Ocs Ai Trader

2024年5月23日

This script perform predictive analytics from a virtual trader perspective!

It acts as an AI Trade Assistant that helps you decide the optimal times to buy or sell securities, providing you with precise target prices and stop-loss level to optimise your gains and manage risk effectively.


System Components
The trading system is built on 4 fundamental layers :

1. Time series Processing layer
   
2. Signal Processing layer
   
3. Machine Learning
   
4. Virtual Trade Emulator
   

Time series Processing layer
This is first component responsible for handling and processing real-time and historical time series data.
In this layer Signals are extracted from
averages such as : volume price mean, adaptive moving average
Estimates such as : relative strength stochastics estimates on supertrend

Signal Processing layer
This second layer processes signals from previous layer using sensitivity filter comprising of an Probability Distribution Confidence Filter
The main purpose here is to predict the trend of the underlying, by converging price, volume signals and deltas over a dominant cycle as dimensions and generate signals of action.
Key terms

• Dominant cycle is a time cycle that has a greater influence on the overall behaviour of a system than other cycles.
  The system uses Ehlers method to calculate Dominant Cycle/ Period.
  Dominant cycle is used to determine the influencing period for the underlying.
  Once the dominant cycle/ period is identified, it is treated as a dynamic length for considering further calculations
  
  Predictive Adaptive Filter to generate Signals and define Targets and Stops
  An adaptive filter is a system with a linear filter that has a transfer function controlled by variable parameters and a means to adjust those parameters according to an optimisation algorithm. Because of the complexity of the optimisation algorithms, almost all adaptive filters are digital filters. Thus Helping us classify our intent either long side or short side
  The indicator use Adaptive Least mean square algorithm, for convergence of the filtered signals into a category of intents, (either buy or sell)
  
  Machine Learning
  The third layer of the System performs classifications using KNN K-Nearest Neighbour is one of the simplest Machine Learning algorithms based on Supervised Learning technique.
  K-NN algorithm assumes the similarity between the new case/data and available cases and put the new case into the category that is most similar to the available categories.
  K-NN algorithm stores all the available data and classifies a new data point based on the similarity. This means when new data appears then it can be easily classified into a well suite category by using K- NN algorithm. K-NN algorithm can be used for Regression as well as for Classification but mostly it is used for the Classification problems.
  
  Virtual Trade Emulator
  In this last and fourth layer a trade assistant is coded using trade emulation techniques and the Lines and Labels for Buy / Sell Signals, Targets and Stop are forecasted!
  
  
  How to use
  The system generates Buy and Sell alerts and plots it on charts
  Buy signal
  Buy signal constitutes of three targets {namely T1, T2, T3} and one stop level
  
  Sell signal
  Sell signal constitutes of three targets {namely T1, T2, T3} and one stop level
  
  What Securities will it work upon ?Volume Informations must be present for the applied security
  The indicator works on every liquid security : stocks, future, forex, crypto, options, commodities
  
  What TimeFrames To Use ?
  You can use any Timeframe, The indicator is Adaptive in Nature,
  I personally use timeframes such as : 1m, 5m 10m, 15m, ..... 1D, 1W
  
  This Script Uses Tradingview Premium features for working on lower timeframesIn case if you are not a Tradingview premium subscriber you should tell the script that after applying on chart, this can be done by going to settings and unchecking "Is your Tradingview Subscription Premium or Above " Option
  How To Get Access ?
  You will need to privately message me for access mentioning you want access to "Ocs Ai Trader" Use comment box only for constructive comments. Thanks !
  
  
  

2024年6月9日

リリースノート

Updates

• Adds Regime Filter and Volatility Probability Scalper
  
• Adds Quadratic Regression Filters
  
• Adds Gaussian Lorentiz Normalisation and Daten Scaling
  
• Adds Volume Float based Support and Resistance
  
• Removes Dependencies from second based data unless necessarily forced by user!
  

2024年6月9日

リリースノート

some links updated

2024年6月11日

リリースノート

Adds Alert Passcode
Adds Marubozu Abnormality Detection
Adds Probability Average and Probability variable Filtering
Adds Historical Buy Sell Positions by Algo

2024年6月29日

リリースノート

Adds Trimean based Quantitative Test
Adds Hyperbolic Trend Tests
Adds Obv based Learnings
Adds Marubozu extremes
Adds Dynamic Target 4 and Target 5
Adds Signal Improvements

2024年6月29日

リリースノート

Minor update for Stop Taking

2024年6月29日

リリースノート

removes target text bugs
adds triple impulse of balance volume

2024年7月15日

リリースノート

Adds Pivotal points and Lines
Fixes issues in target booking

2024年8月12日

リリースノート

Adds Fisher Transform to Result in a variable with an approximately normally distributed variance, stable across different values of the sample correlation coefficient.

2024年8月13日

リリースノート

Does Minor Fixes in replay mode

2024年8月13日

リリースノート

Adds Fine tuning surrounding false volume negatives

2024年8月15日

リリースノート

Adds Tolerance to Fisher Transforms and * Minor Bug Fixes

2024年8月19日

リリースノート

Adds cumulative vol delta Regime filtering !

2024年8月20日

リリースノート

Adds Volatility Derivative Filters, inspired by elder's method!

2024年8月20日

リリースノート

*minor bug fixes -in -<datum plane of volatility reference>

2024年8月21日

リリースノート

Adds Filters based on Impulsive ATR's in order to Identify/Filter periods of increased market activity

2024年9月4日

リリースノート

Adds TRIX Filter's Strength and Weakness Analyser

2024年9月6日

リリースノート

Adds Smoothness and Marubozu Considerations in TRIX Regime Based Signals

2024年9月16日

リリースノート

Adds Work around over Exponential Probability Squeeze for managing random fuzzyness

2024年9月16日

リリースノート

minor FLT plot bugs updates

2024年9月27日

リリースノート

Adds Refined Retrained Weights for machine learning models