Добре дошли в Свободен Български ФОРЕКС форум.
Резултати от 1 до 7 от общо 7
  1. #1
    Наблюдател
    Регистриран
    12.12.2019
    Мнения
    14

    270 години ТА, променят ли се наистина пазарите? Кървфитинг.

    В тази тема ми се иска да говорим за общоприетото схващане, че пазарите се променят, върху какви периоди трябва да се търсят и оптимизират системи и как да избягваме кървфитинга.

    Ще започна с Историята на Munehisa Homma и създаването на съвременния ТА, като в последствие ще пусна изследвания които открих.

    he Most Successful Price Action Trader in History: Munehisa Homma

    Today’s article is about one incredible man who was known as the “God” of the markets in his day;
    Japanese rice trader Munehisa Homma. He lived from 1724 to 1803 and even if half of the legends about him are true, he was by far one of the most amazing traders in history and we can learn a lot from the stories that surround him.

    Homma is rumored to have made the equivalent of $10 billion in today’s dollars trading.

    You should probably listen to a “Samurai trader”
    Homma is rumored to have made the equivalent of $10 billion in today’s dollars trading in the Japanese rice markets. In fact, he was such a skilled trader that he served as an important financial advisor to the Japanese government at the time and was later raised to the rank of honorary Samurai. I don’t know about you, but I think it’s pretty safe to say we can learn something from a guy who was such a great trader that he become a Samurai because of it, to me that is totally cool in what is probably a semi-nerdy kind of way. Rumor has it that he once had 100 profitable trades in a row….granted there’s a bit of an advantage when you are basically the “inventor” of technical analysis and no one else really knows about it yet…but clearly Homma was a force to be reckoned with in the markets and his legend lives on today.

    Homma began recording price movements in the rice market on paper made out of rice plants. He laboriously drew price patterns on his rice parchment paper every day, recording the open, high, low and close of each day. Homma began seeing patterns and repetitive signals in the price bars he was drawing and soon started to give them names, including some of the popular Japanese candlestick patterns that you are probably already familiar with like Spinning tops, Stars, Doji’s, Hanging Man and others, each pattern clearly conveyed a specific meaning and Homma began using these patterns to predict the future direction of rice prices. The discovery of the price action patterns left behind by the movement of rice prices gave Homma a huge advantage over other traders in his day, and combined with his passion and skill for trading, this advantage is what allowed him to become one of the most successful traders ever, if not thee most successful trader ever.

    To any of you reading this who may still be “on the fence” about the relevancy and effectiveness of price action trading, consider the fact that it was used centuries ago by Homma and others and it’s still effective in today’s markets. I cannot think of any other trading method, system, indicator or robot that has been effective for that long and stood the test of time as pure candlestick price action trading has. Whether or not Homma knew the term “price action” in his time is irrelevant, he was clearly trading from the pure price movement of the market and he was the first person who realized the advantages of focusing one’s attention on a market’s price movement to predict its direction.

    Homma realized price action reflects market psychology, and used it to his advantage
    hommacandleIn Homma’s book “The Fountain of Gold – The Three Monkey Record of Money”, which he wrote in 1755, he says that the psychological aspect of the market is critical to trading success and that traders’ emotions have a significant influence on rice prices. He notes that this can be used to position oneself against the market when all are bearish, because at that time there is cause for prices to rise (and vice versa).

    In other words, Homma was the first trader to realize that by tracking the price action in a market he could actually “see” the psychological behavior of other market participants, and make use of it. As it relates to the price action strategies that I teach, this could mean for example that after a large run up or down in a market a long-tailed pin bar signal can give rise to a large move in the opposite direction. I imagine that Homma was the first person to trade a pin bar signal and I’m sure when he realized the power of the signal he got goose bumps all over his body.

    Homma also probably took advantage of false break trading strategies by the sounds of what he wrote in his book. I’m sure that he quickly identified patterns similar to what I teach as the fakey setup and saw that they sometimes form at major market turning points just as the last market participants have finally committed to a direction. The tendency of people to jump into a market when it “feels” safe has probably been around ever since Homma’s trading days back in the 1700’s, and it has not changed over the centuries. Homma probably realized this as it’s very evident by studying the price action of a market and using a big of logic and commonsense. In essence, Homma was the first true “contrarian” trader and this is why he is one of my heroes to this day. Using the price action of the market and logical thinking, we can often find high-probability entries into the market while most other market participants are stuck in a cycle of trading mainly with their emotions and from what makes them feel good.

