Aug 1, 2018 - PDF| Market making (MM) strategies have played an important role in the electronic stock market. However, the MM strategies without any. By algorithmic, mechanical trading. This way, we get the benefits of algo trading, without fighting the high frequency firms! So, algo trading is: Trading 100% according to rules Can be computerized and programmed into software like Tradestation, NinjaTrader, etc Can be calculated manually, as long as the rules are followed.
Strategy Optimization The Strategy Tester allows you to test and optimize trading strategies before using them for live trading. During testing, an Expert Advisor with initial parameters is once run on history data. During optimization, a trading strategy is run several times with different sets of parameters which allows selecting the most appropriate combination thereof. The Strategy Tester is a multi-currency tool for testing and optimizing strategies trading multiple financial instruments. The tester automatically processes information of all symbols that are used in the trading strategy, so you do not need to manually specify the list of symbols for testing/optimization.
The Strategy Tester is multi-threaded, thus allowing to use all available computer resources. Testing and optimization are carried out using special computing that are installed as services on the user's computer. Agents work independently and allow parallel processing of optimization passes. An unlimited number of agents can be connected to the Strategy Tester. In addition, the Strategy Tester can access the.
It brings together thousands of agents around the world, and this computational power is available to any user of the trading platform. In addition to Expert Advisor testing and optimization, you can use the Strategy Tester to test the operation of custom indicators in the.
This feature allows to easily test the operation of demo versions of indicators downloaded from the. How to Optimize Optimization means multiple runs of an Expert Advisor using history data with different sets of parameters, aimed at finding their best combination. During multiple runs, different combinations of the input parameters of an Expert Advisor are tested to find the best ones.
Watch the video: How to test Expert Advisors and Indicators before purchase Watch the video to learn how to test a trading robot before you purchase it from the Market. Every product on the Market is provided with a free demo version, which can be tested in the Strategy Tester. Watch the video for details.
How to select a trading robot for testing Click ' Test' in the context menu of an Expert Advisor in the window. After that the Expert Advisor is selected in the Strategy Tester. Enable required symbols in Market Watch for multi-currency Expert Advisors The Strategy Tester allows backtesting strategies that trade multiple symbols. Such trading robots are conventionally called multicurrency Expert Advisors.
The tester automatically downloads the history of required symbols from the trading platform (not from the trade server!) during the first call of the symbol data. Only the missing price history data are additionally downloaded from the trading server. Before you start optimization of a multi-currency Expert Advisor, enable the symbols required for testing in the Market Watch. In the context menu, click ' Symbols' and enable the required instruments. Choosing Optimization Settings Before you start optimization, select the financial instrument to test the trading robot operation on, the period and the mode.
Date Select the testing and optimization period. You can select one of predefined periods or set a custom time interval.
To set a custom period, enter the start and end dates in the appropriate fields to the right. The specific feature of the tester is that it additionally downloads some data preceding the specified period (to form no less than 100 bars). This is required for a more accurate testing and optimization.
For example, if you test on a one-week timeframe, two additional years are downloaded. If there is not enough history data for forming additional 100 bars (it is especially significant for the monthly and weekly timeframes), for example, when specifying a start of testing close to the start of existing history data, then the start date of testing will be automatically shifted. An appropriate message is added to the Strategy Tester.
Forward This option allows you to check the results of optimization in order to avoid fitting to certain time intervals. During, the period set in the Date field is divided into two parts in accordance with the selected forward period (a half, one third, one fourth or a custom period when you specify the forward testing start date).
Expert Advisor optimization is performed using the data of the first period. After that 10% (in the full search) or 25% (in the genetic algorithm) of best runs are selected and then tested on the forward period. The results of the best optimization runs on both periods can be compared on tabs. Execution The strategy tester allows you to emulate network delays during an Expert Advisor operation in order to bring testing closer to real conditions.
