Search results

Yes...it's C# .NET Core. Send me a PM if you write C# code and would like to try it out.

There are some rules in that system that I cannot currently support. I am getting my product ready for a beta release so I will have to revisit testing the turtle system at another time.

Currently I use all data from SPY for signal/strategy formulation and test each strategy against SPY, QQQ and EEM where all the data is loaded in memory. Out of the hundreds of thousands that might be tested, there might only be a couple of hundred that go on to the next phase. 2 x ATR(14)...

What are the complete rules of the system?

I said the process is easy to do. Writing the platform to do this was certainly not easy to do. In and out of sample data is used for testing to minimize curve fitting.

Here is how I determine if an entry signal has an edge. This process is mostly automated so it is super easy to do. 1. Run Machine Learning routine on in sample data where strategies generated have a limit order and a stop order that are 2 x ATR(14) away from the point of entry. 2. Filter...

Keep in mind that when "scalping for cents" you will be competing against algos running on machines co-located with the exchanges. What do you expect your competitive advantage to be?

That could work, but fortunately someone has already been kind enough to take me up on my trade :)

@Kevin Schmit , @traider You convinced me! Better to have raw data and full control over the "stitching" algorithm.

Minimum order is $1000 at www.tickdata.com. If I get no takers on my offer I will buy data as needed.

I understand. Ideally the data would be pre-stitched with the knowing of the limitations that entails. I am not looking for a perfect solution, just a enough to prove my technology.

Yes...at some point is will need a proper subscription that can be at least updated daily (my platform is not a live trading platform so realtime is not necessary).

I am building a machine learning backtesting platform (C# .NET Core) and it currently supports EOD data. My next step is to add intra-day (1 min) futures data support. I have seen two commercially available products similar to the platform I am building and they range in price from $5000 to...

Depends on the expected volatility of the returns.

C# or Python. You are going to find C# more prevalent with commercial trading platforms where as there are a ton of open source python packages for trading.

Here is what I can offer. My proof of concept version of my Machine Learning backtesting platform (C# .NET Core) is complete and I am gearing up to leave my current job to focus full time on getting the platform production ready. The platform does not use any deep learning algos but instead...

Thanks for the responses. I will ignore interest rates of the risk free return. I plan to commercialize my platform so industry standard is what I am looking for. Thanks!

Assuming different values for "risk free rate of return" were used for each period, then the rate would be a negative value in that case. I am less concerned with having a theoretically "pure" calculation of the Sharpe ratio then matching what other platforms do (Tradestation, etc..) so that...

Sharpe ratio = (Average Portfolio Return - Risk free rate of return) / STDEV of returns From my research, it looks like the 3 month T-bills rate is considered the risk free rate of return. My question is do I need to determine the T-bill rate for each time period in the calculation? Looking...

Man...good catch!! haha