If you have been around algorithmic trading for a while you have probably heard some version of the “switch” concept. This is one of the holy grails of systematic trading, describing an ability to be able to change the way one acts in the market according to market conditions. Today I want to talk about […]
Posts Tagged ‘system evaluation’
- 2017: Jan Feb Mar Apr May Jun Jul Aug Sep Oct Nov Dec
- 2016: Jan Feb Mar Apr May Jun Jul Aug Sep Oct Nov Dec
- 2015: Jan Feb Mar Apr May Jun Jul Aug Sep Oct Nov Dec
- 2014: Jan Feb Mar Apr May Jun Jul Aug Sep Oct Nov Dec
- 2013: Jan Feb Mar Apr May Jun Jul Aug Sep Oct Nov Dec
- 2012: Jan Feb Mar Apr May Jun Jul Aug Sep Oct Nov Dec
- 2011: Jan Feb Mar Apr May Jun Jul Aug Sep Oct Nov Dec
- 2010: Jan Feb Mar Apr May Jun Jul Aug Sep Oct Nov Dec
- 2009: Jan Feb Mar Apr May Jun Jul Aug Sep Oct Nov Dec
December 2017
November 2017
October 2017
July 2017
- Building "the switch" using machine learning
- Predicting trading system out-of-sample success using chaos properties of financial time series
April 2017
March 2017
- Finding out which simple system selections have worked in the past using a GPU
- Visualizing IS/OS relationships in our price action based repository
- A script to retrieve account results from Oanda using the RESTv20 API
- Three basic ways to classify trading system backtesting statistics
January 2017
November 2016
- Introducing pKantuRL: GPU enabled mining for reinforcement learning based systems
- Reinforcement learning in trading: What about random data?
October 2016
- New credit card sized computers for back-testing, system mining and trading
- Making OS predictions using FX symbol market conditions
- Getting an account performance summary directly from Oanda using their REST API and Python
August 2016
- Using QQPat: Calculate and plot the Losing Period Overlap Index
- Finally an out-of-sample performance predicting model that works (a bit)
- How long does it take to see in-sample/out-of-sample variable correlations?
- The Sharpe Ratio: Be careful with comparisons
July 2016
June 2016
- The Omega ratio: A much better performance metric than the Sharpe?
- Getting your backtesting results out of Quantopian and into QQPat
- Automatically downloading and saving 1M from FXDD using Python
- Are islands always better than peaks? About system parameters in Forex trading
- Dealing with Forex data time zones using Pandas
- Relationship between returns and market conditions viewed from the fractal dimension
- Measuring trading system correlation using Python
- Using qqpat: Analyzing your MT4 back-testing results using Python
May 2016
- Do Monte Carlo simulations say anything about system robustness?
- Looking at an old Forex system: The God's Gift ATR
- Using qqpat: When should you expect to see long term statistics?
- What do top out of sample performing trading strategies have in common
March 2016
- After more than one year of trading: Are there any in-sample/out-of-sample correlations?
- Backtesting Trading Systems in Python: Not a really good choice
February 2016
- Using Monte Carlo simulations in trading: Key assumptions
- Graphically identifying trading system worst cases using qq-pat
- Trading System Failure: Easy worst case detection using qq-pat
- Monte Carlo Simulations: Updating failure detection
- Reducing Drawdown Length: Why you can only go so far
- The Rolling Correlation Index: A better measurement for system relationships
- Using qq-pat to find your trading system's worst case statistics
January 2016
December 2015
- Know your data: Find your Forex data's GMT shift and DST offset using the NFP news release
- Oanda's not-so-good 1M data: Can you trust your own broker's historical data?
- Is your trading system under-performing? Properly comparing statistics using python
- Using qq-pat: Getting Monte Carlo simulations for your trading system
- The Maximum Drawdown: Extreme statistics are a poor proxy for true risk
- The brick wall in trading system design: Understanding the limitations of historical data
- Using OpenKantu in Practice: Is old Forex data irrelevant in today's market?
