Search results

  1. dtrader98

    Shall I get some tips about useing Machine Learning on trading?

    What I mean is that if your objective is to forecast big price swings, you might be better off studying finance, statistics, and or time series modeling first. It might give you a better foundation to start with.
  2. dtrader98

    Shall I get some tips about useing Machine Learning on trading?

    To OP, If you are looking for 'big swings,' it is fairly well known that swings or volatility are easier to forecast than direction. The hard part is getting both. You could start to look into GARCH time series modeling to further explore that. People still seem to be stuck on thinking that a...
  3. dtrader98

    Neural Networks Revisited

    You had a lot of really good observations and commentary. I too found myself on a similar path which required really understanding what ML algorithms are trying to accomplish, how they go about it, and more importantly what are their limitations. One big limitation is that common objective/loss...
  4. dtrader98

    Neural Networks Revisited

    Not an easy solution at all as you are over-simplifying the problem. Even if you discretize the data for classification, the problem of stability will still persist. And it's not trivial to properly define and discretize the data sets to give good - stable - results. To put it in some...
  5. dtrader98

    Neural Networks Revisited

    Interesting discussion. But I would caution making the analogy to handwritten digits. One problem with the comparison is that the digits have an underlying and differentiating structure that is stable across many samples. Most of the textbook examples of success have underlying data that is...
  6. dtrader98

    Wanted Book: "The Greatest Bull Market in History" by Martin Armstrong

    As I said, if you accept that a big part of his secret equation dealt with 8.6 years, it is easy to convince yourself of its truth by simply overlaying vertical lines every 8.6 years on a long term plot of Gold or markets and see if it coincides at all with any major turning points in the last...
  7. dtrader98

    Wanted Book: "The Greatest Bull Market in History" by Martin Armstrong

    Interesting thread, but if anyone buys into it... it seems that the magic premise has already been disclosed -- 8.6 year repeatable cycles calling turning points (8.6year * 365 days/year) ~ 3140 days or 1000*pi It should be fairly easy to construct a plot with 8.6 yr interval overlays to...
  8. dtrader98

    10% success rate is better than 60% success rate?

    What you've shown is very few people here have even a rudimentary understanding of probability...
  9. dtrader98

    10% success rate is better than 60% success rate?

    1-P(correct.direction) = P(wrong.direction) 1 - 0.1 = 0.9 just flip prediction sign of strategy 2 0.9 >> 0.6 I'll take the 10% strategy any day; where can I get one?
  10. dtrader98

    Machine Learning Course at Stanford University

    It will be pretty tough to follow much of the ML literature without at least a basic understanding/exposure to vectors and matrices. Ng. does a great job of providing a preliminary understanding of how to read and apply much of the required notation. One of the great features of this course is...
  11. dtrader98

    Do large banks and institutions use TA to profit?

    https://www.quora.com/Do-large-trading-firms-investment-management-firms-large-banks-and-or-hedge-funds-use-technical-analysis
  12. dtrader98

    Basic Strategy to earn 10% yearly?

    Have a look at some of the papers at the top of this list. You sound pretty adept at programming, you could build one of the systems you find appealing and share the results here.
  13. dtrader98

    Need third party software for validation and statistics

    Have a look at http://www.portfolioworkstation.com/ Might be what you are looking for. You can ask the developers how to import local files for your individual systems. They might still roam around here, but you could also contact them via the site above. Good Luck.
  14. dtrader98

    The Big Short is coming out next week

    Great Movie. Wasn't over the top like Wolf of Wall Street. A bit more on the serious side, with the perceived nutcases getting the last laugh. Great performances by Bale and Carell.
  15. dtrader98

    T/A Fails Time and Time Again - Why?

    There are a lot of ways to reduce the influence of time. An obvious method is to resample or discretize the data at different intervals (asynchronous for example). This 'CAN' also help the math and probabilities work in your favor.
  16. dtrader98

    Some good book about Data Mining by MatLab?

    Great book of matlab illustrations, it is a companion to the author's text. He has a more recent matlab based text as well, but I don't know how well the matlab examples are presented. There aren't many data mining books on trading. You are better off finding trading oriented examples...
  17. dtrader98

    yahoo finance down?

    It's back. First time I've seen yahoo down -- in their own area, nevertheless.:rolleyes:
  18. dtrader98

    yahoo finance down?

    Anyone getting this? Firefox can't find the server at www.yahoo.com Firefox can't find the server at finance.yahoo.com edit. odd. isitdownright now shows this website is down just for you.... with a few complaints from NoCal
  19. dtrader98

    The Mathematician who Cracked Wall Street

    http://www.institutionalinvestorsalpha.com/Article/3364716/The-Morning-Brief-The-Secret-To-Medallions-Returns-Leverage.html
Back
Top