Trading Systems
Trading Software
Trading Signals
Trading Software
Our trading software includes advanced technical indicators and a powerful swarm adaptation engine that adapts trading system parameters walking-forward. These products integrate within the BioComp Dakota application framework.
Trading Software Designed to Adapt
BioComp Dakota is a product of BioComp Systems Inc. BioComp Systems provide state of the art modeling, prediction and optimization technologies to corporations and individuals. Dakota is a stand-alone application for building trading systems. The Dakota application framework is flexible thereby, enabling trading systems developers to plug-in their own technical indicators / trading rules, performance engines and adaptation routines.
Whether you are building new systems or updating existing systems Dakota runs in 100% walk-forward mode. Trading simulations should be as realistic as is possible. There is absolutely no point in finding optimal trading system parameters over a 10 year period and then running a trading simulation over the same 10 year period. Even looking at a chart while modifying trading system parameters results in a 'future leak'. When price data for a given trading period (bar) is processed, trading system parameters are adapted using data up to the most recent bar and never beyond. It is our belief that eventually all trading systems software will operate on this basis.
Dakota is superior because historical optimizations are occurring bar by bar. i.e. There is not a huge 'jump' from one optimization period to the next. This enables smooth adjustments in trading system parameters to take place walking-forward. Some trading systems software applications run walk-forward simulations by organizing in-sample and out-of-sample periods so that a new out-of-sample period starts when the prior out-of-sample period finishes. This is the approach that we used over 10 years ago. The 'block by block' approach is better than optimizing over the entire simulation period and thereby producing no out-of-sample results. However, the fact that historical optimizations occur over distinct and potentially very different periods introduces numerous issues that are difficult to work around.
A Dakota trading system is made up of a set of trading robots. The set of bots is referred to as a swarm. Typically, each bot in a swarm is based on the same technical indicators and trading rules. Parameter values for technical indicators and trading rules vary from bot to bot within user defined ranges and are adjusted as new data is processed. Adaptation occurs via the bar by bar adjustments in bot parameter values. The trading system signal is computed by combining the trading signals generated by each of the bots in the swarm.
The swarm adaptation engine is responsible for the bar by bar adaptation of bot parameter values. A trading systems developer can use any technology or set of rules to define the adaptation process. For example, a given trade bot's parameter values can be moved closer to those of the best performing bot in the swarm as well as the trade bot's best position over the performance lookback period. Any suitable algorithm can be used by the trading systems developer to enable the adaptation process. Our swarm adaptation engine for Dakota is the result of hundreds of hours of research and development and has been proven to be effective when applied to S&P 500 data from 1970 to date.
Trading system parameters are generally adjusted gradually period by period by the swarm adaptation engine. Although, relatively rapid adjustments in parameter values occur when significant changes in market behaviour occurs. For example, a simple moving average is used along with some trading rules by each of 60 bots in a swarm. The length of the SMA is set to vary anywhere from 2 to 30 trading days. Bot number 1 is currently using a 9 period SMA and bot number 2 is currently using a 12 period SMA and so on. The minimum period used by the bots in the swarm is 8 trading days and the maximum is 15 trading days. In 20 trading days time the period of the SMA used by each bot will have potentially changed due to the bar by bar adaptation. The minimum period is now 11 trading days and the maximum is 18 trading days.
The spread in parameter values provided by the swarm of bots is just as valuable as the adaptation process itself. The bots in a swarm will tend to be in the vicinity of the historically best performing bot. The best set of parameter values in the future is often not equal to the parameter values of the currently best performing bot, but will often be in the vicinity of those parameter values. Trading simulations that exclusively use the signal generated by the best performing bot in the swarm usually produce inferior results compared to using the average of all bot signals in the swarm.
ATS Indicator Add-Ins
Quality technical indicators are the cornerstone of effective trading systems. Our trading software is innovative and built upon advanced concepts. For instance, the CPredictor is based on the k-nearest neighbor algorithm and predicts the direction that a given oscillator will move in.
--- Innovative Trading Software including Advanced Technical Indicators ---
TrendOscillator and WaveOscillator
for BioComp Dakota
for BioComp Dakota
All ATS BioComp Dakota Indicator Add-Ins Include ScriptBots from the ATS ScriptBot Library applicable to the Add-Ins purchased.