- Is your Forex data full of holes? A script for the evaluation of Forex data quality using Python
- Introducing qq-pat, an open source library for the calculation of financial time series statistics
- Understanding financial time series data: Why a 1D bar is not the same as a 1M bar
- Using OpenKantu in Practice: Analyzing system generation results using R
- Looking into the Sharpe Ratio: Problems, solutions and improvements
November 2015
- Compiler Optimizations: How your backtesting speeds can change depending on how you compile your software
- Powerful Statistical Analysis: Using Pyfolio to analyse your MT4 backtesting results
- Updating OpenKantu to v2.10: Fixing my open source trading system generator for a wider trader audience
- Powerful statistical analysis: Take your MT4 backtesting results to R
October 2015
May 2015
- How far should we go into the past for Forex simulations: Is old data really useless?
- Some algorithmic trading systems from 2010: Revisiting three trend following strategies (BB, CCI and RSI)
January 2015
September 2014
March 2014
- Accurate and systematic evaluation of Data Mining Bias (DMB) in trading strategy creation
- Going below the one minute timeframe: Implementing simulations with Tick-by-tick resolution
February 2014
- What trading system failure means: Defining and quantifying strategy failure, Part 2
- What trading system failure means: Defining and quantifying strategy failure, Part 1
- Using R in Algorithmic Trading: Performing a portfolio test using a rolling window Markowitz optimization
- Beyond Simple Linear Regression: Calculating the Ideal R (IR) for a trading strategy
January 2014
- Choosing trading system combinations: A practical example using rolling correlations
- Using R in Algorithmic Trading: Calculating system weights using Markowitz portfolio theory
- Using R in Algorithmic Trading: Analysing your Trading System's Historical Results
September 2013
June 2013
- Getting data from non-Forex instruments for Forex trading in F4: Dynamically communicating with the Yahoo Finance API using curl
- No more MT4 Back-testing! :o) Moving to a professional, C/Python Backtester for the F4 Framework
- Accurate Forex Trading Simulations Including Historically Accurate Swap Rates: Why interest is so important
May 2013
February 2013
December 2012
- Seasonal Effects: Finding and Using Them to Improve Your Forex Trading Systems
- Can the Lower Time Frames be Useful? : Discussing Information, Robustness and Reliability
- Implementing Another Front-end: Asirikuy Systems Now Trading on MT5 using the F4 Framework
November 2012
- Time Filtering Doesn't Reduce Robustness: Qallaryi's 25 Year Simulated Results
- Cutting Out the Fat at Asirikuy: Changing To Higher Requirements for Trading Strategies
- Enhancing Robustness: Implementing Modifications to Remove a Strategy's Feed Dependency
- Feed Dependency in Higher Time Frame Algorithmic Systems in the Forex Market: Causes and Effects
October 2012
- Walk Forward Analysis: Does the data you use matter ? Looking into some assumptions made by WFA
- One Size Doesn't Fit All: Taking Care of Explicit Correlations in Monte Carlo Simulations
- Judging Trading Strategy Survivability: Looking at Systems like the Military
- Implementing Next-Generation Testing: The Power of the New F4 Strategy Tester Module
- Understanding the Parameter Space: Some Frequently Asked Questions (FAQ)
- Signal Problems: Obtaining Reliable Historical System Correlations for Portfolio Trading
September 2012
- Learning from the past, moving towards the future: Updating to F4 Atinalla Portfolios
- Trading System Walk Forward Analysis: Are you sure you're adapting?
- To Stop or Not to Stop: When is it the Best Time to Stop an Automated Trading System
May 2012
September 2011
August 2011
July 2011
June 2011
- Cause and Effect: Understanding Correlations in Trading Systems and Portfolio Results
- Improving the Asirikuy Performance Analyzer: Towards Better Live Testing Analysis
- Understanding Trading System Evolution: Worst Case Scenarios ARE Dynamic
- Getting Powerful Trading Account Reporting: Using the MyFXBook API
- Back/Live Testing Consistency: Using Different Brokers For Long Term Simulations and Live Trading
- Monte Carlo Simulation Distortions: What They Are Useful For When Developing Portfolios
- The Chi-Squared Test: How to Use This Statistical Tool in Forex Algorithmic Trading
- Analyzing System Results: The Power Of Logarithmic Equity Curves
- Getting to Know Trading Systems Better: Analyzing Strategies Through Custom Ratios
May 2011
- The Time Array Mismatch Problem: A Dark MT4 Secret Comes to Light
- Neural Networks in Trading: Are Trade Results Correlated? Using an NN for Money Management. Part One
- The Golden Problem: Why It is Difficult to Come Up With a Good Trading System for Spot Gold and Some of My Findings
- High Vs Low Reward to Risk: Is One Approach Better Than the Other?
