Below is the 1 week forward forecast of the following currencies and futures:
My neural net models forecast that prices will either close UP or DOWN next Friday (9/26) from the previous Friday’s close .
Here’s another asset class where you really don’t need a neural net to tell you the trend is up. All you need is an understanding on how governmental policy drives currency depreciation.
It’s old news now but the EURUSD currency pair traded above $1.43 for the first time (it’s at $1.4280 right now) yesterday. Weak earnings from Bank of America yesterday drove speculation that the Fed would cut interest rates one more time at their Oct 31st meeting.
A weak economic recovery (IMHO), massive deficits, an unpopular war, a misgiuded administration, and a former sellout of a Federal Reserve Chairman, have all contributed to a bleak outlook for the dollar. Sure we’ll have short term fluctuation’s where the USD might strengthen but in the longterm I would remain long the Euro and short the Dollar.
How can a previously low rate of 5.25% (now 4.75%) derail this fantastic economic expansion we are having?
Good Morning! Today’s breakout scan is:
This one is a huge gapper and I would be very careful entering a position. Over time these gaps tend to close.
Howard confirmed my thoughts, Chinese related stocks have gone parabolic. I used to trend follow FXI using one of my neural net models but I got busy and forgot to update it. You don’t need a neural net to tell you that the trend continues to be up, but neural net models give you an idea if that sell-off is really a “buy in” point or a “get out of this stock” signal.
I think I’m going to dig out my old FXI neural net model and post the results to the member section later today.
Good Morning!
Today I’m posting the breakout scan in the non-member section! I’m back to posting my regular schedule so if you want to see these daily posts, you’ll have to join as a member, its FREE.
Today’s breakout stock is Aluminum Corp. of China Limited (ACH). I’ve followed ACH in the past because of the commodity/China play that’s been going on for years now. Here’s a nice chart.
Just a word of caution, China related stocks have all gone wild lately so a massive pullback could happen.
This chart says it all, we're possibly entering another phase of elevated volatility because of earning season, the fear of recession, and the continued unraveling of the subprime mess. In times of fear we have to be greedy but not abandon our risk management!
I’ve still been keeping an eye on the markets while being on hiatus. The markets seem to be entering an unstable phase right now and my proprietary volatility indicator is creeping higher. Whether or not we’ll see another BUY signal soon in the coming days is a bit too early to tell, but the overall volatility pattern is pointing to a lower trend. For now we’ll take a wait and see attitude (I’ll post a current snapshot of the indicator in the members section later this morning).
The interesting thing to note is yesterday’s oil price. It’s slowly marching toward $100 a barrel with most of the gains coming from the Turkish/American row over the Armenian genocide. Without getting political here, and I do try to keep my political opinions on the down low here, I really do believe that Turkey was committing genocide against the Armenians.
Perhaps a shutdown of American forces using Turkish Air Bases to deliver supplies to the Troops in Iraq will stop and force us to come home sooner, but I digress now.
Sarah left a comment about modeling the microstructure of financial time series data. I think she means “high frequency data” which is what all the tick and sales data is commonly referred too. She specifically asked:
I’ve never modeled this type of data because I don’t have access to it so, unfortunately, I don’t have plots or figures to share with her. However, I did think about how to set up this type of experiment and what the challenges might be.
I would think the hardest part of modeling this data would be to figure out what are the important patterns you want Rapidminer to look for. My guess would be that you want to know the price outcome when similar patterns of large block buying/selling occurs before the stock rises or falls rapidly. It make sense right? If Goldman Sachs starts buying 10,000 shares of XYZ, other traders will get jump on.
The biggest challenge would be to find those large blocks (possibly through a filter using Excel) and tag those records with a nominal or numerical label. Of course this would present itself as an insane task if you had thousands of records of data for hundred’s of stocks over a month’s time! To overcome this, I would suggest to mine your data at a higher level first, such as identifying large volume and large moving stocks, then tag them with a label (UP, DOWN, INTERESTING CANDIDATE, etc) and then select those for your final analysis.
This problem is nothing more than trying to find a needle in a haystack but has its merits, after all a lot of traders I know who read the tape do quite well using their biological neural network. :)
FYI, I would start out using a classification operator in Rapidminer, then maybe a backpropogation operator.
I had a death in the family that I have to attend to so posting in the member section and on this blog is temporarily on hiatus. I should return later this week.
We have a flexible spending account that we use for all kinds of out of pocket stuff from prescriptions to co-pays. I’ll check into this for next year!
read later and comment.
 More Ron Paul stuff
(tags: government ronpaul2008)
While the rest of world tears down their dams because of the ecological disaster they bring, China is building dams.
(tags: China environment economy)
More stuff on objectivity
(tags: aynrand objectivism)
I read last night that Ugly has taken a full time programming position and is leaving daytrading behind. I admit that I feel sad that he won’t be daytrading anymore but, in my opinion, he would dishonor his ideals of capitalism if he didn’t maxmize his skills as a programmer.
I’ve often given thoughts to this as well, part of me wants to make a move to trading full time for either a hedge fund or myself, and the other part of me wants to open a civil engineering business in my town. I haven’t done either yet because I’m good at what I do, being a consultant in the transportation industry. So for him right now the best option was to take this job, maximize his income, and continue with position trading (which is what I like to do).
Although he’ll be working for the man again, I think he realized that sometimes these boring jobs can yield a steady income for you and aren’t that bad if your a professional. I hope that eventually he’ll either save up a fortune and then start trading again or start his own programming company designing ATS’s for hedge funds.
Ugly, I say BRAVO! Good luck in your new endeavor and I hope you keep your site going!
Good Morning! Only one stock made it the the breakout scan party and it is:
The markets were psychotic yesterday! The went from all time highs to a big selloff. I got caught in part of that action, my position in CDS got violently stopped out. I should’ve known something was up when my position in EURUSD also was violently stopped out. I expect these kind of swings in the Forex market but I wasn’t expecting that in the stock market yesterday!