A certain time delay is inserted between placing a trade request and its execution in the strategy tester. From the moment of sending a request till its execution, the price can change. This allows you to evaluate how trade processing speed affects the trading results. In case of the mode, users can additionally check the EA's response to a requote from the trade server. If the difference between requested and execution prices exceeds the value specified in the order, the EA receives a requote. Please note that delays work only for trades performed by an EA (placing, changing, etc.).
For example, if an EA uses pending orders, delays are only applied to placing an order but not to its execution (in real conditions, execution occurs at the server without a network delay). No delay In this mode, all orders are executed at requested prices with no requotes. The mode is used to check an EA in 'perfect' conditions. Random delay This mode allows testing an EA in conditions that are close to real ones. The delay value is generated as follows: a number from 0 to 9 is selected randomly - this is the number of seconds for a delay; if a selected number is equal to 9, another number from the same range is selected randomly and added to the first one. Thus, the possibility of a delay for 0-8 seconds is 90%, possibility of a 9-18 second delay is 10%. Fixed delay You can select one of the predefined delay values or set a custom one.
The platform measures the ping to the trade server and allows you to set that value as a delay in the tester so that you are able to test a robot in the conditions that are as close to the real ones as possible. Tick generation mode Select one of the tick generation modes:. Every tick is the most accurate but also the slowest mode.
It emulates all ticks. Every tick based on real ticks is as close to real conditions as possible. It uses of financial instruments accumulated by a broker. Emulation is not performed. Tick data has larger size.
Downloading it may take quite a long time during the first test. 1 minute OHLC — in this mode only 4 prices (Open, High, Low and Close) of each minute bar are emulated. Open prices only — in this mode OHLC prices are also modeled, however only the open price is used for testing/optimization. Math calculations — in this mode the tester does not download history data and information on symbols, as well as does not generate ticks. Only functions OnInit, OnTester and OnDeinit are called.
Thus a tester can be used for various mathematical calculations where the selection of parameters is required. For more information about tick generation, please read the. Initial deposit and leverage Specify the amount of the initial deposit used for testing and optimization. The deposit currency of the currently account is used by default, but you can specify any other currency.
However, please note that cross rates for converting profit and margin to the specified deposit currency must be available on the account, to ensure proper testing. Only symbols with the 'Forex' or 'Forex No Leverage' calculation type can be used as cross rates.
Next select the leverage for testing and optimization. The leverage influences. Note that symbol specification does not mean that the tester will use only these history data. The tester automatically downloads information on all the symbols used in the Expert Advisor. Before testing/optimization, all the available price data of the symbol on the main chart are automatically downloaded from the server.
It may take quite a long time if the internet connection is slow. Downloading of all data is performed once, only the missing information is downloaded during the next starts. Only the symbols that are currently selected in the are available for testing/optimization. The price data of all necessary symbols are automatically downloaded from the server during testing and optimization.
Testing starts and ends at 00hr.00m.00s. Of the specified dates.
Thus the start date of testing/optimization is included in the testing period, while the end date is not included. Testing ends on the last tick of the previous date. Also you cannot specify the end date, which is greater than the current one. In such case, the testing anyway will be performed to the current date (not including it). The quick optimization based on the genetic algorithm is enabled by selecting in the field located to the right. This field sets the parameter, based on which the most successful Expert Advisor runs are selected.
The larger the value of a selected parameter, the better the result. After setting all the parameters click 'Start'. This launches the process of testing and optimization. The settings of the strategy tester are memorized as testing/optimization is started. In case of a regular optimization stop (when you press the ) all the previously calculated runs are saved.
When the optimization process is resumed, it continues from the last calculated run. Selection of Input Parameters Input parameters allow you to control the behavior of the Expert Advisor, adapting it to different market conditions and a specific financial instrument. For example, you can explore the Expert Advisor performance with different and values, different periods of the moving average used for market analysis and decision-making, etc. Optimization is testing different values and combinations of input parameters to obtain the best result. To enable the optimization of a parameter, mark the appropriate checkbox. Next set the start and end of the range of values, as well as the step for testing.
You can select one or more parameters. The total number of possible combinations is displayed beneath the list of parameters. Parameter sets.
