April 2012 was the first month of the upgraded Danica 1.3. While the forecasts for daily low and high were strongly positively correlated with reality, the predicted changes in the daily close were on average anti-correlated with the actual ones. This system performance review consists of a summary section reporting the figures of merit for the forecasting quality, followed by 14 subsections, dedicated to the individual exchange rates tracked by the system. Those contain the usual green-yellow-blue-red color-coded charts of the performance, such as shown below, for each currency pair. Fig. 0: EUR/USD bar chart for April 2012, color-coded to indicate the degree of success in the forecast for close. Yellow and green bars have been predicted successfully as bearish and bullish respectively; blue and read are unsuccessful bearish and bullish predictions, respectively. The system delivered below-average performance for EUR/USD this month. For comparison with the previous month, you may want to take a look at the March 2012 performance review.
-
April 2012 performance review for Danica
- Tags:
- frontpage
May 6 2012, 4:57pm | Comments »
-
April 2012 Correlation Report
Forex Correlation Analysis Report This monthly forex correlation analysis report is computer-generated. The report follows structure and definitions explained in a separate document, which can be used as a user manual. The report deals with the following exchange rate time series: AUDJPY, AUDUSD, CHFJPY, EURAUD, EURCHF, EURGBP, EURJPY, EURUSD, GBPCHF, GBPJPY, GBPUSD, USDCAD, USDCHF, USDJPY. Table 1. Forex Automaton Index updates for April 2012. CERPI -- Currency Exchange Rate Predictability Index, CERCSI -- Currency Exchange Rate Correlation Strength Index. volatility 1H.1M CERCSI 1H.1M CERPI 1H.1M 0.00106093 0.377023 0.0557995
- Tags:
- frontpage
May 5 2012, 1:03pm | Comments »
-
ForexAutomaton 2012. The Fourth Annual Summary of Research Progress.
Four years of ForexAutomaton's life are over. This year I have been busy starting a currency risk consulting company, along with two partners, therefore less than the usual amount of research content has been published here. Nonetheless, the automated systems -- Danica, Demi, and Heidi -- have been living their silicon-based lives as before, with little to no interference from their creator. This fourth annual report is dedicated entirely to news from their side.
- Tags:
- frontpage
April 8 2012, 6:00pm | Comments »
-
March 2012 performance review for Danica
During March 2012, the third month of the third year of Danica's live operation, the system continued on auto-pilot without parameter changes. While the forecasts for daily low and high were strongly positively correlated with reality, the predicted changes in the daily close were on average anti-correlated with the actual ones. This system performance review consists of a summary section reporting the figures of merit for the forecasting quality, followed by 14 subsections, dedicated to the individual exchange rates tracked by the system. Those contain the usual green-yellow-blue-red color-coded charts of the performance, such as shown below, for each currency pair. Fig. 0: USD/JPY bar chart for March 2012, color-coded to indicate the degree of success in the forecast for close. Yellow and green bars have been predicted successfully as bearish and bullish respectively; blue and read are unsuccessful bearish and bullish predictions, respectively. USD/JPY was one of the most successful pairs for this system in March. For comparison with the previous month, you may want to take a look at the February 2012 performance review.
- Tags:
- frontpage
April 1 2012, 8:02pm | Comments »
-
Danica has been upgraded to v1.3
This upgrade is affecting the way forecasts are generated, in certain situations. In the previous versions, when the predicted close comes out to be above the predicted high, the system would not touch the high, but instead would adjust the close so that the adjusted close is half way between the original one and the high. Similar algorithm would be applied when the predicted close comes out to be below the predicted low. In version 1.3, in this situation, we pull down the high so that it equals the close, or we pull up the low so that it equals the close. The new way is more consistent with my understanding of relatively high prediction quality of high and low as a mundane phenomenon related to continuity of price in the diffusion process, as explained. There is no reason to treat information in the predicted close as secondary priority to that in the extremes, yet that is what took place before this upgrade.