- Getting Asirikuy "Together": Building a Comprehensive Database Solution for Our Results
- How Many Trades are Enough Trades? : Answering the Question of Trade Frequency From a Statistical Perspective
- Understanding Broker Dependency: What Makes Results Different From One Broker to Another
- Re-Evaluating Our Amachay Portfolio: Going the Simple Route
- Diversification in Trading: Not as Simple or Obvious as Most New Traders Think
- Amachay Gets Ready for Its Live Trading Debut: A Full Fibonacci Based Strategy Portfolio
- Missing the Money Train: The Psychological Effect of Positive Performance
- When You Should NOT Trade a Given System: Five Red Flags To Avoid Trading a Strategy
- When the Storm Comes: Five Tips to Deal with the Arrival of Monte Carlo Worst Case Scenarios
April 2011
- Analyzing the Asirikuy System Backtest Database: A Great Excel Analysis Tool
- The Asirikuy Performance Analyzer: A New Convenient Tool For On-The-Fly Analysis
- Trade More or Trade Less: Getting Clearer About This Issue
- Evaluating/Simulating Broker Dependency: What Changes in a System from Broker to Broker?
- Measuring System Quality: Should We Only Use Monte Carlo Criteria?
- The Effects of Increasing System Number: The Deterrents of Big Portfolios
- Indicators Vs Price Action: Is One Better Than the Other ?
- My April Currency Trader Magazine Article: Creating Systems From An Edge Ratio Analysis
- Trade More or Trade Less: The Incidence of Trading Frequency in System Quality
March 2011
- Historical Max Draw Down Abundance in Monte Carlo Simulations: An Excellent System Quality Indicator?
- An Interesting Phenomena: Investigating the Distribution of Return of Trading System Portfolios
- Our First Tests of Indicator Independence: Porting Teyacanani to Use Our TA-Lib MT4 DLL
- Custom Indicators and Back-Testing Speed in MT4: How to Make Your Custom Indis Fast
- Problems with "Big Trading Portfolios": Issues That Show Up When Running Large Arrays of Systems
- Choosing Portfolios Without Bias: Some Strategies Against the "Cherry Picking" of Systems
- Coatl's First Serious Test of Robustness: Facing the JPY During a Week of Intervention and Disaster
- The Ideal Forex Strategy Tester: Features and Key Characteristics
- Improving Our Monte Carlo Simulator: Now With Virtually No Trade/Iteration Size Limitations :o)
- Neural Networks in Trading: How To Properly Evaluate NN Derived Strategies
- Profit Evolution in Asirikuy: Looking at The Asirikuy Index and Its Interpretation
- Walking Forward: Do Asirikuy Systems Yield Profit With Continuous Optimizations ?
February 2011
- Ending an Important Cycle: No More Commercial Forex System Reviews for Me :o)
- Looking at myforexdot.org.uk, an Excellent Website with a Lot to Say
- Developing an Iron-Clad Trading Setup: The First 20 Year Coatl System Portfolio
- Out of Sample Testing: The Power and Correct Execution of This Simulation Technique
- The Wonderful Things About Alternative Testing Solutions: A FreePascal Tester Vs MT4
- The Need for Platform Independence: Analyzing the Odd MT4 Indicator Implementations
- Trading Across Important Market Changes : A DEM/USD Designed System Trading the EUR/USD
- Evolving Our Spread Changing Capabilities: An Improved MT4 Spread Changer for Asirikuy
January 2011
- Talking About "Party Time" : For How Long Could We Expect Profitable Strategies to Remain Profitable
- Trying to Measure a Trading System's Robustness : The Hardness Index
- Measuring a System's Psychological Pressure: The Ulcer Index
- Comparing Your System's Profitability Against Random Outcomes : An Edge or Just Luck ?
