https://imetricablog.com/2018/06/28/imetricafx-an-interactive-javafx-app-for-the-mdfa-toolkit/https://imetricablog.com/wp-content/uploads/2018/06/selection_072.pngSelection_0722019-02-27T21:23:13+00:00monthlyhttps://imetricablog.com/about/2018-06-26T14:05:59+00:00weekly0.6https://imetricablog.com/2018/06/26/mdfa-deeplearning-package-hybrid-mdfa-rnn-networks-for-machine-learning-in-multivariate-time-series/https://imetricablog.com/wp-content/uploads/2018/06/selection_070.pngSelection_0702019-09-30T18:09:44+00:00monthlyhttps://imetricablog.com/2018/06/24/mdfa-toolkit-a-java-package-for-real-time-signal-extraction-in-large-multivariate-time-series/https://imetricablog.com/wp-content/uploads/2018/06/selection_0691.pngSelection_069https://imetricablog.com/wp-content/uploads/2018/06/selection_069.pngSelection_069https://imetricablog.com/wp-content/uploads/2018/06/selection_068.pngSelection_068https://imetricablog.com/wp-content/uploads/2018/06/selection_067.pngSelection_0672018-06-24T22:26:23+00:00monthlyhttps://imetricablog.com/2016/09/28/forecasting-seasonal-adjustment-and-signal-extraction-with-usimx13-in-imetrica/https://imetricablog.com/wp-content/uploads/2016/09/selection_091.pngselection_091https://imetricablog.com/wp-content/uploads/2016/09/menu_092.pngmenu_092https://imetricablog.com/wp-content/uploads/2016/09/menu_090.pngmenu_0902016-09-28T14:54:26+00:00monthlyhttps://imetricablog.com/2012/11/14/model-comparison-with-data-sweeps/https://imetricablog.com/wp-content/uploads/2012/11/sweepstats53.jpegsweepStats5Figure 6. Model (c) (the true model) and the parameter statistics, forecast error, and data sweep controls.https://imetricablog.com/wp-content/uploads/2012/11/sweepstats63.jpegsweepStats6Figure 5. Model (b) and the parameter statistics, forecast error, and data sweep controls.https://imetricablog.com/wp-content/uploads/2012/11/sweepstats44.jpegsweepStats4https://imetricablog.com/wp-content/uploads/2012/11/sweep22.jpegsweep2Figure 2. The window sliding across different subsets of the data. The signal extractions, forecast, and model parameters are recomputed automatically as the window changes. Forecast comparisons with the real data as the window span moves is now trivial. Here, the plot in cyan represents the original time series data in-sample and the 24 step forecast out-of-sample, and the light green plot is the time series data adjusted for outliers, as indicated in the model box. One can select the plots using the "series components" plot box. The data in gray represents the time series data not used in the model estimation. https://imetricablog.com/wp-content/uploads/2012/11/sweep12.jpegsweep1Figure 1. Main drop down menu for the uSimX13 module, showing the "Sliding Span/Window Activate" check box.https://imetricablog.com/wp-content/uploads/2012/11/sweepan7.jpegsweepan7https://imetricablog.com/wp-content/uploads/2012/11/sweepan6.jpegsweepan6https://imetricablog.com/wp-content/uploads/2012/11/sweepan5.jpegsweepan5https://imetricablog.com/wp-content/uploads/2012/11/sweepan4.jpegsweepan4https://imetricablog.com/wp-content/uploads/2012/11/sweepan3.jpegsweepan32016-09-23T16:54:11+00:00monthlyhttps://imetricablog.com/2016/09/23/imetrica-for-linux-ubuntu-64-now-available/https://imetricablog.com/wp-content/uploads/2016/09/selection_087.pngselection_087The MDFA real-time signal extraction module2017-01-17T22:33:06+00:00monthlyhttps://imetricablog.com/2013/01/16/building-a-multi-bandpass-financial-portfolio/https://imetricablog.com/wp-content/uploads/2013/01/peroptimised.gifDynamic Periodogram Animation 1: The changing periodogram for different in-sample sizes and selecting an appropriate band-pass component to the multi-bandpass filter. https://imetricablog.com/wp-content/uploads/2013/01/imetrica-copyright-2009-2012-by-c-blakely_144.pngTransfer FunctionsFigure : The transfer functions for the TM and DIG filter coefficients. https://imetricablog.com/wp-content/uploads/2013/01/imetrica-copyright-2009-2012-by-c-blakely_143.pngFilter CoefficientsFigure : Coefficients for the TM and DIG log-return