset will be used to learn the underlying distribution of the data.
Once the algorithm is trained, we can use it to predict the labels of new data points. To do this, we first need to find the K most similar data points to the new data point. We can then use the labels of those K data points to predict the label of the new data point.
KNN over Torben's moving median is a simple, yet powerful algorithm that can be used for a variety of tasks. It is particularly well-suited for tasks where the data is noisy or where the underlying distribution of the data is unknown.
Here are some of the advantages of using KNN over Torben's moving median:
KNN is able to learn the underlying distribution of the data.
KNN is robust to noise.
KNN is not sensitive to local variations in the data.
Here are some of the disadvantages of using KNN over Torben's moving median:
KNN can be computationally expensive for large datasets.
KNN can be sensitive to the choice of K.
KNN can be slow to train.
Indicator
Machine Learning: Lorentzian Classification█ OVERVIEW
A Lorentzian Distance Classifier (LDC) is a Machine Learning classification algorithm capable of categorizing historical data from a multi-dimensional feature space. This indicator demonstrates how Lorentzian Classification can also be used to predict the direction of future price movements when used as the distance metric for a novel implementation of an Approximate Nearest Neighbors (ANN) algorithm.
█ BACKGROUND
In physics, Lorentzian space is perhaps best known for its role in describing the curvature of space-time in Einstein's theory of General Relativity (2). Interestingly, however, this abstract concept from theoretical physics also has tangible real-world applications in trading.
Recently, it was hypothesized that Lorentzian space was also well-suited for analyzing time-series data (4), (5). This hypothesis has been supported by several empirical studies that demonstrate that Lorentzian distance is more robust to outliers and noise than the more commonly used Euclidean distance (1), (3), (6). Furthermore, Lorentzian distance was also shown to outperform dozens of other highly regarded distance metrics, including Manhattan distance, Bhattacharyya similarity, and Cosine similarity (1), (3). Outside of Dynamic Time Warping based approaches, which are unfortunately too computationally intensive for PineScript at this time, the Lorentzian Distance metric consistently scores the highest mean accuracy over a wide variety of time series data sets (1).
Euclidean distance is commonly used as the default distance metric for NN-based search algorithms, but it may not always be the best choice when dealing with financial market data. This is because financial market data can be significantly impacted by proximity to major world events such as FOMC Meetings and Black Swan events. This event-based distortion of market data can be framed as similar to the gravitational warping caused by a massive object on the space-time continuum. For financial markets, the analogous continuum that experiences warping can be referred to as "price-time".
Below is a side-by-side comparison of how neighborhoods of similar historical points appear in three-dimensional Euclidean Space and Lorentzian Space:
This figure demonstrates how Lorentzian space can better accommodate the warping of price-time since the Lorentzian distance function compresses the Euclidean neighborhood in such a way that the new neighborhood distribution in Lorentzian space tends to cluster around each of the major feature axes in addition to the origin itself. This means that, even though some nearest neighbors will be the same regardless of the distance metric used, Lorentzian space will also allow for the consideration of historical points that would otherwise never be considered with a Euclidean distance metric.
Intuitively, the advantage inherent in the Lorentzian distance metric makes sense. For example, it is logical that the price action that occurs in the hours after Chairman Powell finishes delivering a speech would resemble at least some of the previous times when he finished delivering a speech. This may be true regardless of other factors, such as whether or not the market was overbought or oversold at the time or if the macro conditions were more bullish or bearish overall. These historical reference points are extremely valuable for predictive models, yet the Euclidean distance metric would miss these neighbors entirely, often in favor of irrelevant data points from the day before the event. By using Lorentzian distance as a metric, the ML model is instead able to consider the warping of price-time caused by the event and, ultimately, transcend the temporal bias imposed on it by the time series.
For more information on the implementation details of the Approximate Nearest Neighbors (ANN) algorithm used in this indicator, please refer to the detailed comments in the source code.