    Homma would definitely agree that what “feels” like the “surest” trade is often the wrong one, and once he could start to see the emotion of market participants via candlestick price patterns, this likely became very obvious to him.
    The trend has been your friend or over 250 years, so stop fighting it!
    Homma described the rotation of Yang (bull market), and Yin (bear market) and claims that within each type of market is an instance of the other type.
    I can only imagine the amazement that Homma must have felt when he started to see price trends emerge over his years of drawing price patterns on his rice parchment paper. It must have instantly set off a euphoric feeling in him because he likely realized very quickly that trading with the trend would be the easiest way to make money in the rice markets.

    To this day, trading with the trend is still the easiest way to trade. Traders try to fight it by continuously trying to pick tops and bottoms, but trend-trading has long been the easiest way to make a lot of money in the markets. Simply put, there’s a reason for strong trends, so it’s illogical to fight the trend. Homma was the first trader to be able to identify high-probability entry points in a trending market via simple price action patterns. This method has worked for literally over 250 years, and why so many traders still try to fight it and over-complicate it is beyond me.

    If Homma was alive today and he saw all the messy indicators and trading robots people put on their charts, he would probably get a confused look on his face and wonder why anyone would behave so illogically and ignorantly when everything they need to find high-probability entries into the market has been right in front of their face the whole time.

    Mirrors don’t lie

    samuraiHomma wrote several books in his time, which are apparently out of print now, but the candlestick patterns he described in his books became known as the “Sakata Rules”. These Sakata Rules became the basis of modern candlestick charting and thus most of what Homma wrote about is still relevant today. The fact that the first person to trade from a price chart and arguably the most successful trader of all time was a price action trader, is really not surprising to me. What Homma discovered, and what many of us now know, is that the price movement on a “naked” price chart reflects everything about a market.

    Everything you need to know to find high-probability entry signals into virtually any market is available on a natural price chart. If you want to see your reflection in the mirror, you just go to a mirror and look at yourself. You do not put a wig on or throw a paper bag over your head. Similarly, if you want to see what a market is doing, you simply need to look at its price chart. You do not need to cover up the most accurate reflection of a market with indicators and other nonsense. Munehisa Homma discovered this simple truth about markets over 250 years ago, and to this day many other traders, including myself, are still using pure price action to trade the markets, because there is simply no better way to trade. - by Nial Fuller

  2. #2
    Наблюдател
    Регистриран
    12.12.2019
    Мнения
    32
    Аз смятам че всеки експерт си има собствени особености, има си собствени изисквания за бактест както има и собствена продължителност на живота. Няма как един експерт който се води от суапа , един който работи на малки пипсове и един който работи на големи трендове да имат еднакви изисквания към тестове .
    Ако тестваш суап експерт на данни където си бил с положителен суап а сега е отрицателен ще получиш че преди е губил а сега печелиш и това ще те обърка.
    Не можеш да тестваш експерт на малки пипсове на стари данни където спреда е бил 2-3 пъти по голям и са много по рошави.При подобен тест при сегашния спред ще получиш едно огромно изкуствено ПМО което ще те обърка.
    Не можеш да тестваш трендови експерт на малко данни тъй като ще имаш малко сделки и незначителна извадка.
    Не разбирам защо трябва да слагаме всички експерти под един общ знаменател.Те са толкова различни ...
    По отношения на пазара- аз не мога да докажа че се променя.Може да има и някакви аспекти от него да не се променят.Но аз лично съм имал много експерти , които са работили с години , и без да съм променял кода им са спирали да работят. След като те не са променяни какво остава като възможност...
    Лично за мен няма вечни експерти, всеки един си има живот и лично мен това че някой е много стар хич не ме радва.Напротив за мен това означава че е към края си.Не че не бих го използвал , но бих бил много по внимателен с него.