series. https://imetricablog.com/wp-content/uploads/2013/01/imetrica-copyright-2009-2012-by-c-blakely_142.pngOut-of-sample performanceFigure : Out-of-sample performance of the Toyota trading signal on 85 trading days. https://imetricablog.com/wp-content/uploads/2013/01/imetrica-copyright-2009-2012-by-c-blakely_141.pngCoefficients Figure : The coefficients for the MSFT and GOOG series up to lag 76. https://imetricablog.com/wp-content/uploads/2013/01/msftgoap_period.pngPeriodogram Figure : Aggregate periodogram of MSFT and Google showing the principal spectral peak directly inside the bandpass. https://imetricablog.com/wp-content/uploads/2013/01/imetrica-copyright-2009-2012-by-c-blakely_140.pngMicrosoft Signal Out-of-sampleFigure : Microsoft trading signal for 90 out-of-sample observations. The ROI out-of-sample is 31 percent. https://imetricablog.com/wp-content/uploads/2013/01/vzgoap_coeffs.pngCoefficients of the Verizon Apple FilterFigure : Coefficients of lag up to 76 of the Verizon-Apple filter,https://imetricablog.com/wp-content/uploads/2013/01/vzgoap_fit.pngVerizon Trading SignalFigure : The out-of-sample performance on 124 observations from 7-2012 to 1-13-2013. https://imetricablog.com/wp-content/uploads/2013/01/gldmdydigcoeffs_fit.pngGLD and DIG coefficientsFigure : Coefficients for the GLD and DIG filters. Each are of length 76.2016-09-08T08:21:18+00:00monthlyhttps://imetricablog.com/2013/01/03/the-frequency-effect-part-deux-shifting-time-at-frequency-zero-for-better-trading-performance/https://imetricablog.com/wp-content/uploads/2013/01/coefs_withi2.pngFilter Coefficients with Time-Shift OptimizationFigure 5: The filter coefficients with time-shift optimization. https://imetricablog.com/wp-content/uploads/2013/01/coefs_woi2.pngFilter Coefficients Without OptimzationFigure 6: The filter coefficients without the time-shift optimization. https://imetricablog.com/wp-content/uploads/2013/01/apple_i2.pngOut-of-sample performance IIFigure 4: Out-of-sample performance of the signal built with time-shift constraint and optimized for turning point-detection, The out-of-sample period beings where the light cyan is.https://imetricablog.com/wp-content/uploads/2013/01/apple_woi2.pngOut-of-sample performance IFigure 3: Out-of-sample performance of the signal built without time-shift constraint The out-of-sample period beings where the light cyan line is from Figure 4. https://imetricablog.com/wp-content/uploads/2013/01/sig_woi2.pngTrading Signal Without Time-Shift constraintFigure 2: Trading signal without the time-shift constraint set. https://imetricablog.com/wp-content/uploads/2013/01/sig_wi2.pngTrading Signal With Time-ShiftFigure 1: Trading signal with time-shift constraint set and optimized according to a financial trading criterion. https://imetricablog.com/wp-content/uploads/2013/01/applei2_optimised.gifTrading AppleAnimation 1: The out-of-sample performance over 60 trading days of signal built using a custom i2 criterion. With 5 trades and 4 successful, the ROI is nearly 40 percent. 2016-09-08T08:20:47+00:00monthlyhttps://imetricablog.com/2013/01/11/the-frequency-effect-part-iii-revelations-of-multi-bandpass-filters-and-signal-extraction-for-financial-trading/https://imetricablog.com/wp-content/uploads/2013/01/multiband_optimised1.gifMultiband_optimisedAnimation 2: Example of constructing a multiband pass using the Target Filter control panel in iMetrica. Initially, a low-pass filter is set, then the additional bandpass is added by clicking "Multi-Pass" checkbox. The location is then moved to the desired location using the scrollbars. The new filters are computed automaticall if "Auto" is checked on (lower left corner).https://imetricablog.com/wp-content/uploads/2013/01/multibandtrade_optimised1.gifTrading Out of SampleAnimation of the out-of-sample performance of one of the multibandpass filters built in this article for the daily returns of the price of Google. The resulting trading signal was extracted and yielded a trading performance near 39 percent ROI during an 80 day out-of-sample period on trading