You can at any time return to the current settings of your MQL5 program by saving a set of its parameters using a context menu:. To save the parameters as a set-file on your computer, click 'Save'. These files can be moved between platforms on different computers or sent to other users. To save parameters for future use in the current platform, click 'Save Version'.
These saved presets will be available then in the 'Load Version' sub-menu. They can be applied at any time by selecting an appropriate version from the list. Start of Optimization To start optimization, click 'Start' on the 'Settings' tab. The optimization progress is displayed to the left. Where to View the Optimization Results Detailed results of each optimization run are displayed on the 'Optimization' tab.
The tab contains general testing results, including profit and the number of trades, as well as many statistical values to help assess the performance of the trading robot. See the section for details. The optimization report can be sorted by any parameter by clicking on the column header. Use sorting to find the most profitable combination of parameters and run a for a detailed report. The following values are displayed for each optimization run:. Pass — the number of the testing run;.
Result — the resulting value of the parameter that is the for selecting the best runs;. Profit — profit/loss received after the run;. Total trades — the total number of trades (deals that resulted in fixing a profit or loss) executed for the run;. Profit factor — the ratio of the total profit to the total loss in percents. A value of one means that these parameters are equal;.
Expected payoff — a statistically calculated value that reflects the average profitability/loss of one trade;. Drawdown — the relative drawdown of equity, the largest loss in percents from the maximal value of equity. Withdrawal of assets by an Expert Advisor during optimization is;.
Recovery factor — this parameter displays the risk level of the strategy (the funds that are put to risk to earn the obtained profit). It is calculated as the ratio of gained profit to the maximum drawdown;.
Sharpe Ratio — this parameter shows strategy efficiency and reliability. It reflects the ratio of the arithmetical mean profit for the position holding time to the standard deviation from it. In addition, this value includes the risk-free rate which is the interest on a certain bank deposit amount;. Optimized inputs — in addition to the common statistical values, values of set for this run are shown here. Using context menu commands you can show/hide some of the above columns.
For convenience, check the 'Switch to Optimization Results' option: once the optimization process is complete, the Strategy Tester will automatically switch to the Results tab. The same command is available in the context menu of the Journal tab. If optimization includes, this tab also contains the corresponding values of the optimization parameter (optimization criterion) for the back and forward tests. You can switch between results of back and forward testing using the context menu. A double click on one of the optimization results starts Expert Advisor with the parameters of this run (provided that the optimization is over). During one of the test runs (a population member) can have the same parameters (genes) as the previous test run. In this case, this run is not displayed on the results tab, because it has the same testing result.
However, the display all test runs to visualize the process of searching for the best result. If a line of an optimization run has the red background, it means that an occurred during Expert Advisor operation. An appropriate message is also added to the tester ('tested with error'). Optimization Cache The cache stores data about previously calculated optimization passes. The strategy tester stores the data to enable resuming of optimization after a pause and to avoid recalculation of already calculated test passes. The optimization cache is stored in Platform Data Directory Tester cache as separate binary files for each set of optimized parameters of each Expert Advisor. Files are named according to the following rule: ExpertName.Symbol.Period.StartDate.EndDate.GenerationModeOptimizationMode.Hash.opt.
Where:. ExpertName — the name of the optimized Expert Advisor. Symbol — financial instrument. Period — timeframe (M1,H1.). StartDate — the date of the optimization beginning. EndDate — the end date of the optimization.
GenerationMode —: 0 — 'Every tick', 1 — 'Every tick based on real ticks', 2 — '1 minute OHLC', 3 — 'Open price only', 4 — 'Math calculations'. OptimizationMode —: 0 — 'Slow complete algorithm', 1 — 'Fast genetic based algorithm', 2 — 'All symbols selected in Market Watch'. Hash — the hash derivative of all above parameters, which is used to find cache files.