- Tags:
- frontpage
April 1 2012, 5:40pm | Comments »
-
March 2012 Correlation Report
Forex Correlation Analysis Report This monthly forex correlation analysis report is computer-generated. The report follows structure and definitions explained in a separate document, which can be used as a user manual. The report deals with the following exchange rate time series: AUDJPY, AUDUSD, CHFJPY, EURAUD, EURCHF, EURGBP, EURJPY, EURUSD, GBPCHF, GBPJPY, GBPUSD, USDCAD, USDCHF, USDJPY. Table 1. Forex Automaton Index updates for March 2012. CERPI -- Currency Exchange Rate Predictability Index, CERCSI -- Currency Exchange Rate Correlation Strength Index. volatility 1H.1M CERCSI 1H.1M CERPI 1H.1M 0.00109768 0.359564 0.0416486
- Tags:
- frontpage
April 1 2012, 1:22pm | Comments »
-
Does Forex evolve towards efficiency?
During the past 10 years, liquidity in the FX markets is known to have been growing. One might expect that various non-commercial participants, including those with capabilities to research, fund and execute systematic and algorithmic trading strategies, exhaust the alpha-generating potential of this market and drive it towards efficiency. Do spot foreign exchange markets really evolve towards efficiency? I use the ForexAutomaton CERPI 1H.1M inefficiency index (hourly scale, monthly data accumulation period) to look at the trend of the past 10 years (2003-2012), and compare the picture with that of the evolution in the instantaneous ("non-predictive") correlation strength (CERCSI, pronounced "Sir-see") and volatility. 1.1 1.2 1.3 Fig.1. Monthly data from 2003-2012, using the 14 currency exchange rates: AUD/JPY, AUD/USD, CHF/JPY, EUR/AUD, EUR/CHF, EUR/GBP, EUR/JPY, EUR/USD, GBP/CHF, GBP/JPY, GBP/USD, USD/CAD, USD/CHF, USD/JPY. 1.1: evolution of CERPI 1H.1M, 1.2: evolution of CERCSI 1H.1M, 1.3: evolution of hourly logarithmic volatility. Source of data: ForexAutomaton monthly correlation analysis reports. Definitions of CERPI (Currency Exchange Rate Predictability Index) and CERCSI (Currency Exchange Rate Correlation Strength Index) are given in the separate articles. In brief, CERPI measures the strength (by absolute value) of the 1-hour lagged Pearson correlation coefficients among the individual time series (intermarket correlations) as well as inside each time series (autocorrelations). As an estimator of logarithmic volatility, a simple average of the square root of the autocorrelation peak values over the 14 currency pairs is taken. As with CERPI and CERCSI (also logarithmic measures), the time scale of this measurement is hourly and the time interval is month. The time evolution plots of CERPI, CERCSI and volatility are shown in Fig.1. I will start the discussion with volatility as the most familiar and intuitive of the three. As Fig. 1.3 shows, the "old good" days of relatively tame volatility ended in August 2007 with the Fed starting to cut interest rates in response to the sub-prime crisis. Volatility culminated during the selling climax of 2008. After that, the distinct peaks are the Flash Crash of 2010 and the US sovereign credit rating downgrade of 2011. Fig. 1.2 shows that these bouts of panic are characterized not only by the high volatility, but by unusually high degree of correlation among the instruments (CERCSI). Portfolio diversification breaks down as the universe of financial instruments degenerates into risky assets and safe haven ones. This degeneration, even though it may be linked with high volatility via investor psychology and via the mechanics of the over-leveraged markets, does not follow from a rise in volatility mathematically, and represents an independent aspect in the quantitative description of the panic phenomenon. Importantly, Fig 1.2 shows how a rise in CERCSI preceded the rise in volatility and the market crash of 2008. From the CERCSI point of view, the markets never fully recovered after the crash. Right now another divergence between CERCSI and volatility appears to be forming as the present level of CERCSI is in the higher end of its range while the volatility is at its lowest level since Summer 2008 amid investor complacency. Finally, CERPI, the predictability index, Fig. 1.1, is in a long-term declining trend. The long-time peak of volatility (October 2008) is followed by local maxima in CERCSI and CERPI (November 2008). But overall, events of the financial crisis did very little to leave any outstanding imprint on CERPI. In contrast with Fig. 1.2 and 1.3, Fig. 1.1 shows no clear evidence of any tectonic shift triggered by these events. Curiously, the historic minimum of predictability took place in March 2009: apparently, the markets exhausted by panic were the closest to the academic extreme of the efficient market.
