Article Library

Trading on news has been, and always will be, one of the essential strategies for speculators. In the age of the stockbroker, the execution of news trading was probably much simpler, a broker with a stock tip—if it was a rumor or news—made a phone call to his client and made the sale of securities to tip off profitable gains before it was public knowledge.
Now, trading on news can be much more sophisticated. With high-frequency traders and a race for ever faster price and news dissemination, news trading is more a technological endeavor than ever before. Professional traders operate on very expensive trading platforms that work incessantly just to disseminate quotes and news a split-second faster than the competition. For instance, Bloomberg terminals have had a clear and present advantage to any practitioner, making it a leading technology and a must-have for a long time. However, with the advent of social media, where news stories don’t wait a day to go to print, a new avenue for news trading has opened up.
The speed and transparency of which we can receive news is like lightning compared to the old news trading model. What this means, in essence, is that certain news aggregate…
Read article
Translate to English Show original
hrustiashka avatar


Efegen avatar
Efegen 19 July

Another good article :)

samymahrous avatar

very good

Armands avatar
Armands 23 July

Well written!

pshan avatar
pshan 23 July

Thank you!

orto leave comments
Machine learning can help us optimize automatic trading strategies. By studying the huge amount of past information, we can identify patterns that help us predict the evolution of the market to a sufficient extent. This is of course what some traders have been doing for a long time but the automatization of the process allows us to find much better strategies and much faster than it would take a human. Here we propose a speculative strategy that has been successfully tested and demonstrates the possibilities brought by machine-learning in forex.
Automatically finding a winning speculative strategy on eurusd

EUR/USD is a very lucrative pair for a speculative strategy built from machine-Learning algorithms, although our method is able to find winning strategies on other instruments and some that work across several instruments, the strategies developed for EUR/USD give the best returns. This is how the strategies are built.
We cannot feed the actual price to the algorithm because we want it to recognize patterns independently of their height on a chart. We therefore feed it price movements, from high to high and low to low (better than open to close). This is a simple kind of indica…
Read article
Translate to English Show original
Likerty avatar
Likerty 8 Jan.

Interesting article, really. Just a bit of a problem lies in the price feed of the past - the exact levels that are in play - rarely get reaction "to the pip" - more often they get overshoot as the real accumulation is happening just beyond the level (10/40 pips), not exactly at it. So, by studying past price is difficult to find things.. I would rather shoose to look for levels in advance and by watching price reaction to the spot in real time, I can say - is it a correct level or not..

Skif avatar
Skif 11 Jan.

automatic trading - its benefits are well documented!!!

olga avatar
olga 11 Jan.

cheers, I should have said something about the benefits yeah. for me, the major advantage is that these machines don't have emotions like us, but humans manage and test them and they still have emotions.

Airmike avatar
Airmike 12 Jan.

nice article olga. looking forward to next article about machine learning

nick21 avatar
nick21 31 Jan.

Well done Olga

orto leave comments
Modern techniques like artificial neural networks (ANN) are best used for high frequency trading for several reasons. First, they mimic human intelligence but they mostly don’t reach a human’s level of intelligence, therefore, there is no point in using those techniques on a time scale at which a human could easily be working. Their advantage comes from speed of operation and constant activity. Second, we need a lot of data to train neural networks efficiently and this amount of data will only be found in high frequency trading. Forex has all in all quite few instruments with limited relevant past data on the daily or weekly time-scale. Furthermore, High frequency trading is a type of scalping strategy where we identify noise around the true value of the instrument. This is different from long-term trading that attempts to follow meaningful movements of the instrument according to fundamental analysis.Artificial Neural networks A good time-scale to work on is the minute time-scale. This time-scale is full of noise which will be captured by the algorithm in order to sell at a local high and buy at a local low. This can be proven using a simple neural network trained to predict the f…
Read article
Translate to English Show original
Efegen avatar
Efegen 16 Apr.

Just a thought. If this system works why don't you use it in larger timeframes. So the costs will be more minimal and deviation will be less?

Victor avatar
Victor 18 Apr.

good one.. nicely written

SpecialFX avatar
SpecialFX 30 Apr.

Another very intriguing and interesting article! :) Regarding your comment about Holy Grail, no need to look for it, because it doesn't exist... well, it does, but that will be for another time... ;)

nippur72 avatar
nippur72 21 Nov.

The reason why you are able to predict "high to high" and not "close to close" IMHO is very simple: when you predict "high to high" you are not forecasting the future, but you are forecasting (partially) the past, since the High(-10 to 0) is a point back in time. It's a common pitfall that I've also experienced myself when experimenting with neural networks. As a rule of thumb, when you see hit rates easily going above 65% there is chance you are doing something wrong, e.g. forecasting the preset or the past.

olga avatar
olga 24 Nov.