The WaveOscillator technical indicator add-in is a wavelet transform designed to extract the phase of price fluctuations for a user defined period.
The TrendOscillator indicator add-in shares some of the basic functions with the WaveOscillator. It is designed to continue to output a positive trading signal while market prices are rising over the user defined period.
Both the TrendOscillator and WaveOscillator have proven to be effective for modeling the S&P 500 index and stock index futures contracts in particular.
The TrendOscillator indicator add-in shares some of the basic functions with the WaveOscillator. It is designed to continue to output a positive trading signal while market prices are rising over the user defined period.
Both the TrendOscillator and WaveOscillator have proven to be effective for modeling the S&P 500 index and stock index futures contracts in particular.
USD $295
Hypothetical equity curve for a Dakota System based on the WaveOscillator
CPredictor USD $295
for BioComp Dakota
for BioComp Dakota
The CPredictor is based on the k-nearest neighbor algorithm. It is designed to predict the short-term trend of a given indicator on a walk-forward basis. The CPredictor is highly non-linear and adaptive by nature.
Dakota ScriptBots for predicting the trend of indicators such as the Aroon, CCI, DblStoch, DirectionalEntropy, ProjectionOscillator, RSI, Stochastic, StochRSI, TrendOscillator, WaveOscillator and ZScore are included. Note that TrendOscillator and WaveOscillator technical indicator add-ins are a separate product.
Dakota ScriptBots for predicting the trend of indicators such as the Aroon, CCI, DblStoch, DirectionalEntropy, ProjectionOscillator, RSI, Stochastic, StochRSI, TrendOscillator, WaveOscillator and ZScore are included. Note that TrendOscillator and WaveOscillator technical indicator add-ins are a separate product.
Hypothetical equity curve for a Dakota System based on the CPredictor
WaveIndicators for BioComp Dakota, Patterns and Profit 8
USD $295
The WaveIndicators Library for BioComp Dakota, Patterns and Profit 8 includes the WavePeriod, WaveOsc2 and WaveTrend2 technical indicators. These indicators are based on vibration (resonance) theory.
The WavePeriod indicator returns a bar by bar estimation of the dominant period in price fluctuations in the vicinity of the Period specified by the user.
The WaveOsc2 indicator is designed to estimate the phase of a given semi-periodic fluctuation in the input series with as close to zero lag as possible.
The WaveTrend2 indicator is designed to estimate the total displacement attributable to a series of semi-periodic fluctuations in the input series.
Hypothetical equity curve for a Patterns System based on the WaveIndicators
ATS Swarm Adaptation Library for Dakota
The ATS Swarm Adaptation Library for BioComp Dakota includes the ATS Equity Engines for Dakota. Swarm adaptation is at the heart of the Dakota application and thousands of hours of research and development have been invested in our adaptation algorithm. The ATS Equity Engines provide the swarm adaptation algorithm with performance metrics. Adaptive trading systems software is a must.
Updates of these products are provided free for lifetime and installation 'keys' are not required.
ATS Swarm Adaptation and USD $595
Equity Engine Add-Ins for Dakota
Equity Engine Add-Ins for Dakota
The ATS Swarm Adaptation Library for BioComp Dakota is built upon the SMARTswarm algorithm. The SMARTswarm algorithm smoothly adjusts the convergence and velocity factors of trade bots based on walk-forward performance.
Minimum and maximum rates of convergence and the number of discreet subswarms are user definable parameters. Default SMARTswarm parameter values that generally produce the best performance are provided.
The swarm pictured on the right is running 5 discreet sub-swarms each with 15 trade bots. Notice how the overall swarm is able to occupy an irregular volume within the parameter space.
Image of a swarm of trade bots in BioComp Dakota
The ATS Dakota Equity Engines measure the performance of each trade bot over the lookback period and feed this information to the swarm adaptation engine on a bar by bar basis. The adaptation engine determines the parameter values for each of the trade bots that, in turn, produce trading signals. There are 6 ATS Equity Engines included in the package.
Updates of this product are provided free for lifetime and no installation 'keys' are not required.