Cache files allow viewing results of previous optimizations. Open the 'Optimization results' tab, select an Expert Advisor and a file with the desired optimization cache: The list contains all Expert Advisor optimization cache files available on the disk Optimization date, testing settings (symbol, timeframe and interval) and input parameters are shown for each file. You can additionally filter optimization results by the trade server. From the result viewing mode, you can also change the, which you selected at the start of optimization. It is displayed in the Results tab and determines the quality of a tested set of input parameters. The higher the value of the optimization criterion, the better the testing pass is considered to be. Select the desired criterion from the list at the top of the tab, and the tester will automatically recalculate all values in the 'Result' column.
To analyze results in third-party programs, for example, Office Excel, optimization report can be saved as a file through the ' Export to XML' command of the context menu. Also, the context menu features commands for exporting and importing cache files.
Use these commands to transfer optimization results between different platforms. For optimize disk space usage, cache files are automatically deleted if they are not accessed within 30 days.
During the, intermediate results are saved in the cache after the calculation of each generation (in a file platformdatafolder/tester/cache/.gen). Thus the optimization process can be interrupted at any time.
Even if the process of genetic optimization is interrupted as a result of an external factor (for example, a black out), the optimization will be automatically continued from the last calculated generation once you restart it. The genetic optimization cache is stored until the are changed or the optimization process is completed. In case of a regular optimization stop (when you press the ) all the previously calculated runs are saved. When the optimization process is resumed, it continues from the last calculated run. The Visualization of Optimization Results The Strategy Tester in the trading platform provides a powerful visualization system for presenting optimization results.
Open 'Optimization graph'. The tab contains several types of charts, you can switch between them using the context menu.
Zero line (plane) All kinds of graphs, except have a zero line (or pane if it's a three-dimensional chart). If the balance value is used as the, this line usually means the initial deposit, allowing to visually separate loss-making and profitable passes. In all other cases this line is drawn on the zero value of the optimization criterion.
Graph of results and linear chart (1D) A graph with optimization results opens by default. Each pass of an Expert Advisor with certain input parameters is displayed as a point on the graph.
The number of a pass is shown on the horizontal axis, the value of the parameter that is the is shown on the vertical axis. The linear chart (1D) shows the variation of the parameter selected as the optimization criterion (vertical axis) depending on one of the selected for the horizontal axis. To select a parameter for the horizontal axis, use the 'X Axis' command in the context menu. Flat chart (2D) and three-dimensional chart (3D) In the two-dimensional graph mode, variations of the selected used for optimization are shown on both axes. Variation of the optimization criterion is shown using the color gradient.
The deeper the color, the higher the value of the optimization criterion. In the three-dimensional visualization mode, changes of the selected used for optimization are shown on the X and Y axes. Variation of the is displayed on the vertical Z axis and using a color gradient. To select a parameters for the horizontal and vertical axes, use commands 'X Axis' and 'Y Axis' in the context menu. 3D chart management using a mouse. To move a chart, grab its central part using the left mouse button and move the cursor.
To rotate a chart around its vertical axis, grab it outside the center and move the cursor. To rotate a chart around its horizontal axis, rotate the mouse wheel holding down the 'Ctrl' key. To zoom in/out a chart, press 'Ctrl' and move the mouse cursor vertically in the central part of the chart holding down the left mouse button.
To move the zero plane, press 'Ctrl' and move the mouse cursor vertically outside the central part of the chart holding down the left mouse button. To return to the initial position of the chart, double click in its central part. 3D chart management using a keyboard. Action Keys Show/hide the grid. G Switching between solid filling and filling with lines. Space The camera moves up (the chart moves down). Up Arrow The camera moves down (the chart moves up).
Down Arrow The camera moves to the right (the chart moves to the left). Right Arrow The camera moves to the left (the chart moves to the right). Left Arrow The camera moves closer (zoom in the chart).
Plus The camera moves away (zoom out the chart). Minus Rotate the graph downward around its horizontal axis. Home Rotate the graph upward around its horizontal axis. Page Up Rotate the graph around the vertical axis counterclockwise. End Rotate the graph around the vertical axis in a clockwise direction. Page Down Moving the upward by one. Ctrl+Arrow up Moving the zero plane downward by one.