- Tags:
- frontpage
March 25 2012, 7:11pm | Comments »
-
Introducing CERCSI, the correlation-based forex correlation strength index
Currency Exchange Rate Correlation Strength Index (CERCSI) is a measure of zero-lag correlation strength with a specified timeframe (time scale) and measurement interval. For quantities we report regularly, measurement interval is the same as period of measurement. The quantities reported in the Forex Correlation Analysis Reports 1H.1M section of the site are measured monthly at the end of a month and include the whole month of data. This article defines the way CERCSI is constructed.
- Tags:
- frontpage
March 24 2012, 1:16pm | Comments »
-
Introducing CERPI, the correlation-based forex inefficiency index
Currency Exchange Rate Predictability Index (CERPI) is a measure of market inefficiency with a specified time frame (time scale) and measurement interval. For quantities we report regularly, measurement interval is the same as period of measurement. For example, quantities reported in the Forex Correlation Analysis Reports 1H.1M section of the site are measured monthly at the end of a month and include the whole month of data. This article defines the way CERPI is constructed.
- Tags:
- frontpage
March 10 2012, 5:39pm | Comments »
-
February 2012 performance review for Danica
February 2012, the second month of the third year of Danica's live operation, will be remembered for the steady decline in the value of Japanese Yen and continued stock market rally. The system continued on auto-pilot without parameter changes. While the forecasts for daily low and high were strongly positively correlated with reality, the predicted changes in the daily close were on average anti-correlated with the actual ones. This system performance review consists of a summary section reporting the figures of merit for the forecasting quality, followed by 14 subsections, dedicated to the individual exchange rates tracked by the system. Those contain the usual green-yellow-blue-red color-coded charts of the performance, such as shown below, for each currency pair. Fig. 0: USD/JPY bar chart for February 2012, color-coded to indicate the degree of success in the forecast for close. Yellow and green bars have been predicted successfully as bearish and bullish respectively; blue and read are unsuccessful bearish and bullish predictions, respectively. The sustained trend is the kind of pattern easy for the system to deal with. For comparison with the previous month, you may want to take a look at the January 2012 performance review.
- Tags:
- frontpage
March 4 2012, 6:37pm | Comments »
-
February 2012 Correlation Report
Forex Correlation Analysis Report This monthly forex correlation analysis report is computer-generated. The report follows structure and definitions explained in a separate document, which can be used as a user manual. The report deals with the following exchange rate time series: AUDJPY, AUDUSD, CHFJPY, EURAUD, EURCHF, EURGBP, EURJPY, EURUSD, GBPCHF, GBPJPY, GBPUSD, USDCAD, USDCHF, USDJPY. Table 1. Forex Automaton Index updates for February 2012. CERPI -- Currency Exchange Rate Predictability Index, CERCSI -- Currency Exchange Rate Correlation Strength Index. volatility 1H.1M CERCSI 1H.1M CERPI 1H.1M 0.00112748 0.410047 0.0455519
- Tags:
- frontpage
March 4 2012, 10:35am | Comments »
-
January 2012 Correlation Report
Forex Correlation Analysis Report This monthly forex correlation analysis report is computer-generated. The report follows structure and definitions explained in a separate document, which can be used as a user manual. The report deals with the following exchange rate time series: AUDJPY, AUDUSD, CHFJPY, EURAUD, EURCHF, EURGBP, EURJPY, EURUSD, GBPCHF, GBPJPY, GBPUSD, USDCAD, USDCHF, USDJPY. Table 1. Forex Automaton Index updates for January 2012. CERPI -- Currency Exchange Rate Predictability Index, CERCSI -- Currency Exchange Rate Correlation Strength Index. volatility 1H.1M CERCSI 1H.1M CERPI 1H.1M 0.00108551 0.429364 0.0484016
- Tags:
- frontpage
February 25 2012, 8:22am | Comments »
-
Introducing monthly correlation reports
Forex Automaton is launching a new type of information product: a monthly correlation analysis report. The reports are computer-generated and follow a pre-defined format. This document explains the purpose and structure of the reports and is intended to serve as a brief user manual to the new information product. It also collects in one place any other information necessary to understand the reports, which otherwise would have to be repeated in every report. The document explains the quantities shown in the plots and relationships between the plots.