  3. #3
    Моето мнение за пазарите е подобно. Че се променят, променят се, но не самоте пазари, а вградените в тях зависимости. Такива зависимости вероятно има хиляди, по-слаби или по-силни, като таймфрейма на тези зависимости е различен - от такива на секундно и минутно ниво, до такива на седмино, месечно и дори годишно ниво. Това обаче не променя факта, че ПАЗАРЪТ Е СЛУЧАЕН. Той всъщност представлява една глобална сума от всички зависимости, но тази сума изглежда случайна за хората, които не ги знаят какви са тези зависимости като посока и сила.

    Вторият момент - има ли вечни зависимости или не?

    Тука аз си мисля, че вечни зависимости няма. По-правилното разсъждение е, че вечни зависимости може и да има, но те ще са такива само до момента, до който някой не ги открие. Когато ги открие и започне да ги експлоатира, самият той със действията си ще доведе до отслабването на тези зависимости или дори до тяхното пълно изчезване. Тогава той ще спре да ги експлоатира, но това пък ще даде шанс на същите тези зависимости отново да се появят на пазара. Какви изводи можем да си направим от тези разсъждения:

    1. Вероятно има вечни зависимости, които са вечни поради непроменящата се природа на пазарните субекти, търгуващи на тези пазари.
    2. Експлоатирането на тези зависимости обаче ги отслабва или дори временно ги премахва.
    3. С премахването на зависимостите се премахва и експлоатацията им, което дава шанс на зависимостите да се възстановят.
    4. Точки 1, 2 и 3 всъщност са обяснение защо има ЦИКЛИЧНОСТ в появата и изчезването на една или друга зависимост. Ами защото тя изпада в един вечен цикъл от типа Поява => Детектиране => Експлоатация => Отслабване поради експлоатацията => Спиране на Експлоатацията => Ново засилване на зависимоста => Начало на следващия цикъл Детектиране, Експлоатация и т.н.

    Ако приемем, че съм прав в разсъжденията си, в наш интерес е да създадем стратегии, които да са търпеливи в периода си на стагнация, и да се опитват да го преживеят с минимални загуби в очакване загубилата се зависимост да възкръсне отново.

  4. #4
    Наблюдател
    Регистриран
    12.12.2019
    Мнения
    14
    Ето първото изследване което намерих, чрез ровене в един уеб архиватор, тъй като автора я беше махнал. Дали прозто поради бъг или е сметнал че в нея има нещо ценно не знам.

    Не оспорвам и нещата които казвате, може да има и повече от една истини, особено ако говорим за различни типове стратегии като кери трейд и такива с малко ПМО, както казва шаката, но ако говорим за експлоатиране на зависимости в ценовото поведение все пак клоня към това което е показал експеримента от статията.


    I have written in the past about the use of old market data (1985-2000) in the back-testing and design of Forex systems (for example here and here). There is a significant number of traders who believe that you should not use old data because it is “out-dated” and does not represent the “current market” and that changes in overall market structure during this entire time have caused extremely large changes in the market that make any conclusions drawn from experiments including this data completely irrelevant. Traders who hold this view commonly point to the raise of computer based trading and the rise of the internet as two reasons why both market structure and information flow are different and hence past market data should not hold any relevance in today’s market. The real question is, is this actually true? On today’s post we are going to take an evidence based approach to the testing of this hypothesis. We will look at the search for trading systems in old data (1986-2000) and we will see how much predictive value they actually hold across new market data (2000-2015). You can download the data that we will be using through the article

    Щракнете върху изображението за по-голям размер

Име:	1.jpg
Прегледи:      40
Размер:	54.6 KB
ID:	10277
    To see if old market data does hold any predictive value across the newer market data we must use statistical hypothesis testing. We establish the null hypothesis that past performance in the 1986-2000 set is not indicative of performance in the 2000-2015 set and we set to negate this null hypothesis. To do this we first establish the probability that a trading system with a high linearity (R²>0.95) and low max drawdown length (<500 days) generated across 15 years of random market data is profitable through the next 15 years and we see if the percentage of profitable systems on the average random data set (used more than 100 random data sets generated using bootstrapping with replacement) over the percentage of systems found on the real data set is less than 1%, if this is the case we can then negate the null hypothesis that 1985-2000 past performance is not related with 2000-2015 performance with a 99% confidence. For the generation process in OpenKantu I used the options showed on the image above.