You are totally right and strangely enough I had realized this before and I made the mistake again. I also found similar pitfalls when training and testing instances aren't totally separated including the period you gather information on and the period you try to predict when you use cross-validation. It’s very easy to get excited about good results and in this article, it totally happened to me. In conclusion, kudos for pointing out the flaw that destroys any interest lying in this article and I believe more and more that high-frequency trading has no solution.

orto leave comments
Introduction When designing a strategy, a beginner will pick a few parameters at random, either directly from the price or from indicators, and will attempt to predict future movements based on those parameters. When he’s convinced those parameters don’t hold any information, he’ll choose some slightly different parameters and so forth. This is a sensible way to explore forex instruments however, there are so many parameters to look at and try out that you will most likely die of old age or at least go bankrupt before you find a winning strategy. That’s why I automated the process in an algorithm that attempts to find the optimal parameters for predicting EURUSD movements.A randomizable set of parameters We have to define limits for a space of parameters we want to explore. To do this I first build a list of the lowest price daily, in two days, in three days… until 15 days. The high price could also have been used.Once we have this list, a parameter is defined by three numbers we’re going to call i, j and k. The value for a single parameter for day n is given by taking, in column i, the difference in percent between price n – j and n – k. Thus, our parameters are movements from hi…
Read article
Translate to English Show original
OneGoodTrade avatar

It looks like some big hedge fund's algorithmic trading department is waiting for you :)

Likerty avatar
Likerty 8 Feb.

Pre-programmed trading was always a mystery for me:) Good luck in the contest!

doctortyby avatar
doctortyby 15 Feb.

I agree with One Good Trade... a prop shop is the environement that you need to devellop ;)

orto leave comments
Introduction In an earlier article I compared the length of trends on a daily time-scale between EURUSD and a randomized instrument only to find that the differences were marginal. The conclusion was that on a whole, trends on a daily time-scale don’t last rather than reverse. Using statistics ans data-mining, I look at intra-day trends and show that on certain hours of the day, prices tend to travel in trends while on others they tend to travel within a range. Range throughout the day The range per hour is the difference between the high and the low of the hourly period.This graph shows the average range for each hour of the day for EURUSD over 2.5 years of data. three peaks of activity arise, one at around midnight, one at around 08h00 and one around 14h00. These correspond to the peaks from the Tokyo, London and New York markets respectively. There is thus a verry strong correlation between volume and range.Intra-day trends cannot be analyzed with the classical definition that says a bullish trend ends when the price falls below the last bottom and a bearish trend ends when the price rises above the previous peak. It’s wrong to use this definition because the average range chang…
Read article
Translate to English Show original
LSD avatar
LSD 4 Feb.

Are all days really the same? Of course not.
I think that too much data aggregates tend not to give effective information.
From Friday's closing to Sunday's opening of the market often there is a gap regardless of the volume.
In addition, the daylight saving time changes throughout the year and so is the time of the swap (when you have high spreads).
The first Thursday of the month, every day of the week (Monday, Tuesday, etc.) tends to be different from others etc.
However, every effort should be appreciated for the good purpose of sharing knowledge. I thank you for the article.

olga avatar
olga 5 Feb.

you're right, the title is misleading because the days are in fact only truly similar in terms of volume and therefore range. I should probably have included standard deviations to convince more. and I agree that certain days, about 1 on 10, are very different from the rest, as to what day of the week or month, this is new insight to me and I hadn't thought of looking there.

SpecialFX avatar
SpecialFX 22 Feb.

Am I right in saying that those peaks at about 21:00-22:00 (Average Range Volume, for example) are due to the roll-over at 17:00NY time, when the spreads temporarily widen? Interesting article :)

olga avatar
olga 22 Feb.

that's quite possible but enligthen me, are rollovers calculated at a specific time? Then do you mean that some people quickly change their position in order to take advantage of the difference in interest rates?

SpecialFX avatar
SpecialFX 26 Feb.

Yes, rollovers are calculated market-wide at 17:00 NY time, or 22:00GMT currently. Some traders might do that on purpose to take advantage of the interest rates, but what happens during the rollover is the simultaneous closing of the existing position at the daily close rate and re-entering at the new opening rate the next trading day (which starts at 17:00NY), this is done automatically by the brokers

orto leave comments
IntroductionMachine learning is a field of artificial intelligence where computer programs learn instead of blindly following a script. With enough training data you can teach those algorithms to drive a car, pilot a helicopter or build the best search engine in the world. Here are the results I obtained with my initial approach at applying machine learning to forex trading.Thechnical ConsiderationsA variety of algorithms are put in place to try and predict the evolution of an instrument with data from only 8 daily bars into the past. For each day, four values are recorded, the first three record information on the movement from the previous day’s close to the day’s high, low and close, in percent while the fourth records the volume for the day. This makes for 32 independent variables total. The data is obtained from three instruments in the dukascopy database, EURUSD, AUDJPY and GBPCHF daily Ask bars from the 1st January 2008 to the 31th December 2011, with weekends blended in the following Monday. For each of the algorithms tested, the first two years were used to train the models while 2012 was used to test them. The open java library for machine learning algorithms used comes f…
Read article
Translate to English Show original
PipSpinner avatar
PipSpinner 13 Dec.

I don't have the reputation to like this yet, but thanks for the great article! Have you tried applying any ML to depth of market and volume data?

olga avatar
olga 16 Dec.

I have applied it to volume data and throughout the day for example it is quite possible to predict the volume based on the time of day. for example it's easy to predict there will be a bottom at midnight and that the overall volume will resemble the previous day but meaningfull differences are hard to predict. I suppose it would be similar for market depth but I have never looked into such data.

Aircooled avatar
Aircooled 22 Jan.

Good article. Unfortunately audience here is not "ready" for such stuff.

campione avatar
campione 13 Sep.

Nice article :)  I assume you used period of 2008~2011 static data as input, I need to do something like this with live data, to analysis the live data and give me live decisions.  Could you implement something like this? I'm happy to help you to do this together if you are up to? ;) best of luck for you in trading

orto leave comments