Ctrl+Arrow down Moving the zero plane upward by 10 units. Ctrl+Page Up Moving the zero plane downward by 10 units. Ctrl+Page Down Moving the zero plane to the maximum value of the graph. Ctrl+Home Moving the zero plane to the minimum value of the graph. Ctrl+End Increasing the transparency of the zero plane.
Ctrl+Plus Reducing the transparency of the zero plane. Ctrl+Minus Setting the maximum transparency of the zero plane (it disappears).
Ctrl+Right Arrow Setting the minimum transparency of the zero plane (it becomes nontransparent). Ctrl+Left Arrow Reset to default graph settings. '5' key on the num pad. Testing a Trading Robot on a Forward Non-Optimized Period Forward testing is the repeated run of the best optimization results on a different time period. This feature allows you to avoid parameters fitting in certain areas of historical data. To start the forward testing, in the Forward field of the Settings tab select the part of the for it:.
No — forward testing is not used;. 1/2 — half of the specified period is used for the forward test;. 1/3 — one third of the specified period is used for the forward test;. 1/4 — a quarter of the specified period is used for the forward test;. Custom — specify the forward test start day manually. The second (latest) part of the total period is always taken for the forward testing.
The forward test start date is displayed as a vertical line on the. The selected part is separated from the period specified in the field. The first part is the period of back testing, and the second one is the period of forward testing. The full optimization (slow or fast) of the Expert Advisor is conducted on the back testing period.
After that 10% (in the full search) or 25% (in the genetic algorithm) of best runs are selected and then tested on the forward period. There is a lower limit for the number of passes of forward testing. If the number of best runs is less than 256, the additional best runs are used for forward testing until their number reaches 256. If the number of all runs is less than 256, all of them participate in forward testing. Results of back and forward testing can be compared on the 'Optimization Results' (select 'Forward testing results' in the context menu) and 'Forward Results' tabs. The better the results coincide, the more likely it is that the Expert Advisor will show good results in real trading.
The visualization of optimization results on the forward period is available on the 'Forward optimization graph' tab. To compare these results with the backtest, switch between them using the context menu. For details about testing results please read sections. Multithreaded Testing Using Agents The multithreaded Strategy Tester uses all available computer resources.
Testing and optimization are carried out using special computing agents that are installed as services on the user's computer. Agents work independently and calculate optimization passes in parallel. Three types of agents are available: local, remote and cloud (MQL5 Cloud Network). Local agents are installed automatically when you install the trading platform.
Their number is equal to the number of logical cores of the computer. Remote and cloud agents run on other computers. For detailed information about agents, please read. Open the 'Agents' section in the Strategy Tester and select the type of agents you want to use for optimization. Tips and features:. To conserve the laptop battery, you can disable local agents and use only the remote and cloud ones. If testing/optimization is not finished manually (neither by pressing the Stop button at the nor by closing the trading platform), the processes of used local agents are not unloaded from the computer memory for 5 minutes.
This feature allows avoiding delays connected with preparing the price history and starting the agent processes when re-testing/re-optimizing the same Expert Advisor at the same symbol, timeframe and time period. Only local agents are installed together with the platform installation.
They are only used in the Strategy Tester of the local platform. That can also be connected to the global MQL5 Cloud Network can be installed only. How to Speed up Optimization Using a Local Farm of Agents You can purchase a processor with more cores, but it does not allow to multiply the number of concurrent tasks. You can create your own farm of processing agents in your local network. How to Create a Farm of Agents Install agents on each computer of the local network. If the platform is installed on a computer, open testing agents manager using the 'Tools' menu. Otherwise, download a separate application for managing agents and go through the simple installation process.
On the Services tab of the manager:. Select the number of agents to be installed. They are installed based on the number of logical cores. Enter the password for connecting to the agent.
Select a range of ports for connection. After installation, the agents are available for use from other computers on the local network. Remote agents can only be used in 64 bit systems. To save traffic and disk space, as well as for security reasons:. messages of Expert Advisors (Print function) and messages about trade operations are not added to the Journal;. DLL call is prohibited on remote agents.