    This mining process carried out on 100 random data sets generated using bootstrapping with replacement from each real data set generated on average less than 1% systems that were profitable within the second 15 year period data. The value is extremely low because the probability to be profitable across such a long time span becomes very low for a random walk process, which is essentially what happens if a system has no edge. This means that if we find that 20% of systems are profitable in the 2000-2015 period we would already be able to say that this is well above what is expected simply from random chance and that the 1988-2000 data actually holds information that is relevant for the prediction of profitability in the 2000-2015 period. We could say that old market data was not irrelevant.When we analyze the results from doing the above exercise on the EUR/USD (DEM/USD before 2000), USD/JPY and GBP/USD daily timeframes (3 pip constant spreads)(you can reproduce my analysis using the R script above and the data linked before) you can see that the probability to generate a strategy that was profitable in the 2000-2015 period is very high, as a matter of fact the probabilities are 88.5% (EUR/USD), 90.5% (USD/JPY) and 80.16% (GBP/USD) much higher than the expected probabilities from a simple luck of the draw. In fact the large majority of systems were able to make money in the 2000-2015 period which would be extremely improbable if the information present in the 1988-2000 period was simply irrelevant. There was an obvious deterioration in system quality under such a long out of sample period as systems only performed equally or better 20.7% (EUR/USD), 0.92% (USD/JPY) and 1.66% (GBP/USD) of the time but the mere fact that they were able to make money overall over this period is already fascinating.
    Щракнете върху изображението за по-голям размер

Име:	2.jpg
Прегледи:      39
Размер:	77.5 KB
ID:	10278

    But what if losers were simply much worse than winners and it was all made up of small winners and huge losers in the 2000-2015 period? The analysis of the distribution of 2000-2015 results shows that this is actually not the case. The distributions show that losers are in general much smaller than winners on average with the distributions skewed heavily towards a larger profit/trade. This is completely unexpected if the 1988-2000 data was irrelevant because when no real inefficiencies are present in the data used for mining the future profit distributions are heavily skewed towards the losing side, as you would expect for a random walk process with a negative drift caused by trading costs. Repeating the above analysis for the EUR/USD 1H, 30M and 15M results yield extremely similar results so as a matter of fact this does not seem to be a timeframe dependent phenomena.

    Despite what people like to say about old data not being useful and the market having changed, the reality is that old data, even data from 1986, holds important information that can lead to the creation of systems that survive newer and unknown market conditions. Why this is the case is certainly open to speculation but the truth is that old market data -despite the advent of the internet and computational power – transmits some general market characteristics that may still be useful today for the creation of profitable trading systems. If the 1988-2000 data was relevant to create profitable systems from 2000-2015 then it is reasonable to assume that it will also hold some relationship with the future 2015-2030 data. Using all available market information (1986-2015) for the creation of trading systems ensures that we reduce curve-fitting and only capture the most general of market inefficiencies.In the end systems created using vast amounts of data (almost 30 years) may hold the greatest chances of achieving profitable results going forward as they contain the least amount of curve-fitting and the most information to tackle new market conditions.



  5. #5
    Наблюдател
    Регистриран
    12.12.2019
    Мнения
    14
    Втория материал, който е подобен и се набляга на кървфитинга

    Curve Fitting and Data Usage: Evidence on why using all available historical data makes sense

    There are many different opinions on how system construction should be carried out. Suggestions go from using only recent data and then regenerating or reoptimizing systems after a given period of time to performing system creation using all available data. On today’s post I am going to show evidence on why the later case is the one that makes the most sense and why failure probabilities and other problems are expected to be much higher with shorter amounts of data. I will also talk about why the idea of fixed regeneration or reoptimization does not make a lot of sense and why all this inevitably leads us to system creation methodologies where no historical out of sample tests are either necessary or even advisable.