█ HOW TO USE
Below is an explanatory breakdown of the different parts of this indicator as it appears in the interface:
Below is an explanation of the different settings for this indicator:
General Settings:
Source - This has a default value of "hlc3" and is used to control the input data source.
Neighbors Count - This has a default value of 8, a minimum value of 1, a maximum value of 100, and a step of 1. It is used to control the number of neighbors to consider.
Max Bars Back - This has a default value of 2000.
Feature Count - This has a default value of 5, a minimum value of 2, and a maximum value of 5. It controls the number of features to use for ML predictions.
Color Compression - This has a default value of 1, a minimum value of 1, and a maximum value of 10. It is used to control the compression factor for adjusting the intensity of the color scale.
Show Exits - This has a default value of false. It controls whether to show the exit threshold on the chart.
Use Dynamic Exits - This has a default value of false. It is used to control whether to attempt to let profits ride by dynamically adjusting the exit threshold based on kernel regression.
Feature Engineering Settings:
Note: The Feature Engineering section is for fine-tuning the features used for ML predictions. The default values are optimized for the 4H to 12H timeframes for most charts, but they should also work reasonably well for other timeframes. By default, the model can support features that accept two parameters (Parameter A and Parameter B, respectively). Even though there are only 4 features provided by default, the same feature with different settings counts as two separate features. If the feature only accepts one parameter, then the second parameter will default to EMA-based smoothing with a default value of 1. These features represent the most effective combination I have encountered in my testing, but additional features may be added as additional options in the future.
Feature 1 - This has a default value of "RSI" and options are: "RSI", "WT", "CCI", "ADX".
Feature 2 - This has a default value of "WT" and options are: "RSI", "WT", "CCI", "ADX".
Feature 3 - This has a default value of "CCI" and options are: "RSI", "WT", "CCI", "ADX".
Feature 4 - This has a default value of "ADX" and options are: "RSI", "WT", "CCI", "ADX".
Feature 5 - This has a default value of "RSI" and options are: "RSI", "WT", "CCI", "ADX".
Filters Settings:
Use Volatility Filter - This has a default value of true. It is used to control whether to use the volatility filter.
Use Regime Filter - This has a default value of true. It is used to control whether to use the trend detection filter.
Use ADX Filter - This has a default value of false. It is used to control whether to use the ADX filter.
Regime Threshold - This has a default value of -0.1, a minimum value of -10, a maximum value of 10, and a step of 0.1. It is used to control the Regime Detection filter for detecting Trending/Ranging markets.
ADX Threshold - This has a default value of 20, a minimum value of 0, a maximum value of 100, and a step of 1. It is used to control the threshold for detecting Trending/Ranging markets.
Kernel Regression Settings:
Trade with Kernel - This has a default value of true. It is used to control whether to trade with the kernel.
Show Kernel Estimate - This has a default value of true. It is used to control whether to show the kernel estimate.
Lookback Window - This has a default value of 8 and a minimum value of 3. It is used to control the number of bars used for the estimation. Recommended range: 3-50
Relative Weighting - This has a default value of 8 and a step size of 0.25. It is used to control the relative weighting of time frames. Recommended range: 0.25-25
Start Regression at Bar - This has a default value of 25. It is used to control the bar index on which to start regression. Recommended range: 0-25
Display Settings:
Show Bar Colors - This has a default value of true. It is used to control whether to show the bar colors.
Show Bar Prediction Values - This has a default value of true. It controls whether to show the ML model's evaluation of each bar as an integer.
Use ATR Offset - This has a default value of false. It controls whether to use the ATR offset instead of the bar prediction offset.
Bar Prediction Offset - This has a default value of 0 and a minimum value of 0. It is used to control the offset of the bar predictions as a percentage from the bar high or close.
Backtesting Settings:
Show Backtest Results - This has a default value of true. It is used to control whether to display the win rate of the given configuration.
█ WORKS CITED
(1) R. Giusti and G. E. A. P. A. Batista, "An Empirical Comparison of Dissimilarity Measures for Time Series Classification," 2013 Brazilian Conference on Intelligent Systems, Oct. 2013, DOI: 10.1109/bracis.2013.22.
