Machine Learning: Gaussian Process Regression [LuxAlgo]We provide an implementation of the Gaussian Process Regression (GPR), a popular machine-learning method capable of estimating underlying trends in prices as well as forecasting them.
While this implementation is adapted to real-time usage, do remember that forecasting trends in the market is challenging, do not use this tool as a standalone for your trading decisions.
🔶 USAGE
The main goal of our implementation of GPR is to forecast trends. The method is applied to a subset of the most recent prices, with the Training Window determining the size of this subset.
Two user settings controlling the trend estimate are available, Smooth and Sigma . Smooth determines the smoothness of our estimate, with higher values returning smoother results suitable for longer-term trend estimates.
Sigma controls the amplitude of the forecast, with values closer to 0 returning results with a higher amplitude. Do note that due to the calculation of the method, lower values of sigma can return errors with higher values of the training window.
🔹 Updating Mechanisms
The script includes three methods to update a forecast. By default a forecast will not update for new bars (Lock Forecast).
The forecast can be re-estimated once the price reaches the end of the forecasting window when using the "Update Once Reached" method.
Finally "Continuously Update" will update the whole forecast on any new bar.
🔹 Estimating Trends
Gaussian Process Regression can be used to estimate past underlying local trends in the price, allowing for a noise-free interpretation of trends.
This can be useful for performing descriptive analysis, such as highlighting patterns more easily.
🔶 SETTINGS
Training Window: Number of most recent price observations used to fit the model
Forecasting Length: Forecasting horizon, determines how many bars in the future are forecasted.
Smooth: Controls the degree of smoothness of the model fit.
Sigma: Noise variance. Controls the amplitude of the forecast, lower values will make it more sensitive to outliers.
Update: Determines when the forecast is updated, by default the forecast is not updated for new bars.
Indicator
Machine Learning Momentum Oscillator [ChartPrime]The Machine Learning Momentum Oscillator brings together the K-Nearest Neighbors (KNN) algorithm and the predictive strength of the Tactical Sector Indicator (TSI) Momentum. This unique oscillator not only uses the insights from TSI Momentum but also taps into the power of machine learning therefore being designed to give traders a more comprehensive view of market momentum.
At its core, the Machine Learning Momentum Oscillator blends TSI Momentum with the capabilities of the KNN algorithm. Introducing KNN logic allows for better handling of noise in the data set. The TSI Momentum is known for understanding how strong trends are and which direction they're headed, and now, with the added layer of machine learning, we're able to offer a deeper perspective on market trends. This is a fairly classical when it comes to visuals and trading.
Green bars show the trader when the asset is in an uptrend. On the flip side, red bars mean things are heading down, signaling a bearish movement driven by selling pressure. These color cues make it easier to catch the sentiment and direction of the market in a glance.
Yellow boxes are also displayed by the oscillator. These boxes highlight potential turning points or peaks. When the market comes close to these points, they can provide a heads-up about the possibility of changes in momentum or even a trend reversal, helping a trader make informed choices quickly. These can be looked at as possible reversal areas simply put.
Settings:
Users can adjust the number of neighbours in the KNN algorithm and choose the periods they prefer for analysis. This way, the tool becomes a part of a trader's strategy, adapting to different market conditions as they see fit. Users can also adjust the smoothing used by the oscillator via the smoothing input. Indicator
Indicator
Stock Market Emotion Index (SMEI)Implementation of Charlie Q. Yang's research paper “The stock market emotion index”, subtitle “A New Sentiment Measure Using Enhanced OBV and Money Flow Indicators”, (2007) where he combined “five simple emotion statistics” - Close Emotion Statistic (CES), Money Flow Statistic (MFS), Supply Demand Statistic (SDS), Relative Strength Statistic (RSS), and Psychological Level Statistic (PLS) - into one indicator.
Quotations:
“The index calculation is solely based on observed short term market volatility as reflected by each day’s trading volume, open, high, low, and close prices”
“The basic premise of Dow theory is that the market discounts everything, including the emotions of all traders. The fundamentals of a company do not change suddenly when its daily stock price is fluctuating as driven by human emotions that are often irrational. However, over a longer time period, a company's fundamentals do change. Again, different types of human emotions, triggered by the flow of material events, are moving the stock price trend up or down. This paper summarizes the author’s attempt in understanding primary trend extent and duration by proposing a new sentiment measure using statistical analysis of stock market human emotion.”
Even though “indicator is intended for identifying primary trend cycles that typically last one year or longer“ where Mr. Yang used a fixed averaging length of 260 days and only days as time frame, my implementation has been changed slightly to accommodate for all time frames and to adapt faster using shorter averaging (timeframe dependent).
How to use it:
Positive values indicating a bullish trend and negative values indicating a bearish trend. Background color is set to green or red accordingly.
Positive and negative bar to bar changes are indicated with green and red to show bar to bar (ultra short term) trends.
(No financial advise, use for testing purposed only) Indicator
Delta Volume by SiddWolfDelta Volume is Difference between Buying Volume and Selling Volume. This indicator gives the Delta Volume based on Lower TimeFrame Candles. It utilizes security_lower_tf() function, a function that provides Lower TF candle data in Higher TF Chart.
security_lower_tf() is a new function provided by PulseWire yesterday. If you are a PineScript Programmer, I suggest you to read about it, as it is a very powerful function that can extremely improve your trading strategy.