- Get Your Feet On Earth: Understanding the Difference Between Expected and Real Profits
- Trading System Transparency : The Problems of Blurry Logic
- Why No EUR/CHF or EUR/GBP One Hour Systems? : Looking Into the Problems of Long term Simulations on These Pairs Based on 1M Data
- Banging Trading Systems Against the Wall : Stress-Testing Strategies to Evaluate Their Robustness
- Can a Computer Design a Trading System ? Part Six : A Twenty Instrument Portfolio
- The Big System Portfolios : The Wonderful Effect of "Piling Up" Strategies
- Evaluating System Distributions : How Many Trades are Enough Trades ?
- Improving Our Asirikuy Analysis Tool : Implementing Monthly Return Analysis
December 2010
- Getting Better at Monte Carlo : Distribution Based Simulations of Trading Strategies
- Better System Analysis : Our Own Asirikuy Delphi Monte Carlo Simulator
- Metatrader 4/5 Simulations : Our Intention to Move Beyond
- Modelling Quality in Metatrader 4 : An Almost Meaningless Number
- Accurate Scalper Development : What Needs to Be Done to Reliably Develop Scalping Strategies
- Knowing When Systems Stop Working : Why Learning System Worst-Case Statistics is Vital for Success
- The Lower Time Frame Problem : Why Metatrader Cannot Accurately Simulate Systems Below the 30 Minute Time Frame (NOT even With 99% Testing Quality)
- Are Our Assumptions True ? : Validating the Ten Year Back-testing Hypothesis
November 2010
- One System to Rule Them All : Developing Strategies For All Forex Instruments
- Analyzing System Results On the Run : The Asirikuy "EA Analyzer" Indicator
- The Frequency Distribution of Returns : Developing Further Criteria to Determine When a System Stops Working
- Automated Trading Execution : Dependent Vs Independent Platform Solutions
- Taking Advantage of Control Point Simulations : In-Depth Studies of Simple Strategies
- Stress Testing Systems : Learning About Monte Carlo Simulations
- Destroying a Mechanical Trading Myth : Frequent Short Term Optimization Works
- The Development of Robust Basket Systems : Systematically Improving Their Results
- Changing the Spread in the MT4 Strategy Tester : My SpreadChanger Program Solves the Problem
- The Dangers of Real Live Results : No Understanding, No Meaning
October 2010
- Can a Computer Design a Trading System ? Part Two : Genetic Programming
- Optimizing Without Curve-Fitting : Six Tips to Avoid Over-Optimization
- Robustness : Ideal Trading System Characteristics to Withstand Change
- Monthly Return Analysis : A Basic Tool to Understand Your Trading System
- Backtesting With the New Alpari Data : Some Findings and Changes
- Destroying a Myth : Past Results Do Not Matter
- Can We Run Reliable, Computationally Cheap System Simulations on Metatrader 4 ? : Using the Control Points Method Accurately
September 2010
- Short Term Randmoness and Long Term Statistics : Learning to Evaluate the Live Results of a Trading System
- Why Demo Testing a System is NO Good : Five Reasons Why You Should Always Test Systems With Real Money
August 2010
- The Pain Index : A Measurement of How Hard it is to Trade a System from a Psychological Perspective
- To Trade or Not to Trade : A Little Bit About Friday Trading
- Evaluating Trading Systems : Characteristics and Quality
July 2010
- Why Catastrophic Losses in Forex are Always Possible : A Look at the Forex Worst-Case Scenario
- Judging by the Amount of Trades. Does it Really Matter ?
- How we Have Been Fooled : An Evaluation of Traditional Indicator Setups
June 2010
April 2010
March 2010
February 2010
January 2010
November 2009
June 2009
- You think your expert advisor is profitable ? Profitable, may not mean Profitable
- Testing Every Expert Advisor, The WRONG Strategy !