shares of Google.https://imetricablog.com/wp-content/uploads/2013/01/gnuplot-window-id-0_124.pngPlot of the Piecewise Smoothing FunctionFigure 1: Plot of the Piecewise Smoothing Function for alpha = 15 on a mutli-band pass filter.https://imetricablog.com/wp-content/uploads/2013/01/multibandtrade_optimised.gifAnimationAnimation of the out-of-sample performance of one of the multiband filters build in this article. The muitliband signal was extracted and the trading performance was near 42 percent ROI during an 80 day period on trading shares of Google. https://imetricablog.com/wp-content/uploads/2013/01/filter_final.pngFrequency Response FunctionsFigure 10: The frequency response functions of the multiband filter.https://imetricablog.com/wp-content/uploads/2013/01/coeffs_final.pngCoefficients Figure 9: The coefficients of the final filter depicting characteristics of both a trend and bandpass filter, as expected.https://imetricablog.com/wp-content/uploads/2013/01/attempt3.pngTrading Signal and PerformanceFigure 8: Third attempt at building a multiband pass filter. Here, I turn on i2 filter constraint and optimize the time shift. https://imetricablog.com/wp-content/uploads/2013/01/attempt2.pngTrading Signal and PerformanceFigure 7: The trading performance and signal for the second attempt at construction a multiband pass filter. This one included a few more higher frequencies. https://imetricablog.com/wp-content/uploads/2013/01/attempt1.pngTrading signal and Performance Attempt 1Figure 6: The trading performance and signal for the initial attempt at a building a multiband pass fitler. https://imetricablog.com/wp-content/uploads/2013/01/multiband_optimised.gifExample of Multiband passAnimation 2: The construction of the multiband pass using the Target Filter control panel in iMetrica. Initially, a low-pass filter is set, then the additional bandpass is added by clicking multiband checkbox. The location is then moved to the desired location using the scrollbars. 2016-09-08T08:20:24+00:00monthlyhttps://imetricablog.com/2012/12/31/the-frequency-effect-how-to-infer-optimal-frequencies-in-financial-trading/https://imetricablog.com/wp-content/uploads/2012/12/073.pngTrading Optimization PanelFigure 2: The financial trading optimization panel. Here the values of the optimization criteria are plotted for all the different frequency intervals. The interval with the maximum value is automatically chosen and then computed.https://imetricablog.com/wp-content/uploads/2012/12/optim21.pngOptimization PanelFigure 2: The financial trading optimization panel. Here the values of the optimization criteria are plotted for all the different values of $latex omega_2$. https://imetricablog.com/wp-content/uploads/2012/12/targetfilter1.pngTarget Filter Design PanelFigure 1: Target filter design panel. https://imetricablog.com/wp-content/uploads/2012/12/optim2.pngOptimization PanelFigure 1: The Financlal Trading optimization panel featuring the values of the rank coefficient for varying cutoffs $latex \omega_2$ in a bandpass filter with length .12. https://imetricablog.com/wp-content/uploads/2012/12/optim_final.pngOut-of-sample ApplicationAfter applying the constructed filter on the next 30 days out-of-sample. https://imetricablog.com/wp-content/uploads/2012/12/optim_insamp.pngOptimization In-sampleAfter in-sample optimization on both the customization and filter frequency band. https://imetricablog.com/wp-content/uploads/2012/12/optimised_per1.gifPeriodogram and Various Frequency IntervalsAnimation 1: Click to view animation. Periodogram and Various Frequency Intervals. https://imetricablog.com/wp-content/uploads/2012/12/optimised_trade.gifIn-sample performance Animation 2: Click to view animation. The in-sample performance of the trading signal for each frequency sweep shown in the animation above. https://imetricablog.com/wp-content/uploads/2012/12/targetfilter.pngTarget Filter PanelControl Panel for Building Target $latex Gamma(omega)$.https://imetricablog.com/wp-content/uploads/2012/12/periodogram.gifPeriodogram sweepFinding optimal