- Tags:
- frontpage
February 19 2012, 2:56pm | Comments »
-
January 2012 performance review for Danica
During January 2012, the first month of the third year of Danica's live operation, the system continued on auto-pilot without parameter changes. While the forecasts for daily low and high were strongly positively correlated with reality, the predicted changes in the daily close were on average anti-correlated with the actual ones. This system performance review consists of a summary section reporting the figures of merit for the forecasting quality, followed by 14 subsections, dedicated to the individual exchange rates tracked by the system. Those contain the usual green-yellow-blue-red color-coded charts of the performance, such as shown below, for each currency pair. Fig. 0: EUR/JPY bar chart for January 2012, color-coded to indicate the degree of success in the forecast for close. Yellow and green bars have been predicted successfully as bearish and bullish respectively; blue and read are unsuccessful bearish and bullish predictions, respectively. The success chart looks not too bad, even though the correlation of the predictions with reality turned out to be negative for the month in this currency pair. For comparison with the previous month, you may want to take a look at the December 2011 performance review.
- Tags:
- frontpage
February 4 2012, 3:22pm | Comments »
-
Heidi performance review
Data accumulation for the present incarnation of Heidi began on December 1, 2010 and the first predictions (in back-testing mode) were generated for March 16, 2011. The present system was announced and began live operation on May 23. Now, eight months later, I take a look at the first statistically significant performance figures of merit and make an adjustment to one of the system parameters.
- Tags:
- frontpage
January 21 2012, 7:00pm | Comments »
-
December 2011 performance review for Danica
During December 2011, the last month of the second year of Danica's live operation, the system continued on auto-pilot without parameter changes. While the forecasts for daily low and high were strongly positively correlated with reality, the predicted changes in the daily close were on average anti-correlated with the actual ones. Thus the system has ended the year in which it functioned as a surprisingly stable "anti-system", a curious quantitative phenomenon which no doubt will be useful to research and possibly exploit, but not the intended one. This system performance review consists of a summary section reporting the figures of merit for the forecasting quality, followed by 14 subsections, dedicated to the individual exchange rates tracked by the system. Those contain the usual green-yellow-blue-red color-coded charts of the performance, such as shown below, for each currency pair. Fig. 0: AUD/USD bar chart for December 2011, color-coded to indicate the degree of success in the forecast for close. Yellow and green bars have been predicted successfully as bearish and bullish respectively; blue and read are unsuccessful bearish and bullish predictions, respectively. AUD/USD was the currency pair of the system's worst performance for the month of December. The areas of alternating red and blue bars is when the system was getting out of sync with the reality it tries to predict. For comparison with the previous month, you may want to take a look at the October 2011 performance review.
- Tags:
- frontpage
January 7 2012, 5:18pm | Comments »
-
November 2011 performance review for Danica
During November 2011, the eleventh month of the second year of Danica's live operation, the system continued on auto-pilot without parameter changes. Many FX markets moved in recognizable trends this month, and the market average of the correlation coefficient between Danica's forecasts and the reality for daily close came out somewhat positive, while the forecasts for daily low and high were strongly positively correlated with reality. This system performance review consists of a summary section reporting the figures of merit for the forecasting quality, followed by 14 subsections, dedicated to the individual exchange rates tracked by the system. Those contain the usual green-yellow-blue-red color-coded charts of the performance, such as the one shown below, for each currency pair. Fig. 0: GBP/JPY bar chart for November 2011, color-coded to indicate the degree of success in the forecast for close. Yellow and green bars have been predicted successfully as bearish and bullish respectively; blue and read are unsuccessful bearish and bullish predictions, respectively. The system persistently stayed with the downward trend throughout much of the month despite a number of disappointing days, then turned around to catch the trend change almost perfectly, given the time scale of its operation. For comparison with the previous month, you may want to take a look at the October 2011 performance review.
