I couldn't find the CRB creation logic clearly described anywhere, the general description that I found seems susceptible to sync problems. Doesn't matter anyway, they don't interest me. Directional change "bars" converge in exactly 1 bar.

Machine Learning with algoTraderJo

Hmm, are you sure about that? The CRB construction rules that I found do not mention any kind of pivot/extreme point. They only care about range. So for example, if you start computing them in the middle of a constant up trend, when the trend ...

Machine Learning with algoTraderJo

There is something in the same idea as renko charts, but much better (and immune to this problem). It's called directional change. url I'm using this as input into my convolutional networks.

Machine Learning with algoTraderJo

I traded relatively rarely (around once per week), so I don't have enough statistics. And it wasn't on EUR/USD, where liquidity is bigger, it was a different pair (still a major). But the broker was honest, I had L2 access (depth of market), and you ...

At what lot size/account size do you have scale issues?

Above 10 lots I would start getting slipped. So when I would enter/exit the market, I would do it in 10 lot chunks (1 mil market orders). Sometimes I would need to wait 1-2 sec for the liquidity to replenish. Putting on a 50 lot position would take ...

At what lot size/account size do you have scale issues?

A lot of HFT firms work with minute-by-minute distributions. Meaning that they compute what is the typical distribution (for whatever you measure, like return or volume) at 12:01, what is the typical distribution at 12:02, and so on. This is such a ...

FXEZ's Quantitative Research In R

The best volatility measure would be using the IV's (implied volatilities) from the option market. The advantage is that they price in FUTURE expected events - ie: the IV's got large before the Brexit referendum, which is not something that your ...

FXEZ's Quantitative Research In R

So what are you trying to say? That's the exact definition of what a standard deviation is. The yellow line is 2 std, so by definition ~96% of the samples are inside it.

FXEZ's Quantitative Research In R

Yeah, one would typically use a regularization technique like dropout or batch normalization to avoid that.

FXEZ's Quantitative Research In R

Indeed, Forex as a whole doesn't. But individual Forex brokers do publish such information. When I said loss function I didn't mean stop-loss. A loss function is a formula used to compute how "good" your machine learning prediction is. In regards to ...

FXEZ's Quantitative Research In R

Indeed, this is one of the inputs I use in my conv nets, for the minute-by-minute sources. I'm now trying to integrate sparser sources (hour-by-hour or longer). Also, related to the above discussion, the loss function can be a bit tricky to define. ...

FXEZ's Quantitative Research In R

That's only a problem for low frequency strategies. You just showed above that a HFT strategy (ie: lots of samples) quickly converges. To get back to the edge question, anybody here using anything beside level-1 price data?

FXEZ's Quantitative Research In R

Great post. A few comments. The standard name for this is volatility drag. As with all summaries, some people will be satisfied by this, others will not. For example, if you trade a portfolio of strategies, it's very important to know the ...

FXEZ's Quantitative Research In R

Nice discussion here. Playing with random numbers only gets you so far. What about edges or real market data analysis?

FXEZ's Quantitative Research In R

If you are a programmer this is a pretty simple indicator to write. I also use something like this.

Real Volume Indic + OrderBook

This indicator was created by Mediator, see his thread - url By his description, I think it uses the data from here - url

Real Volume Indic + OrderBook

What kind of machine learning? Can you give more detail?

Are there any successful Traders in Forex Factory?

It's hard to trade the futures market without at least an $10K account. Not sure how many retailers can put up that sum.

What is the most important piece of advice you've received?

Can you post a backtest of it running on USD/JPY?

Testing Needed on Two Great Experts

Then you can write a book, appear on TV and tour the world speaking about what you learned, like Jerome Kerviel. Of course, while being paid for it

I plan to quit forex!