(2) Y. Kerimbekov, H. Ş. Bilge, and H. H. Uğurlu, "The use of Lorentzian distance metric in classification problems," Pattern Recognition Letters, vol. 84, 170–176, Dec. 2016, DOI: 10.1016/j.patrec.2016.09.006.
(3) A. Bagnall, A. Bostrom, J. Large, and J. Lines, "The Great Time Series Classification Bake Off: An Experimental Evaluation of Recently Proposed Algorithms." ResearchGate, Feb. 04, 2016.
(4) H. Ş. Bilge, Yerzhan Kerimbekov, and Hasan Hüseyin Uğurlu, "A new classification method by using Lorentzian distance metric," ResearchGate, Sep. 02, 2015.
(5) Y. Kerimbekov and H. Şakir Bilge, "Lorentzian Distance Classifier for Multiple Features," Proceedings of the 6th International Conference on Pattern Recognition Applications and Methods, 2017, DOI: 10.5220/0006197004930501.
(6) V. Surya Prasath et al., "Effects of Distance Measure Choice on KNN Classifier Performance - A Review." .
█ ACKNOWLEDGEMENTS
@veryfid - For many invaluable insights, discussions, and advice that helped to shape this project.
@capissimo - For open sourcing his interesting ideas regarding various KNN implementations in PineScript, several of which helped inspire my original undertaking of this project.
@RikkiTavi - For many invaluable physics-related conversations and for his helping me develop a mechanism for visualizing various distance algorithms in 3D using JavaScript
@jlaurel - For invaluable literature recommendations that helped me to understand the underlying subject matter of this project.
@annutara - For help in beta-testing this indicator and for sharing many helpful ideas and insights early on in its development.
@jasontaylor7 - For helping to beta-test this indicator and for many helpful conversations that helped to shape my backtesting workflow
@meddymarkusvanhala - For helping to beta-test this indicator
@dlbnext - For incredibly detailed backtesting testing of this indicator and for sharing numerous ideas on how the user experience could be improved. Indicator
kNNLibrary "kNN"
Collection of experimental kNN functions. This is a work in progress, an improvement upon my original kNN script:
The script can be recreated with this library. Unlike the original script, that used multiple arrays, this has been reworked with the new Pine Script matrix features.
To make a kNN prediction, the following data should be supplied to the wrapper:
kNN : filter type. Right now either Binary or Percent . Binary works like in the original script: the system stores whether the price has increased (+1) or decreased (-1) since the previous knnStore event (called when either long or short condition is supplied). Percent works the same, but the values stored are the difference of prices in percents. That way larger differences in prices would give higher scores.
k : number k. This is how many nearest neighbors are to be selected (and summed up to get the result).
skew : kNN minimum difference. Normally, the prediction is done with a simple majority of the neighbor votes. If skew is given, then more than a simple majority is needed for a prediction. This also means that there are inputs for which no prediction would be given (if the majority votes are between -skew and +skew). Note that in Percent mode more profitable trades will have higher voting power.
depth : kNN matrix size limit. Originally, the whole available history of trades was used to make a prediction. This not only requires more computational power, but also neglects the fact that the market conditions are changing. This setting restricts the memory matrix to a finite number of past trades.
price : price series
long : long condition. True if the long conditions are met, but filters are not yet applied. For example, in my original script, trades are only made on crossings of fast and slow MAs. So, whenever it is possible to go long, this value is set true. False otherwise.
short : short condition. Same as long , but for short condition.
store : whether the inputs should be stored. Additional filters may be applied to prevent bad trades (for example, trend-based filters), so if you only need to consult kNN without storing the trade, this should be set to false.
feature1 : current value of feature 1. A feature in this case is some kind of data derived from the price. Different features may be used to analyse the price series. For example, oscillator values. Not all of them may be used for kNN prediction. As the current kNN implementation is 2-dimensional, only two features can be used.
feature2 : current value of feature 2.