How this indicator works:
This indicator checks volume data on lower TimeFrame Candles and Shows it's delta in the current Chart Timeframe. For example: If you open 4 hours chart, this indicator checks volume of 1 minute chart and separates Buying-Selling volume. Then it subtracts Candle's Selling volume from Candle's Buying volume, finally calculating the Delta Volume.
This indicator also provides a Smooth Delta Volume, which is moving average of Delta Volume. As Delta Volume changes a lot, Smooth Delta Volume can be very helpful for identifying Trends . Goto settings and in "Show" section select "Smooth Delta Volume" to lay it on the chart.
Settings is the Key:
Settings are key to all of my indicators. Play around with it a bit. You can change what to show on the chart from settings. Smooth Delta Volume moving average length can be changed from the settings. You can also select "Show as Percentage", which shows Delta Volume as Percentage of Overall Candle's Volume. If you use Weekly or Monthly Timeframe, change increase lower timeframe from settings. Read the tooltips to understand what each settings mean. Tooltips are the (i) button in-front of each settings.
FAQs:
Q. Does the indicator Repaint ?
--- No. None of my indicators repaints. What you see now is what's drawn in real time.
Q. What TimeFrame is Best for this Indicator ?
--- It can be used on timeframes from 5 minutes to higher. But I would prefer to use it from timeframes higher than 30 minutes, as it gathers data from 1 minute TF.
Q. Indicator doesn't show anything ?
--- This indicator only works on security with Volume data. Also use it from higher timeframe than specified in Settings, because Volume Delta is calculated using Data from Lower TimeFrame.
Q. Delta volume is not provided by PulseWire, So how exactly does this indicator work?
--- This indicator takes advantage of new pinescript function security_lower_tf(), and calculates volume for smaller timeframe data and calculates delta on higher timeframe.
Q. Does this indicator give financial advice?
--- No. Nope. Nein. Não. नहीं.
Conclusion:
This indicator is very basic but if used correctly it can be very powerful. If you have any questions or suggestions feel free to comment below. I'd love to connect with you. Thank you.
~ @SiddWolf Indicator
Indicator
Indicator
Multi-timeframe MAs + Stoch RSI SignalsHello traders,
I welcome you to my first published script on PulseWire: “Multi-timeframe Moving Averages + Stochastic RSI”.
The script is based on a simple formula: Buy signals are generated when a fast moving average is above a slower moving average (uptrend) and the Stochastic RSI K line is crossing above the oversold level (entry).
Sell signals are generated when a fast moving average is below a slower moving average (downtrend) and the Stochastic RSI K line is crossing below the overbought level (entry).
This indicator works best in strong trends!
**Please note the above example has repainting turned on which may produce unrealistic results when viewing historical data. See below for more information regarding this and how you can turn it off.**
The user has the following inputs:
- Option to change the Stochastic RSI settings, including the oversold and overbought levels.
- Option to enter any value for both the Fast Moving Average and the Slow Moving Average.
- Option to change between EMA or SMA for each moving average.
- Multiple time frames to choose from, as well as the ability to selectively turn off individual time frames (both plots and alerts).
(Default time frames are 1 hour, 4 hour, and Daily. You can have a 4th time frame by changing your current time frame to something lower than the other 3 time frames)
- Turn on/off repainting: If repainting is turned on you will get an alert and buy/sell signal on chart immediately when condition is met, however the signal may disappear from chart if the condition reverses during the same candle.
If repainting is turned off, the indicator will wait for the candle to close before issuing the alert and painting the signal on chart.
For higher time frames, the indicator will wait for the candle in the higher time frame to close before issuing a signal if repaint is turned off. Default is set to Repaint on, so please be aware of this if you do not want repainting.
How to use alerts:
- Before you do anything, make sure your current time frame is the lowest time frame you’d like alerts on, as you will still receive alerts for the higher time frames you selected in settings.
- Once you have all the settings changed to how you like, save your chart first. Then right click on any of the indicator’s buy/sell signals on the chart and click “Add Alert on MAs + Stoch RSI”.
- Make sure “Any alert() function call” is selected under the Condition.
- You can delete or change the text in “Alert name” if you want as the alert message is already built into the indicator, and it will tell you in the alert message which asset and time frame to buy or sell.
Other things to note:
- The indicator will not display the buy/sell signals of lower time frames when you are on a higher time frame. This was done purposely to reduce clutter on the chart when you switch to higher time frames.
- While the alert message will tell you which time frame a signal was generated, the plots on the chart will instead show “Buy/Sell TF1, or TF2, or TF3”.
If the signal is from the current time frame that the alert was created on, then it will simply show “Buy” or “Sell”.
Hope you guys enjoy using this one, please drop a like if you found it useful. If anyone wants to modify my script in any way, please just credit me for the original work when you publish the script. Good luck! Indicator
Indicator
Indicator
Indicator
Strategy
Indicator
Indicator
Indicator
Indicator
Indicator
Indicator
Strategy
Indicator
Strategy
Indicator