How to Connect Agents Open the Strategy Tester. On tab 'Agents', select 'Local Network Farm' and click 'Add' in the context menu.
The easiest and fastest way is to automatically scan the local network for a range of IP addresses and ports. Select them and enter the agent connection password that was specified during installation. Click 'Finish' and all the found agents become available for testing. Other options to add agents:. Add agents (by IP address or domain name) — specify the IP address or domain name of a server where agents are installed, as well as the range of ports and password for connecting to the agents. Import from file.mt5 — select this option, click 'Next' and specify the file from which you want to import agents. Agents installed on the computer using MetaTester 5 Agents Manager, can be connected as remote on the same computer.
If the processor cores have extra computation power during calculations, they can take a higher load to use all the computing capacity. How to Change Agent Settings To change the settings, click the ' Edit' command in its context menu. The following fields are available in the settings window:. Name — the name of the agent;. Address — IP address and port for connecting to an agent, separated by a colon;. Password — password for connection;.
Enable — this option allows to enable or disable the use of the agent during testing and optimization. In settings of local agents only the option of enabling/disabling them is available. Import and Export of Settings of Remote Agents To make setting up of remote agents easier, the platform provides a feature for importing and exporting their settings. The files of settings have the.mt5 extension. The import and export commands are located in the context menu of the 'Agents' tab. Files of settings have the following format: Name;Address:port;Password;Description;Enable. Name — the name of the agent;.
Address:port — IP address and port for connecting to an agent, separated by a colon;. Password — password for connection;. Description — description of the hardware the agent is running on;. Enable — agent operation mode: 1 — the agent is enabled, 0 — the agent is disabled. Settings of different agents are separated from each other with line breaks. How to Speed Up Optimization Using the MQL5 Cloud Network allows you to quickly optimize your Expert Advisors using the power of thousands of computers. The network combines remote agents and distributes optimization tasks among them.
The Strategy Tester connects to the cloud network through multiple access points, which are distributed on a territorial basis (e.g., MQL5 Cloud Europe). Features of the MQL5 Cloud Network. The entire power of the MQL5 Cloud Network is used only for. During, only agents of one access point are used.
It is connected with the specific features of the genetic algorithm. The genetic optimization mode is automatically enabled when the total number of optimization steps exceeds 100 million. MQL5 Cloud Network can be used in 64 bit systems only.
In addition to using the MQL5 Cloud Network, you can provide your CPU computing power in the network. To install the remote agents and include them into the network, use a special utility. Read more about the MQL5 Cloud Network on. Payments for the Use of the MQL5 Cloud Network. Using agents of the MQL5 Cloud Network is paid. The formula for calculating the cost is described in.
The current MQL5.community account balance is displayed above the list of cloud agents. To use MQL5 Cloud Network a user needs to have at least 1 US dollar on the MQL5.community account. Tasks are passed in packages to several access points simultaneously, and the user must be able to pay for completion of that tasks. The Network is not able to calculate the exact cost as the time and resources required for calculations cannot be estimated precisely before the start of calculations.
Enabling MQL5 Cloud Network To use the network agents, enable them using command ' Enable' in the context menu. Since the MQL5 Cloud Network is a paid service, a user must have an account at the website, through which all the accounting operations are performed.
Account details are specified on the tab of the platform settings. If you do not specify the details of your MQL5.community account before enabling the MQL5 Cloud Network agents, you will be offered to do this. If you have not registered on the website, use the link. Starting Calculations Using the MQL5 Cloud Network Like with a conventional optimization, you need to set all the testing options and Expert Advisor input parameters. On the Agents tab, you can monitor how the Strategy Tester distributes tasks to available agents.
The number of available and currently used agents is displayed for each access point. Traders may need to run hundreds of thousands of optimization passes in a reasonable time. With the multi-threaded Strategy Tester and the MQL5 Cloud Network, in one hour you can complete the calculations that would require a few days without the network. The computing power of thousands of cores is available straight on the trading platform.