    The idea of using limited amounts of data and then repeating system creation procedures every given fixed amount of time seems to make a lot of intuitive sense. Methodologies that follow these lines make the assumption that recent historical data is the most relevant and that in order to avoid performance deterioration it is critical to maintain your trading system aligned to whatever market conditions have happened recently. The evidence that supports this assumption is scarce. I have showed in the past strong evidence that really old market conditions are relevant to predicting more recent market movements, a fact that completely obliterates the notion that past data is irrelevant. However people arguing for the “recent optimization” argument might expose that it is not that the past is irrelevant but that recent conditions can simply more accurately predict the immediate future.
    To test this we can test the probability of trading success across randomly chosen periods of different lengths if strategies are generated for one period and then tested on the one just following them. For this I tested a simple price action based generation methodology on the 1H charts such that the only prerequisites to be selected was for the system to be profitable during the design period, have more than 10 trades and to have a correlation coefficient (R²) higher than 0.90. The generation procedure was continued until at least 5000 systems had been generated across randomly chosen periods for each desired length. The generation and testing periods are exactly the same length, so if generation was done for 60 days then the testing period was the immediately following 60 day period to the initial generation time span. The tests used data from 1986 to 2016.



    If we do this we obtain results as those shown on the two graphs above, which are equal across several different Forex symbols (the above are results on two different symbols). Trends remain the same with variations in the generation methodology – relative evolution of the success probability is exactly the same as a function of period length – although the absolute success probability values do change depending on the actual generation method (system building space, filters used, etc). These plots show us how the probability of a profitable outcome increases drastically as a function of the generation period length, such that success across short periods is very low while the number of expected profitable systems grows bigger and bigger as the sample size increases. This means that you have a historically better expectation to be profitable across a period equal in length to your design period if you use more data. Your probability to fail and over-fit is therefore strongly related with how much data you use, if you use more data you are much less likely to face this problem. This makes sense as more data means that your system can face more market conditions. For the above methodology extrapolating to a 30 year in sample would give us a success probability above 80% while for others it can be above 90%.
    Given the above it then makes sense to use just as much data as possible for the design of trading strategies. This means that leaving any data out for any historical in sample Vs out of sample tests is a futile exercise because you’re removing market conditions that could benefit the design process. Such out of sample processes also fail to bring any real benefit since they end up being a part of a more complex curve fitting exercise since their results are generally used to redesign the trading strategies . Using as much data as possible provides the greatest probability that your systems will perform positively under real out of sample conditions since they will be prepared to face the largest amount of variability that can be inferred from the historical data.


    Establishing a fixed period for regeneration is also unwarranted since there is no fundamental reason to re-engineering a strategy that is working as expected. Since the way in which market conditions change has no immutable pattern we should keep strategies trading for whatever period they perform in line with their historical distribution of returns. If the market happens to behave in a manner that a system can handle very well for 2 years then there is no reason to impose a regeneration every 2 months. Doing adequate monitoring of trading strategies to remove them from trading, especially without such removal necessarily implying significant losses is a way to do this. In this manner systems are removed when they stop working but they can take advantage of long profitable periods if they choose to happen.

  6. #6
    Наблюдател
    Регистриран
    12.12.2019
    Мнения
    14
    Ето още нещо на което попаднах, е спестя подробностите и ще постна само изводите

    The most important observation – which matches previous analysis made by myself and others – is that the top performers in the out-of-sample are not the best performers during the immediately previous in-sample market conditions. As a matter of fact selecting the top performers in terms of the last few in-sample years gives you a practically all-losing system sets. This is one of the big reasons why creating systems using small amounts of recent data is a recipe for disaster, it is almost warranted that the market will become efficient to the immediately preceding conditions, since these are the ones that possibly get the most exploited both by humans and machines. Humans will have a fresher memory of the recent past while trading machines are often created to give more weight to recent market conditions. All in all recent conditions are the most analysed and therefore inefficiencies present largely or solely within them get eliminated fairly quickly.

  7. #7
    Ако искаш да се развие някаква дискусия, преразказвай набързо за какво се говори в тези английски текстове и какво е твоето мнение по въпроса. Иначе ние няма как да знаем какво в тези дълги текстове ти е направило впечатление.

 

 

Информация за темата

Потребители разглеждащи тази тема

В момента има 1 потребител (и), разглеждащ (и) тази тема. (0 потребител (и) и 1 гост (и))

Разрешения за писане

  • Вие не може да да публикувате нови теми
  • Вие не може да публикувате мнения
  • Вие не може да публикувате прикачени файлове
  • Вие не може да редактирате вашите мнения
  •