frequency ranges in the data.2016-09-08T08:19:58+00:00monthlyhttps://imetricablog.com/2012/12/20/dynamic-adaptive-filtering-and-signal-extraction/https://imetricablog.com/wp-content/uploads/2012/12/example41.jpegAnother Update (shown with output of symmetric filter in gray)https://imetricablog.com/wp-content/uploads/2012/12/example31.jpegAfter Updatehttps://imetricablog.com/wp-content/uploads/2012/12/example21.jpegBefore Updatehttps://imetricablog.com/wp-content/uploads/2012/12/amplitudes2.jpegOvershooting AmplitudesFigure 5. The overshooting in the pass-band of the frequency response function multivariate filter. The spikes above one in the pass-band indicate this and will most-likely produce overshooting in the signal out-of-sample.https://imetricablog.com/wp-content/uploads/2012/12/amplitudes.jpegOvershooting Amplitudes Figure 5. The overshooting in the pass-band of the frequency response function multivariate filter. The spikes above one in the pass-band indicate this and will most-likely produce overshooting in the signal out-of-sample.https://imetricablog.com/wp-content/uploads/2012/12/example6.jpegAdaptive FilteringThe original signal (green) built using 300 observations in-sample, and then applied to 30 out-of-sample observations. A high-order approximation to the target symmetric filter is plotted in gray. https://imetricablog.com/wp-content/uploads/2012/12/example4.jpegAdaptive FilteringNot satisfied with the results of our filter update, we can easily adjust the parameters more to find a satisfying configuration. In this example, since the data is simulated, I've computed the symmetric filter to compare my results with the theoretically "perfect" filter. After further adjusting regularization parameters, I end up with this signal shown in the plot. Here, the gray signal is the target symmetric "perfect" signal. The result is a very close fit to the target signal with no overfitting. https://imetricablog.com/wp-content/uploads/2012/12/example3.jpegAdaptive FilteringAfter filter updating in the final 30 observations. We chose the filter settings in the adaptive filter settings to improve timeliness with a small amount of smoothing. Furthermore, regularization (smooth, decay) were applied to ensure no overfitting. Notice how the properties of the signal are vastly improved (namely timeliness and little to no overshooting). https://imetricablog.com/wp-content/uploads/2012/12/example2.jpegAdaptive Filtering - BeforeApplying an update to the signal by allocating the 30 most recent out-of-sample observations and computing a new filter of length 10. The blue shaded region shows the updating region. Here the old filter has been applied to the 30 out-of-sample observations and we notice significant mangling of timeliness and signal amplification in the pass-band of the filter. This is due to bad properties of the filter coefficients. Not enough regularization was applied. https://imetricablog.com/wp-content/uploads/2012/12/adaptivepanel.jpegAdaptive Filter PanelThe panel interface for controlling every aspect of updating a filter. 2016-09-08T08:19:29+00:00monthlyhttps://imetricablog.com/2013/02/14/high-frequency-financial-trading-with-multivariate-direct-filtering-i-forex-and-futures/https://imetricablog.com/wp-content/uploads/2013/02/fxy_optimised.gifAnimation 1Animation 1: Click to see animation of the Japanese Yen filter in action on 164 hourly out-of-sample observations. https://imetricablog.com/wp-content/uploads/2013/02/selection_177.pngFilter Transfer functionsFigure : The filter transfer functions.https://imetricablog.com/wp-content/uploads/2013/02/fxy_15min_result.pngJapanese Yen - 15 minute log-returnsFigure : Out-of-sample performance of the Japanese Yen filter on 15 minute log-return data. https://imetricablog.com/wp-content/uploads/2013/02/uro_period_30.pngPeriodogram comparisonFigure : Comparing the periodogram of the signal with the log-return data. https://imetricablog.com/wp-content/uploads/2013/02/symmetric_approx.pngApproximation of Symmetric filterFigure : Plot of approximation of