The ATS NDC Equity Engine returns the net direction correct.
The ATS PPCT Equity Engine returns the proprotion of perfect given a user defined desired maximum average trading period.
The ATS PPEC Equity Engine returns the proportion of perfect trading multiplied by the relative equity straightness.
The ATS PPIP Equity Engine returns the proportion of perfect trading (while in position).
The ATS WNDC Equity Engine returns the weighted net direction correct.
The ATS WPP Equity Engine returns the weighted proportion of perfect.
Image of ATS Equity Engines within BioComp Dakota
ATS ScriptBot Library for Dakota
The ATS ScriptBot Library can function with or without the ATS Swarm Adaptation Library. However, it is important to note that some of the ScriptBots included in the library require the ATS Technical Indicator Add-Ins for Dakota. The ATS Indicator Add-Ins and ATS ScriptBot Library are separate products.
The ATS ScriptBot Library is a formidable collection of over 1,500 Dakota ScriptBots that are a valuable resource when developing Dakota systems. The library is extended on a reasonably frequent basis.
All ScriptBots can be configured to function as either counter trend or trend following systems and to use intermarket data to generate the trading signals. All of this is done via the Dakota user interface.
All ScriptBots can be configured to function as either counter trend or trend following systems and to use intermarket data to generate the trading signals. All of this is done via the Dakota user interface.
ATS ScriptBot Library USD $395
Updates of this product are provided free for lifetime and no installation 'keys' are not required.
Image of the ATS ScriptBot Library as it appears in Windows Explorer
ATS EST ScriptBot Library for Dakota
The purpose of the Ensemble Signal Trader (EST) ScriptBots is to read in trading signals exported from other systems (usually Dakota systems) and process them to produce a single 'meta-system' trading signal. Layered or tiered architectures consisting of regular Dakota systems as well as EST systems can be constructed.
The objective is to build Dakota meta-systems that are more complex, more intelligent and more adaptive than any of the individual component systems. Note that all Dakota systems can be updated daily during a single Dakota batch processing run by listing the systems according to system dependencies in the Dakota batch processing file.
The objective is to build Dakota meta-systems that are more complex, more intelligent and more adaptive than any of the individual component systems. Note that all Dakota systems can be updated daily during a single Dakota batch processing run by listing the systems according to system dependencies in the Dakota batch processing file.
List of EST ScriptBots in BioComp Dakota
Updates of this product are provided free for lifetime and no installation 'keys' are not required.
ATS EST ScriptBot Library USD $395
Example of a Dakota Meta-System Architecture utilizing EST ScriptBots
Bundled Trading Software Packages
AdaptiveTradingSystems.com in conjunction with BioComp Systems, Inc. offer the following bundled trading software packages. If you are an existing customer of AdaptiveTradingSystems.com and you would like to purchase additional products then please email info@adaptivetradingsystems.com for customized pricing.
ATS Software & ScriptBot Libraries for Dakota
USD $1,589
ATS Trading Software Kit for Dakota:
- CPredictor Indicator Add-In
- TrendOscillator Indicator Add-In
- WaveOscillator Indicator Add-In
- WaveIndicators Indicator Add-Ins
- ATS Swarm Adaptation Library
- ATS Equity Engines
- ATS ScriptBot Library
- ATS EST ScriptBot Library
Represents a discount of USD $681 compared to the sum of the regular retail prices!
BioComp Dakota EOD Standard License Plus ATS Software & ScriptBot Libraries for Dakota
USD $2,385
Represents a discount of USD $880 compared to the sum of the regular retail prices!
NOTE: Hypothetical or simulated performance results have inherent limitations. Unlike an actual performance record, simulated results do not represent actual trading. Also, since the trades have not actually been executed, the results may have under- or over-compensated for the impact, if any, of certain market factors, such as lack of liquidity. Simulated trading programs in general are also subject to the fact that they are designed with the benefit of hindsight. No representation is being made that any account will or is likely to achieve profits or losses similar to those shown. Past performance of our trading systems, trading software and trading signals, whether actual or indicated by simulated historical tests of trading strategies, is not indicative of future results.
© Copyright 2008-2012 Adaptive Trading Systems