- Tags:
- frontpage
December 4 2011, 3:56pm | Comments »
-
October 2011 performance review for Danica
October 2011, the tenth month of the second year of Danica's live operation, saw generally high risk appetites and ended with the long-awaited JPY intervention. The system continued on auto-pilot without parameter changes. The market average of the correlation coefficient between its forecasts and the reality for daily close came out strongly negative, while the forecasts for daily low and high were positively correlated with reality, in line with the established pattern of this system's live operation. This system performance review consists of a summary section reporting the figures of merit for the forecasting quality, followed by 14 subsections, dedicated to the individual exchange rates tracked by the system. Those contain the usual green-yellow-blue-red color-coded charts of the performance, such as shown below, for each currency pair. Fig. 0: USD/JPY bar chart for October 2011, color-coded to indicate the degree of success in the forecast for close. Yellow and green bars have been predicted successfully as bearish and bullish respectively; blue and read are unsuccessful bearish and bullish predictions, respectively. The BOJ intervention, which went against the predicted trend, created the long blue bar. For comparison with the previous month, you may want to take a look at the September 2011 performance review.
- Tags:
- frontpage
November 4 2011, 1:37pm | Comments »
-
September 2011 performance review for Danica
September 2011, the ninth month of the second year of Danica's live operation, will be remembered for the CHF intervention and the announcement of the so-called Operation Twist in the US. The system continued on auto-pilot without parameter changes. The market average of the correlation coefficient between its forecasts and the reality for daily close came out slightly positive, despite the strong negative contribution from USD/CHF, one of the pairs that suffered from the Swiss intervention. The system kept doing a good job making forecasts positively correlated with reality for the daily extremes (in all cases, logarithmic returns are analysed). This system performance review consists of a summary section reporting the figures of merit for the forecasting quality, followed by 14 subsections, dedicated to the individual exchange rates tracked by the system. Those contain the usual green-yellow-blue-red color-coded charts of the performance, such as shown below, for each currency pair. Fig. 0: EUR/JPY bar chart for September 2011, color-coded to indicate the degree of success in the forecast for close. Yellow and green bars have been predicted successfully as bearish and bullish respectively; blue and read are unsuccessful bearish and bullish predictions, respectively. Several successful alternations of green and yellow indicating successful switches in the direction of the trade, not prompted by losses, are seen in the chart. For comparison with the previous month, you may want to take a look at the August 2011 performance review.
- Tags:
- frontpage
October 8 2011, 4:27pm | Comments »
-
August 2011 performance review for Danica
August 2011 was the eighth month of the second year of Danica's live operation. The system continued on auto-pilot without parameter changes. The market average of the correlation coefficient between its forecasts and the reality for daily close came out negative, but the result is strongly dominated by a single market, EUR/USD, which was range-bound but at the same time volatile. The system kept doing a good job making forecasts positively correlated with reality for the daily extremes (in all cases, logarithmic returns are analysed). The best performing pair was EUR/AUD. This system performance review consists of a summary section reporting the figures of merit for the forecasting quality, followed by 14 subsections, dedicated to the individual exchange rates tracked by the system. Those contain the usual green-yellow-blue-red color-coded charts of the performance, such as shown below, for each currency pair. Fig. 0: USD/JPY bar chart for August 2011, color-coded to indicate the degree of success in the forecast for close. Yellow and green bars have been predicted successfully as bearish and bullish respectively; blue and read are unsuccessful bearish and bullish predictions, respectively. Several successful alternations of green and yellow indicating successful switches in the direction of the trade, are seen in the chart. For comparison with the previous month, you may want to take a look at the July 2011 performance review.
- Tags:
- frontpage
September 3 2011, 1:14pm | Comments »