the real-time trading signal for UROH3 with a high order approximation of the symmetric filter transfer function. https://imetricablog.com/wp-content/uploads/2013/02/uro_results.pngEuro 30-min out-of-sampleFigure : Out-of-sample performance on the 30-min log-returns of Euro futures contract UROH3. https://imetricablog.com/wp-content/uploads/2013/02/imetrica-copyright-2009-2012-by-c-blakely_167.pngCoefficients of the BP FutureFigure 6: The coefficients for the 3 explanatory series of the BP futures,https://imetricablog.com/wp-content/uploads/2013/02/bph3_gold.pngBritish Pount FutureFigure 5: The out-of-sample results of the British Pound using 30-minute return data. https://imetricablog.com/wp-content/uploads/2013/02/imetrica-copyright-2009-2012-by-c-blakely_158.pngCoefficients of the Yen filterCoefficients of the Yen filter. Here we use three different explanatory series to extract the trading signal shown in Figure 1. https://imetricablog.com/wp-content/uploads/2013/02/imetrica-copyright-2009-2012-by-c-blakely_164.pngPeriodogram of daily log-returnsFigure 3: Periodogram of Japanese Yen using 580 daily log-return observations. 2016-09-08T08:18:23+00:00monthlyhttps://imetricablog.com/2013/02/19/high-frequency-financial-trading-on-forex-with-mdfa-and-r-an-example-with-the-japanese-yen/https://imetricablog.com/wp-content/uploads/2013/02/35072310.jpg35072310Verification and cross-validation is important, just as the most interesting man in the world knows. https://imetricablog.com/wp-content/uploads/2013/02/imetrica-copyright-2009-2012-by-c-blakely_198.pngiMetrica - Copyright 2009-2012 by C. Blakely_198Figure : In-sample and out-of-sample performance of the Yen filter in iMetrica. Nearly identical with performance obtained in R. https://imetricablog.com/wp-content/uploads/2013/02/selection_197.pngIn-sample and out-of-sample performanceIn-sample (observations 1-235) and out-of-sample (observations 236-455) performance of the trading signal built in this tutorial using MDFA. (Top) The log price of the Yen (FXY) in 15 minute intervals and the trades generated by the trading signal. Here black line is a buy (long), blue is sell (short position). (Bottom) The returns accumulated (cash) generated by the trading, in percentage gained or lossed. https://imetricablog.com/wp-content/uploads/2013/02/selection_196.pngIn-sample and out-of-sample performanceIn-sample (observations 1-235) and out-of-sample performance of the trading signal built in this tutorial using MDFA. (Top) The log price of the Yen (FXY) in 15 minute intervals and the trades generated by the trading signal. Here black line is a buy (long), blue is sell (short position). (Bottom) The returns accumulated (cash) generated by the trading, in percentage gained or lossed. https://imetricablog.com/wp-content/uploads/2013/02/selection_194.pngFrequency response functions Figure : Frequency response functions of the two filters and their corresponding coefficients. https://imetricablog.com/wp-content/uploads/2013/02/out_of_samp_pi12.pngOut-of-sample Figure : Out-of-sample performance of filter with lower cutoff. https://imetricablog.com/wp-content/uploads/2013/02/imetrica_outofsample.pngiMetrica out-of-sampleFigure : In-sample and out-of-sample performance of the Yen filter in iMetrica. Nearly identical with performance obtained in R. https://imetricablog.com/wp-content/uploads/2013/02/selection_191.pngOut-of-sample performanceFigure : Out-of-sample performance of the regularized filter on 200 out-of-sample 15 minute returns of the Yen. https://imetricablog.com/wp-content/uploads/2013/02/selection_190.pngOut-of-sample Figure : Out-of-sample trading signal with regularization. https://imetricablog.com/wp-content/uploads/2013/02/selection_189.pngIn-sample performanceFigure : In-sample performance of the new filter and the trades that are generated. 