The wrapper returns a tuple: [ longOK, shortOK ]. This is a pair of filters. When longOK is true, then kNN predicts a long trade may be taken. When shortOK is true, then kNN predicts a short trade may be taken. The kNN filters are returned whenever long or short conditions are met. The trade is supposed to happen when long or short conditions are met and when the kNN filter for the desired direction is true.
Exported functions :
knnStore(knn, p1, p2, src, maxrows)
Store the previous trade; buffer the current one until results are in. Results are binary: up/down
Parameters:
knn : knn matrix
p1 : feature 1 value
p2 : feature 2 value
src : current price
maxrows : limit the matrix size to this number of rows (0 of no limit)
Returns: modified knn matrix
knnStorePercent(knn, p1, p2, src, maxrows)
Store the previous trade; buffer the current one until results are in. Results are in percents
Parameters:
knn : knn matrix
p1 : feature 1 value
p2 : feature 2 value
src : current price
maxrows : limit the matrix size to this number of rows (0 of no limit)
Returns: modified knn matrix
knnGet(distance, result)
Get neighbours by getting k results with the smallest distances
Parameters:
distance : distance array
result : result array
Returns: array slice of k results
knnDistance(knn, p1, p2)
Create a distance array from the two given parameters
Parameters:
knn : knn matrix
p1 : feature 1 value
p2 : feature 2 value
Returns: distance array
knnSum(knn, p1, p2, k)
Make a prediction, finding k nearest neighbours and summing them up
Parameters:
knn : knn matrix
p1 : feature 1 value
p2 : feature 2 value
k : sum k nearest neighbors
Returns: sum of k nearest neighbors
doKNN(kNN, k, skew, depth, price, long, short, store, feature1, feature2)
execute kNN filter
Parameters:
kNN : filter type
k : number k
skew : kNN minimum difference
depth : kNN matrix size limit
price : series
long : long condition
short : short condition
store : store the supplied features (if false, only checks the results without storage)
feature1 : feature 1 value
feature2 : feature 2 value
Returns: filter output Library
Machine Learning: kNN (New Approach)Description:
kNN is a very robust and simple method for data classification and prediction. It is very effective if the training data is large. However, it is distinguished by difficulty at determining its main parameter, K (a number of nearest neighbors), beforehand. The computation cost is also quite high because we need to compute distance of each instance to all training samples. Nevertheless, in algorithmic trading KNN is reported to perform on a par with such techniques as SVM and Random Forest. It is also widely used in the area of data science.
The input data is just a long series of prices over time without any particular features. The value to be predicted is just the next bar's price. The way that this problem is solved for both nearest neighbor techniques and for some other types of prediction algorithms is to create training records by taking, for instance, 10 consecutive prices and using the first 9 as predictor values and the 10th as the prediction value. Doing this way, given 100 data points in your time series you could create 10 different training records. It's possible to create even more training records than 10 by creating a new record starting at every data point. For instance, you could take the first 10 data points and create a record. Then you could take the 10 consecutive data points starting at the second data point, the 10 consecutive data points starting at the third data point, etc.
By default, shown are only 10 initial data points as predictor values and the 6th as the prediction value.
Here is a step-by-step workthrough on how to compute K nearest neighbors (KNN) algorithm for quantitative data:
1. Determine parameter K = number of nearest neighbors.
2. Calculate the distance between the instance and all the training samples. As we are dealing with one-dimensional distance, we simply take absolute value from the instance to value of x (| x – v |).
3. Rank the distance and determine nearest neighbors based on the K'th minimum distance.
4. Gather the values of the nearest neighbors.
5. Use average of nearest neighbors as the prediction value of the instance.
The original logic of the algorithm was slightly modified, and as a result at approx. N=17 the resulting curve nicely approximates that of the sma(20). See the description below. Beside the sma-like MA this algorithm also gives you a hint on the direction of the next bar move. Indicator
Strategy
Indicator
Indicator
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: PulseWires'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 Indicator