2016-09-08T08:17:22+00:00monthlyhttps://imetricablog.com/2013/03/10/high-frequency-financial-trading-on-index-futures-with-mdfa-and-r-an-example-with-euro-stoxx50/https://imetricablog.com/wp-content/uploads/2013/03/selection_2471.pngTotal performance of signalFigure 15: In-sample and out-of-sample performance of the i1 constrained filter design. https://imetricablog.com/wp-content/uploads/2013/03/selection_251.pngLog-returns and signalFigure 14: In-sample and out-of-sample signal produced from the low-pass with i1 coefficient constraints. https://imetricablog.com/wp-content/uploads/2013/03/selection_250.pngTransfer functions Figure 13: Transfer function and filter coefficients after setting the coefficient constraint i1 to true. https://imetricablog.com/wp-content/uploads/2013/03/selection_249.pngConcurrent transfer functionsFigure 11: The concurrent transfer functions after changing to lowpass filter.https://imetricablog.com/wp-content/uploads/2013/03/selection_248.pngConcurrent Transfer FunctionsFigure 11: The concurrent transfer functions after changing to lowpass filter.https://imetricablog.com/wp-content/uploads/2013/03/selection_247.pngFilter performance Figure 1: Out-of-sample performance of the trading signal for the Euro Stoxx50 index futures with expiration March 18th (STXE H3) during the period of 1-9-2013 and 2-1-2013, using 15 minute log-returns. The black dotted lines indicate a buy/long signal and the blue dotted lines indicate a sell/short (top). https://imetricablog.com/wp-content/uploads/2013/03/selection_245.pngPerformanceFigure 10: Total performance over in-sample and out-of-sample periods.https://imetricablog.com/wp-content/uploads/2013/03/selection_244.pngTrades in-sample and out-of-sampleFigure 9: The total in-sample plus out-of-sample buys and sells. https://imetricablog.com/wp-content/uploads/2013/03/selection_243.pngOut-of-sampleFigure 9: Out-of-sample signal and log-return data of STXEhttps://imetricablog.com/wp-content/uploads/2013/03/selection_241.pngSelection_241Figure 7: The in-sample performance of the trading signal. 2016-09-08T08:16:36+00:00monthlyhttps://imetricablog.com/2013/02/28/high-frequency-financial-trading-with-multivariate-direct-filtering-part-deux-index-futures/https://imetricablog.com/wp-content/uploads/2013/02/optimisedstxe1.gifoptimisedstxehttps://imetricablog.com/wp-content/uploads/2013/02/selection_229.pngPeriodogram for YAPH3 and explanatory seriesFigure : The periodograms for YAPH3 and explanatory series with spectral peak in YAPH3 framed by the red dashed lines. https://imetricablog.com/wp-content/uploads/2013/02/selection_228.pngFilter coefficients for YAPH3Figure 16: Filter coefficients for the YAPH3 series. https://imetricablog.com/wp-content/uploads/2013/02/selection_227.pngSelection_227Figure : The log-returns of the ASX future YAPH3https://imetricablog.com/wp-content/uploads/2013/02/yaph3.pngOut-of-sample performance for YAPH3Figure : The out-of-sample performance of the low-pass filter on YAPH3. https://imetricablog.com/wp-content/uploads/2013/02/selection_225.pngSignal and log-return seriesFigure 12: The signal built from the extracted spectral peak and the log-return ESH3 data. https://imetricablog.com/wp-content/uploads/2013/02/selection_224.pngPerformanceFigure 13: The performance in-sample and out-of-sample of the simple bandpass filter extracting the spectral peak. https://imetricablog.com/wp-content/uploads/2013/02/selection_222.pngLog-return dataThe log-return data of ES H3 at 15 minute intervals from 1-4-2013 to 2-1-2013.https://imetricablog.com/wp-content/uploads/2013/02/selection_221.pngPeriodogramsFigure 13: Periodograms of ES H3 log-returns (red) and the explanatory series (pink). The red dashed vertical lines are framing the spectral peak between .23 and .32. https://imetricablog.com/wp-content/uploads/2013/02/selection_220.pngPerformance Out-of-sampleFigure 11: Performance out-of-sample (right of cyan line) of the ES H3 filter on 200 15 minute observations. 2016-09-08T08:15:19+00:00monthlyhttps://imetricablog.com/2013/06/14/tws-imetrica-the-automated-intraday-financial-trading-interface-using-adaptive-multivariate-direct-filtering/https://imetricablog.com/wp-content/uploads/2013/06/initiallaunchscreen.pnginitialLaunchScreenFigure 3 - The TWS-iMetrica interface when first launched and everything blank. https://imetricablog.com/wp-content/uploads/2013/06/tws_imetrica_financial_trading.pngTWS_iMetrica_Financial_TradingFigure 1: The TWS-iMetrica automated financial trading platform. Featuring fast performance optimization, analysis, and trading design features unique to iMetrica for building direct real-time filters to generate automated trading signals for nearly any tradeable financial asset. The system was built using Java, C, and the Interactive Brokers IB API in Java. https://imetricablog.com/wp-content/uploads/2013/06/selection_303.pngPlotsFigure 8 - The plots for the trading interface. Features price, log-return, account cumulative returns, signal, buy/sell lines, and up to two additional auxiliary signals. https://imetricablog.com/wp-content/uploads/2013/06/main_control_panel.pngmain_control_panelFigure 7 - The main control panel for choosing and/or modifying all the options during intraday trading. https://imetricablog.com/wp-content/uploads/2013/06/tws-imetrica-_main_interface.pngTWS-iMetrica Main InterfaceFigure 5 - The TWS-iMetrica main trading interface features many control options to design your own automated MDFA trading strategies.https://imetricablog.com/wp-content/uploads/2013/06/imetrica_mdfa.pngiMetrica_MDFAFigure 4: The iMetrica MDFA module for constructing the trading filters. Features dozens of design, analysis, and optimization components to fit the trading priorities of the user and is used in conjunction with the TWS-iMetrica interface.https://imetricablog.com/wp-content/uploads/2013/06/portfolioconstruction.pngPortfolio ConstructionThe Setup MDFA Portfolio panel featuring all the setting necessary to construct the automated trading MDFA environment. 2016-09-08T08:14:34+00:00monthlyhttps://imetricablog.com/2013/01/28/realizing-the-future-with-imetrica-and-heavy-models/https://imetricablog.com/wp-content/uploads/2013/01/scattplot.pngScatter Plot of Empirical DistributionFigure 2: Scatter plot of the empirical distribution of devolatilized values for h and mu. https://imetricablog.com/wp-content/uploads/2013/01/volplot1.pngVolatility PlotFigure 1: Plots of the filtered returns and realized measures with 20 step forecasts for Verizon for 300 trading days.https://imetricablog.com/wp-content/uploads/2013/01/imetrica-copyright-2009-2012-by-c-blakely_152.pngBayesCronos InterfaceFigure 3: BayesCronos interface in iMetrica for HEAVY modeling. https://imetricablog.com/wp-content/uploads/2013/01/gnuplot-window-id-0_151.pngEmpirical DistributionFigure 2: Empirical distribution of $latex F_{\zeta, \eta}$https://imetricablog.com/wp-content/uploads/2013/01/gnuplot-window-id-0_150.pngExample PlotsFigure 1: Plots of the $latex h_t, \mu_t$ and 20 step forecasts for Verizon for 300 trading days.https://imetricablog.com/wp-content/uploads/2013/01/imetrica-copyright-2009-2012-by-c-blakely_148.pngLog-Return and Realized Measure Data for GOOGFigure 4: The log-return data (blue) and the (annualized) realized measure data using 5 minute returns (pink). https://imetricablog.com/wp-content/uploads/2013/01/realizedpanel.pngRealized Measure ComputationFigure : Computing Realized measures in iMetrica using a convenient realized measure control panel. 2013-01-28T05:51:14+00:00monthlyhttps://imetricablog.com/2012/12/21/dream-within-a-dream-how-science-fiction-concepts-from-the-movie-inception-can-be-accomplished-in-real-life-via-mdfa/https://imetricablog.com/wp-content/uploads/2012/12/extractors.pngThe ExtractorsHaters gonna hate... extractors gonna extract. https://imetricablog.com/wp-content/uploads/2012/12/tumblr_ma0xhcw6on1qhchz6o1_400.jpgLeoNolan, why you leavin' Leo out? https://imetricablog.com/wp-content/uploads/2012/12/inception-cast-and-characters_50290a6d1de0d.pngInception posterQuestion: Why was Leo left out of the new Batman movies?https://imetricablog.com/wp-content/uploads/2012/12/inception-the-movie.pngScene from Inception“Careful, we may be in a model…within a model.” (From an Inception movie poster.)2012-12-24T22:07:24+00:00monthlyhttps://imetricablog.com/2012/11/28/hierarchy-of-financial-trading-parameters/https://imetricablog.com/wp-content/uploads/2012/11/tradeparams1.jpegTrading ParametersFigure 5: The basic trading regulation parameters currently offered in the Financial Trading Interface. This panel is accessed by using the Financial Trading menu at the top of the software. Here, we have direct control over setting the trading frequency, the trading costs per transaction, and the risk-free rate for computing the Sharpe Ration, all controlled by simply sliding the bars to the desired level. One can also set the option to short sell during the trading period (provided that one is able to do so with the type of financial asset being traded). https://imetricablog.com/wp-content/uploads/2012/11/filterdesign.jpegTarget Filter Design interfaceThe main interface for building the target symmetric filter that is used for computing the real-time (nonsymmetric) filter and output signal. Many of the desired risk/reward properties are controlled in this interface. One can control every aspect of the target filter as well as spectral densities used to compute the optimal filter in the frequency domain. https://imetricablog.com/wp-content/uploads/2012/11/zpcinterface.jpegZPC-Filter InterfaceFigure 4: The main interface for constructing Zero-Pole Combination filters, the original paradigm for real-time direct filtering. Here, one can control all the parameters involved in ZPC filtering, visualize the frequency domain characteristics of the filter, and inject the filter into the I-MDFA filter to create "hybrid" filters. https://imetricablog.com/wp-content/uploads/2012/11/realtime.jpegRealTime Filter DesignThe interface for controlling many of the parameters involved in MDFA. Adjusting any of these parameters will automatically compute the new filter and signal output with the new set of parameters and plot the results on the MDFA module plotting canvases. https://imetricablog.com/wp-content/uploads/2012/11/imetrica-copyright-2009-2012-by-c-blakely_046.pngiMetrica - Financial Trading CanvasA trading signal produced in iMetrica for the daily price index of GOOG (Google) using the log-returns of GOOG and AAPL (Apple) as the explanatory data, The blue-pink line represents the account wealth over time, with a 89 percent return on investment in 16 months time (GOOG recorded a 23 percent return during this time). The green line represents the trading signal built using the MDFA module using the hierarchy of parameters described in this article. The gray line is the log price of GOOG from June 6 2011 to November 16 2012. 2014-09-23T19:44:42+00:00monthlyhttps://imetricablog.com/2012/11/14/imetrica-economic-and-financial-data-control/https://imetricablog.com/wp-content/uploads/2012/11/datacontrol6.jpegdataControl6Figure 5. The daily log-returns of Google (GOOG) and Apple (AAPL) along with their respective volumes loaded into the data control module and plotted on the canvas. The data was uploaded by using the "Load Market Data" interface panel. https://imetricablog.com/wp-content/uploads/2012/11/datacontrol4.jpegdataControl4https://imetricablog.com/wp-content/uploads/2012/11/datacontrol3.jpegdataControl3Figure 4. The "Load Market Data" interface to download market data directly from Yahoo!. Here the daily log-returns and volume of Google (GOOG) and Apple (AAPL) are being downloaded.https://imetricablog.com/wp-content/uploads/2012/11/datacontrol2.jpegdataControl2https://imetricablog.com/wp-content/uploads/2012/11/datacontrol1.jpegdataControl12012-11-14T22:40:08+00:00monthlyhttps://imetricablog.com/2012/10/24/introduction/https://imetricablog.com/wp-content/uploads/2012/10/fintrading2.jpegHigh-Frequency Financial Trading InterfaceThe high-frequency Financial Trading interface of iMetrica. Easily construct in-sample trading strategies with an array of optimizers unique to iMetrica and then employ the strategies out-of-sample to test and fine-tune the trading performance.2012-11-14T20:01:24+00:00monthlyhttps://imetricablog.comdaily1.02019-09-30T18:09:44+00:00